Knowledge graph embedding involves learning representations of entities—the vertices of the graph—and relations—the edges of the graph—such that the resulting representations encode the known factual information represented by the knowledge graph and can be used in the inference of new relations. We show that knowledge graph embedding is naturally expressed in the topological and categorical language of cellular sheaves: a knowledge graph embedding can be described as an approximate global section of an appropriate knowledge sheaf over the graph, with consistency constraints induced by the knowledge graph’s schema. This approach provides a generalized framework for reasoning about knowledge graph embedding models and allows for the expression of a wide range of prior constraints on embeddings. Further, the resulting embeddings can be easily adapted for reasoning over composite relations without special training. We implement these ideas to highlight the benefits of the extensions inspired by this new perspective.

Living in an uncertain world, nearly all of our decisions are made with some degree of uncertainty about the consequences of actions selected. Although a significant progress has been made in understanding how the sensorimotor system incorporates uncertainty into the decision-making process, the preponderance of studies focus on tasks in which selection and action are two separate processes. First people select among alternative options and then initiate an action to implement the choice. However, we often make decisions during ongoing actions in which the value and availability of the alternatives can change with time and previous actions. The current study aims to decipher how the brain deals with uncertainty in decisions that evolve while acting. To address this question, we trained individuals to perform rapid reaching movements towards two potential targets, where the true target location was revealed only after the movement initiation. We found that reaction time and initial approach direction are correlated, where initial movements towards intermediate locations have longer reaction times than movements that aim directly to the target locations. Interestingly, the association between reaction time and approach direction was independent of the target probability. By modeling the task within a recently proposed neurodynamical framework, we showed that action planning and control under uncertainty emerge through a desirability-driven competition between motor plans that are encoded in parallel.

A fundamental question in neuroscience is how the brain creates an internal model of the world to guide actions using sequences of ambiguous sensory information. This is naturally formulated as a reinforcement learning problem under partial observations, where an agent must estimate relevant latent variables in the world from its evidence, anticipate possible future states, and choose actions that optimize total expected reward. This problem can be solved by control theory, which allows us to find the optimal actions for a given system dynamics and objective function. However, animals often appear to behave suboptimally. Why? We hypothesize that animals have their own flawed internal model of the world, and choose actions with the highest expected subjective reward according to that flawed model. We describe this behavior as {\it rational} but not optimal. The problem of Inverse Rational Control (IRC) aims to identify which internal model would best explain an agent's actions. Our contribution here generalizes past work on Inverse Rational Control which solved this problem for discrete control in partially observable Markov decision processes. Here we accommodate continuous nonlinear dynamics and continuous actions, and impute sensory observations corrupted by unknown noise that is private to the animal. We first build an optimal Bayesian agent that learns an optimal policy generalized over the entire model space of dynamics and subjective rewards using deep reinforcement learning. Crucially, this allows us to compute a likelihood over models for experimentally observable action trajectories acquired from a suboptimal agent. We then find the model parameters that maximize the likelihood using gradient ascent. Our method successfully recovers the true model of rational agents. This approach provides a foundation for interpreting the behavioral and neural dynamics of animal brains during complex tasks.

The representations learned by deep neural networks are difficult to interpret in part due to their large parameter space and the complexities introduced by their multi-layer structure. We introduce a method for computing persistent homology over the graphical activation structure of neural networks, which provides access to the task-relevant substructures activated throughout the network for a given input. This topological perspective provides unique insights into the distributed representations encoded by neural networks in terms of the shape of their activation structures. We demonstrate the value of this approach by showing an alternative explanation for the existence of adversarial examples. By studying the topology of network activations across multiple architectures and datasets, we find that adversarial perturbations do not add activations that target the semantic structure of the adversarial class as previously hypothesized. Rather, adversarial examples are explainable as alterations to the dominant activation structures induced by the original image, suggesting the class representations learned by deep networks are problematically sparse on the input space.

Intensive summer schools often provide strong students with career-changing impact, teaching them the art of the trade, letting them understand the logical underbelly of a field, and connecting them with an elite circle of peers and field leaders. Indeed, many professors attribute considerable aspects of their growth as a scientist to such schools. Such summer schools are an essential service to the community. A well-run summer school combines many of the aspects that jointly define students overall success. Eight years of organizing the annual two-week Computational Sensory-Motor Neuroscience (CoSMo, http://www.compneurosci.com/CoSMo) summer school has allowed us to experiment with different approaches and evaluate teaching outcomes, and we have seen rather clear patterns. Many new schools are started each year, only some move on to ongoing success, and the vast majority take a while until they reach very good ratings (our ratings are still increasing but approaching 10/10). Focusing on the student experience, we present a set of 10 simple rules to help you organize better summer schools that are more useful to students.We organize summer schools despite the considerable cost in terms of money and effort associated with them. We do this because we want to improve the field. Understanding the students and the change we want to effect is essential to being effective. For example, CoSMo mostly serves the objective of improving the way the field handles data and computation. Everything else derives from this objective. Teaching objectives should thus be defined by answering the following questions: What is missing in the field? What are the educational bottlenecks in the field? Where would we like the field to move? We should think of summer schools not as a generic way of teaching students but a specific way of effecting the change the field needs. Organizing a summer school is a way of leading the change you want to see.Knowing the students also implies not overloading them. The learning experience is far better when students learn material that they can realistically acquire than if an overly ambitious program instead teaches the students a little bit of many things without giving them important new skills. A summer school is no replacement for an education in science. It is a boost and a little bit of a push into the right direction.Crucial to the success of a teaching objective is the recruitment of pedagogically outstanding lecturers. Those individuals do not have to be the biggest names in the field; rather, they should be good teachers and should have the required hands-on practical knowledge to tutor participants. This said, students are attracted by faculty stars, so consider a healthy balance between fame and pedagogy. It is often useful to recruit additional teaching assistants if necessary to provide a high teacher-to-student ratio where each student can receive individualized attention. Often there are also experts among the participants, and one can take advantage of impromptu peer mentoring approaches. Fewer educators are better than many so that a coherent teaching framework can be applied over one to two days for each lecturer team. If multiple lecturers coteach a topic, true coteaching can be tremendously beneficial (but requires serious initial organization). We found that reducing the number of lecturers was almost universally associated with improved perceived quality of education ratings.Summer school participants usually come with a broad variety of educational backgrounds and can be at different career stages. It is thus important to design the summer school teaching content in a way that provides enough introductory material in order to equalize knowledge before more specialized or in-depth topics are covered. Our experience shows that about half the content of the summer school should be structured to convey the basics of a research field. These basics should ideally be taught by a small team of instructors (e.g., the way the three organizers of CoSMo do this) to ensure maximum coherence and coordination of content. Indeed, the content should be selected with at least two criteria in mind: it should level the ground for the following guest lecturers, who typically cover more specialized, in-depth content, and it should provide a coherent but critical perspective of current approaches in the field, including philosophical considerations.A perennial problem when teaching the basics is how to provide the more advanced students with good learning opportunities while helping weaker students advance. We found that keeping tutorials multilevel can be good at solving this issue. First, the advanced students can be assigned to help the less advanced ones at certain times. Second, it is often possible to provide an extra-hard problem in the same tutorial content. When we teach, we often have the hard problems at the bottom of the slide and the main ones in the middle.The aspect that sets a summer school apart from university-based teaching, lectures at conferences, and reading material is that due to the targeted topic and small number of students at a summer school, we can teach skills instead of material. Of course, some lecturing is important to introduce certain concepts and background. In a tutorial, students can learn how to solve problems in a way that will almost immediately allow them to replicate those skills back in their own lab. We found that in computational neuroscience, assigning more than half of the time to tutorials considerably improves what students learn.We also found that switching to a microlecture-tutorial format considerably improved outcomes. We teach a concept for a few minutes, and then for about the next 10 minutes, students immediately use what they just learned to solve a concrete problem that they could encounter in their own lab. This immediate link between knowledge and its application makes it both easier to attend the lecture because it will become relevant knowledge in 5 minutes. It is also easier for students not to get lost. The application makes it easy for them to see what they have not understood. Learning outcomes are optimized through active learning. Problem-based learning tutorials are best because they require critical thinking and the development of logical solutions. They implicitly force participants to ask the right questions, identify assumptions, and make hypotheses explicit. This can be a slow process, but it ensures a profound and practical understanding. Also, whenever possible, choose a single data set or problem for participants to work on from different angles in order to reduce introduction time. Thus, often when it comes to selecting course content, less is more.The venue should also be adapted to the teaching objectives. Interactive classrooms with round tables, lots of whiteboard space, breakout rooms, and audio-video equipment in many cases greatly increases teaching efficiency. It is truly helpful if the more advanced students can help those who are less advanced understand the material. An open design (e.g., with round tables) makes it easy for students to interact with many peers.We also found that switching activities is important to keep up participants' energy and attention span. Frequent switching between lectures and tutorials, switching between lecturers, switching groups for tutorial work, taking breaks, and interjecting special activities (e.g., sports, a special lecture, an open discussion, telling an anecdote) all help to increase the teaching outcomes.Tutorials allow students to work on only small problems. A small group project (three to five group members are ideal) that spans the entire duration of the summer school allows a more in-depth treatment of a selected topic. It also fosters more creativity, additional individualized teaching opportunities, and opportunities for participants to more deeply network with other students with whom they have the most in common. For most summer schools that we know of, combining these two timescales of learning is perceived as productive.Importantly, for group projects to be truly productive, it is essential that they are guided and tutored in the right way. Students need considerable guidance at multiple points along the way. First, it greatly helps if the group generation process is guided. Students should build groups that cover complementary skills while having common interests. Group parity should also be targeted because it leads to better group dynamics. Second, it is essential that group projects are tutored, but in a way that lets the participants steer them. The students can often learn a lot from learning why a given project is not a good group project. Third, it needs a final set of maximally public presentations so that the students have the sense that they are working toward an important goal. To maximize this effect, we convinced those at one of our field's main annual conferences to automatically accept the best paper presented at our summer school in a year. Moreover, CoSMo summer projects regularly end up being published as scientific papers in established journals.The pace for the entire summer school, and in particular the group projects, is set in the first two days or so. Long work hours (e.g., 9:00 a.m. to 11:00 p.m.) create group cohesion (through “suffering” together) and promote a community spirit that is fertile for learning, ideas, and collaboration. This atmosphere can be enhanced by providing an immersive learning environment where lecturers and tutors are available at all times. Make sure enough time is available for group projects.Teaching materials, including lectures, tutorials, solutions, and additional resources, should be publicly shared, for example, on a wiki site (e.g., http://compneurosci.com/wiki/index.php/CoSMo) or www.OSF.io. This crucial component has many benefits. It is, of course, useful for students to always have access to all materials. It is also useful for instructors to see what previous materials have been covered. More important, open access of materials is immensely useful for the community and in high demand. It is one way to extend the impact of a summer school far beyond the limited group of those attending. Other professors will use tutorial and lecture materials for their own classes. Researchers have a means to learn new approaches on their own, which can tremendously accelerate a field's research endeavor, especially when example code from tutorials is advanced enough that it can be directly applied to research questions. Finally, a public written trace is also useful for summer school lecturers to keep a good institutional memory. It is critical to remember over the years what has been taught, what has worked, and what needs to be improved (see also rule 10).In fact, many of the materials developed for CoSMo ended up being used more broadly across the field. For example, a tutorial aimed at teaching multivoxel pattern analysis ended up being a crucial resource for teaching in the entire field (http://www.cosmomvpa.org/). In many ways, the online materials are a continuation of the summer school itself.A summer school is a unique networking event that can build lifelong professional relationships. It is thus important to promote networking and have enough unstructured time available, even if that means prolonged lunch and dinner breaks. This can be done in many ways: through creating mailing lists, blogs, and forums; using social media; and organizing group events, (for example, an outing after the first week of the school, such as sightseeing or sports activities). Networking should not be limited to participants but should include all lecturers.Our alumni organize get-togethers at the big national conferences. They share news of personal progress on the Facebook page for the course session they attended. They hire one another once they become professors. And they often end up collaborating with one another later in their careers. Keeping the network in place after a summer school is crucial to the success of the participants.We found a simple yet critical way to increase the effectiveness of the summer school. A problem for probably most of our students is access to research supervisors in their home universities. The students may have a supervisor, but that person may not have much time to give to his or her students. In addition, they have a conflict of interest as mentors. Therefore, having one-on-one access at the summer school to their field's leaders is incredibly valuable to these students.We thus ask all students which of the professors they most would like to meet individually. Our guest lecturers coteach, each staying for two days but teaching only for one. The remaining time can then be used for a large number of one-on-one slots. Being able to sign up for one of these meetings, which last for 15 to 30 minutes, is one of the highlights for CoSMo attendees. Indeed, some have told us that this was the highlight of the school. The goal of these one-on-one meetings is to allow participants to establish a personal relationship with established researchers in their field. It allows participants to ask questions in a private setting while having the full attention of the experts. Conversation topics can range from career advice to feedback on research projects, work-life balance, or recruitment interviews. Other schools achieve the same aims simply by having faculty around for a long time and allocating a lot of time for unstructured networking.Organizing and running a summer school is a lot of work, and the schools themselves are tiring for lecturers, attendees, and the organizers. In order to avoid burnout, maintaining a fun and supportive environment is crucial. Organizers and lecturers need to bring and share positive energy. Positive energy is contagious, and participants draw from the lecturers' energy. Make sure to maintain this positive energy. The emotional side of a summer school is essential. Happy lecturers come again, happy students spread the word and successfully network, and happy organizers will be more willing to go through all that work again next year.Positive energy can be cultivated in a number of ways and should be spread from the beginning. One way is to spend time with your co-organizers and lecturers without students, even if that means less available networking time. It is essential to be there for one another as the teaching team but also essential to see the students as partners in learning. And, quite possibly, we should celebrate a summer school well run. By coteaching and co-organizeing with people we like, the fun will spill over to the participants. It also helps to plan for some fun bonding activities (e.g., sports, games) and make sure there is time for relaxation (e.g., cultural activities, day off, pub night), and not to overwhelm you or the participants.Successful summer schools learn from their mistakes and improve over the years, So ask for feedback from participants. Students often understand what would have helped them. After the school, thier feedback can be followed up with questions asked through Google Forms. The feedback forms should be a mix of rating scales to get participants' overall impressions on what was good and what was not and free-form text for them to provide their feedback about the individual school activities. For example, you can ask separately about lecture versus tutorial content for each teaching component or each lecturer. What was the difficulty level? Did participants feel they really learned something? What improvements could be made?Once feedback has been collected, analyze the ratings and suggestions. Often you need to read between the lines to identify the underlying causes of negative feedback or even to understand constructive suggestions. Always try to improve the summer school. Even after running CoSMo for eight years, we still see room for improvement. A research community is not static, and thinking as well as techniques evolve. Feedback also allows us to identify unmet expectations and make adjustments based on the direction the field is heading in.We thank Pascal Wallisch, Terry Sejnowski, and Adrienne Fairhall for helpful feedback. We also thank all 2011–2018 CoSMo attendees for their constructive (anonymous) feedback that has tremendously helped us shape these 10 simple rules.

The vast majority of recommender systems model preferences as static or slowly changing due to observable user experience. However, spontaneous changes in user preferences are ubiquitous in many domains like media consumption and key factors that drive changes in preferences are not directly observable. These latent sources of preference change pose new challenges. When systems do not track and adapt to users' tastes, users lose confidence and trust, increasing the risk of user churn. We meet these challenges by developing a model of novelty preferences that learns and tracks latent user tastes. We combine three innovations: a new measure of item similarity based on patterns of consumption co-occurrence; model for spontaneous changes in preferences; and a learning agent that tracks each user's dynamic preferences and learns individualized policies for variety. The resulting framework adaptively provides users with novelty tailored to their preferences for change per se.

In many problems, we would like to find relation between data and description. However, this description, or label information, may not always be explicitly associated with the data. In this paper, we deal with the data with incomplete label information. In other words, the label only represents a general concept of a bag of data vectors instead of a specific information of one data vector. Our approach assumed that the feature vectors generated from the bag of data can be partitioned into baglabel relevant and irrelevant parts. Under this assumption, we give an algorithm that allows for efficiently extracting meaningful features from a large pool of features, and learning a multiple instance based predictor. We applied our algorithm to the monkey fixation data to predict the monkeys' quit behavior. Our algorithm outperforms other standard classification methods such as binary classifier and one-class classifier. In addition, the microsaccade is interpreted from a large set of features using our method. We find that it is the most effective element to predict the quit behavior.

Studies have shown that the recommendation of unseen, novel or serendipitous items is crucial for a satisfying and engaging user experience. As a result, recent developments in recommendation research have increasingly focused towards introducing novelty in user recommendation lists. While, existing solutions aim to find the right balance between the similarity and novelty of the recommended items, they largely ignore the user needs for novelty. In this paper, we show that there are large individual and temporal differences in the users' novelty preferences. We develop a regression model to predict these dynamic novelty preferences of users using features derived from their past interactions. Finally, we describe an adaptive recommender,~\emph{adaNov-R}, that adapts to the user needs for novel items and show that the model achieves better recommendation performance on a metric that considers both novel and familiar items.

Recommendation methods have mainly dealt with the problem of recommending new items to the user while user visitation behavior to the familiar items (items which have been consumed before) are little understood. In this paper, we analyze user activity streams and show that user's temporal consumption of familiar items is driven by boredom. Specifically, users move on to a different item when bored and return to the same item when their interest is restored. To model this behavior we include two latent psychological states of preference for items - sensitization and boredom. In the sensitization state the user is highly engaged with the item, while in the boredom state the user is disinterested. We model this behavior using a Hidden Semi-Markov Model for the gaps between user consumption activities. We show that our model performs much better than the state-of-the-art temporal recommendation models at predicting the revisit time to the item. Moreover, we attribute two main reasons for this: (1) recommending items that are not in the bored state for the user, (2) recommending items where user has restored her interests.

Decisions involve two fundamental problems, selecting goals and generating actions to pursue those goals. While simple decisions involve choosing a goal and pursuing it, humans evolved to survive in hostile dynamic environments where goal availability and value can change with time and previous actions, entangling goal decisions with action selection. Recent studies suggest the brain generates concurrent action-plans for competing goals, using online information to bias the competition until a single goal is pursued. This creates a challenging problem of integrating information across diverse types, including both the dynamic value of the goal and the costs of action. We model the computations underlying dynamic decision-making with disparate value types, using the probability of getting the highest pay-off with the least effort as a common currency that supports goal competition. This framework predicts many aspects of decision behavior that have eluded a common explanation.

The goal of training is to produce learning for a range of activities that are typically more general than the training task itself. Despite a century of research, predicting the scope of learning from the content of training has proven extremely difficult, with the same task producing narrowly focused learning strategies in some cases and broadly scoped learning strategies in others. Here we test the hypothesis that human subjects will prefer a decision strategy that maximizes performance and reduces uncertainty given the demands of the training task and that the strategy chosen will then predict the extent to which learning is transferable. To test this hypothesis, we trained subjects on a moving dot extrapolation task that makes distinct predictions for two types of learning strategy: a narrow model-free strategy that learns an input-output mapping for training stimuli, and a general model-based strategy that utilizes humans' default predictive model for a class of trajectories. When the number of distinct training trajectories is low, we predict better performance for the mapping strategy, but as the number increases, a predictive model is increasingly favored. Consonant with predictions, subject extrapolations for test trajectories were consistent with using a mapping strategy when trained on a small number of training trajectories and a predictive model when trained on a larger number. The general framework developed here can thus be useful both in interpreting previous patterns of task-specific versus task-general learning, as well as in building future training paradigms with certain desired outcomes.

Spontaneous devaluation in preferences is ubiquitous, where yesterday's hit is today's affliction. Despite technological advances facilitating access to a wide range of media commodities, finding engaging content is a major enterprise with few principled solutions. Systems tracking spontaneous devaluation in user preferences can allow prediction of the onset of boredom in users potentially catering to their changed needs. In this work, we study the music listening histories of Last.fm users focusing on the changes in their preferences based on their choices for different artists at different points in time. A hazard function, commonly used in statistics for survival analysis, is used to capture the rate at which a user returns to an artist as a function of exposure to the artist. The analysis provides the first evidence of spontaneous devaluation in preferences of music listeners. Better understanding of the temporal dynamics of this phenomenon can inform solutions to the similarity-diversity dilemma of recommender systems.

The nature of the neural codes for pitch and loudness, two basic auditory attributes, has been a key question in neuroscience for over century. A currently widespread view is that sound intensity (subjectively, loudness) is encoded in spike rates, whereas sound frequency (subjectively, pitch) is encoded in precise spike timing. Here, using information-theoretic analyses, we show that the spike rates of a population of virtual neural units with frequency-tuning and spike-count correlation characteristics similar to those measured in the primary auditory cortex of primates, contain sufficient statistical information to account for the smallest frequency-discrimination thresholds measured in human listeners. The same population, and the same spike-rate code, can also account for the intensity-discrimination thresholds of humans. These results demonstrate the viability of a unified rate-based cortical population code for both sound frequency (pitch) and sound intensity (loudness), and thus suggest a resolution to a long-standing puzzle in auditory neuroscience.

With rapid profusion of video data, automated surveillance and intrusion detection is becoming closer to reality. In order to provide timely responses while limiting false alarms, an intrusion detection system must balance resources (e.g., time) and accuracy. In this paper, we show how such a system can be modeled with a partially observable Markov decision process (POMDP), representing possible computer vision filters and their costs in a way that is similar to human vision systems. The POMDP representation can be optimized to produce a dynamic sequence of operations and achieve a tradeoff between time and detection quality, taking into account uncertainty in the filter predictions. In a set of experiments on actual video data, we show that our method can both outperform static “expert” models and scale to large dynamic domains. These results suggest that our method could be used in real-world intrusion detection systems.

Statistical decision theory axiomatically assumes that the relative desirability of different options that humans perceive is well described by assigning them option-specific scalar utility functions. However, this assumption is refuted by observed human behavior, including studies wherein preferences have been shown to change systematically simply through variation in the set of choice options presented. In this paper, we show that interpreting desirability as a relative comparison between available options at any particular decision instance results in a rational theory of value-inference that explains heretofore intractable violations of rational choice behavior in human subjects. Complementarily, we also characterize the conditions under which a rational agent selecting optimal options indicated by dynamic value inference in our framework will behave identically to one whose preferences are encoded using a static ordinal utility function.

As we move, the relative location between our hands and objects changes in uncertain ways due to noisy motor commands and imprecise and ambiguous sensory information. The impressive capabilities humans display for interacting and manipulating objects with position uncertainty suggest that our brain maintains representations of location uncertainty and builds compensation for uncertainty into its motor control strategies. Our previous work demonstrated that specific control strategies are used to compensate for location uncertainty. However, it is an open question whether compensation for position uncertainty in grasping is consistent with the stochastic optimal feedback control, mainly due to the difficulty of modeling natural tasks within this framework. In this study, we develop a stochastic optimal feedback control model to evaluate the optimality of human grasping strategies. We investigate the properties of the model through a series of simulation experiments and show that it explains key aspects of previously observed compensation strategies. It also provides a basis for individual differences in terms of differential control costs-the controller compensates only to the extent that performance benefits in terms of making stable grasps outweigh the additional control costs of compensation. These results suggest that stochastic optimal feedback control can be used to understand uncertainty compensation in complex natural tasks like grasping.

Determining distances to objects is one of the most ubiquitous perceptual tasks in everyday life. Nevertheless, it is challenging because the information from a single image confounds object size and distance. Though our brains frequently judge distances accurately, the underlying computations employed by the brain are not well understood. Our work illuminates these computions by formulating a family of probabilistic models that encompass a variety of distinct hypotheses about distance and size perception. We compare these models' predictions to a set of human distance judgments in an interception experiment and use Bayesian analysis tools to quantitatively select the best hypothesis on the basis of its explanatory power and robustness over experimental data. The central question is: whether, and how, human distance perception incorporates size cues to improve accuracy. Our conclusions are: 1) humans incorporate haptic object size sensations for distance perception, 2) the incorporation of haptic sensations is suboptimal given their reliability, 3) humans use environmentally accurate size and distance priors, 4) distance judgments are produced by perceptual "posterior sampling". In addition, we compared our model's estimated sensory and motor noise parameters with previously reported measurements in the perceptual literature and found good correspondence between them. Taken together, these results represent a major step forward in establishing the computational underpinnings of human distance perception and the role of size information.

Rigidity and reflectivity are important properties of objects, identifying these properties is a fundamental problem for many computer vision applications like motion and tracking. In this paper, we extend our previous work to propose a motion analysis based approach for detecting the object's rigidity and reflectivity. This approach consists of two steps. The first step aims to identify object rigidity based on motion estimation and optic flow matching. The second step is to classify specular rigid and diffuse rigid objects using structure from motion and Procrustes analysis. We show how rigid bodies can be detected without knowing any prior motion information by using a mutual information based matching method. In addition, we use a statistic way to set thresholds for rigidity classification. Presented results demonstrate that our approach can efficiently classify the rigidity and reflectivity of an object.

Studies of sequential decision-making in humans frequently find suboptimal performance relative to an ideal actor that has perfect knowledge of the model of how rewards and events are generated in the environment. Rather than being suboptimal, we argue that the learning problem humans face is more complex, in that it also involves learning the structure of reward generation in the environment. We formulate the problem of structure learning in sequential decision tasks using Bayesian reinforcement learning, and show that learning the generative model for rewards qualitatively changes the behavior of an optimal learning agent. To test whether people exhibit structure learning, we performed experiments involving a mixture of one-armed and two-armed bandit reward models, where structure learning produces many of the qualitative behaviors deemed suboptimal in previous studies. Our results demonstrate humans can perform structure learning in a near-optimal manner.

Perception is fundamentally underconstrained because different combinations of object properties can generate the same sensory information. To disambiguate sensory information into estimates of scene properties, our brains incorporate prior knowledge and additional "auxiliary" (i.e., not directly relevant to desired scene property) sensory information to constrain perceptual interpretations. For example, knowing the distance to an object helps in perceiving its size. The literature contains few demonstrations of the use of prior knowledge and auxiliary information in combined visual and haptic disambiguation and almost no examination of haptic disambiguation of vision beyond "bistable" stimuli. Previous studies have reported humans integrate multiple unambiguous sensations to perceive single, continuous object properties, like size or position. Here we test whether humans use visual and haptic information, individually and jointly, to disambiguate size from distance. We presented participants with a ball moving in depth with a changing diameter. Because no unambiguous distance information is available under monocular viewing, participants rely on prior assumptions about the ball's distance to disambiguate their -size percept. Presenting auxiliary binocular and/or haptic distance information augments participants' prior distance assumptions and improves their size judgment accuracy-though binocular cues were trusted more than haptic. Our results suggest both visual and haptic distance information disambiguate size perception, and we interpret these results in the context of probabilistic perceptual reasoning.

Due to noisy motor commands and imprecise and ambiguous sensory information, there is often substantial uncertainty about the relative location between our body and objects in the environment. Little is known about how well people manage and compensate for this uncertainty in purposive movement tasks like grasping. Grasping objects requires reach trajectories to generate object-fingers contacts that permit stable lifting. For objects with position uncertainty, some trajectories are more efficient than others in terms of the probability of producing stable grasps. We hypothesize that people attempt to generate efficient grasp trajectories that produce stable grasps at first contact without requiring post-contact adjustments. We tested this hypothesis by comparing human uncertainty compensation in grasping objects against optimal predictions. Participants grasped and lifted a cylindrical object with position uncertainty, introduced by moving the cylinder with a robotic arm over a sequence of 5 positions sampled from a strongly oriented 2D Gaussian distribution. Preceding each reach, vision of the object was removed for the remainder of the trial and the cylinder was moved one additional time. In accord with optimal predictions, we found that people compensate by aligning the approach direction with covariance angle to maintain grasp efficiency. This compensation results in higher probability to achieve stable grasps at first contact than non-compensation strategies in grasping objects with directional position uncertainty, and the results provide the first demonstration that humans compensate for uncertainty in a complex purposive task.

This work addresses the problem of building representative subsets of benchmarks from an original large set of benchmarks, using statistical analysis techniques. The subsets should be developed in this way to include only the necessary information for evaluating the performance of a computer system or application. The development of representative workloads is not a trivial procedure, since incorrectly selecting benchmarks the representative subset can produce erroneous results. A number of statistical analysis techniques have been developed for identifying representative workloads. The goal of these approaches is to reduce the dimensionality of the original set of benchmarks prior to identifying similar benchmarks. In this work we propose a combination of independent component analysis (ICA) and evolutionary algorithm (EA) as a more efficient way for reducing the computational complexity of the problem and the redundant information of the original set of benchmarks. Experimental results validate that the proposed technique generates more representative workloads than prior techniques.

We use graphical models and structure learning to explore how people learn policies in sequential decision making tasks. Studies of sequential decision-making in humans frequently find suboptimal performance relative to an ideal actor that knows the graph model that generates reward in the environment. We argue that the learning problem humans face also involves learning the graph structure for reward generation in the environment. We formulate the structure learning problem using mixtures of reward models, and solve the optimal action selection problem using Bayesian Reinforcement Learning. We show that structure learning in one and two armed bandit problems produces many of the qualitative behaviors deemed suboptimal in previous studies. Our argument is supported by the results of experiments that demonstrate humans rapidly learn and exploit new reward structure.

We present a semi-parametric model that describes pricing behaviors in a market environment, and we show how that model can be used to guide resource allocation and pricing decisions in an autonomous trading agent. We validate our model by presenting experimental results obtained in the Trading Agent Competition for Supply Chain Management.

Automatic detection of dynamic events in video sequences has a variety of applications including visual surveillance and monitoring, video highlight extraction, intelligent transportation systems, video summarization, and many more. Learning an accurate description of the various events in real-world scenes is challenging owing to the limited user-labeled data as well as the large variations in the pattern of the events. Pattern differences arise either due to the nature of the events themselves such as the spatio-temporal events or due to missing or ambiguous data interpretation using computer vision methods. In this work, we introduce a novel method for representing and classifying events in video sequences using reversible context-free grammars. The grammars are learned using a semi-supervised learning method. More concretely, by using the classification entropy as a heuristic cost function, the grammars are iteratively learned using a search method. Experimental results demonstrating the efficacy of the learning algorithm and the event detection method applied to traffic video sequences are presented.

This paper addresses the problem of selecting contact locations for grasping objects in the presence of shape and contact location uncertainty. Focusing on two-dimensional planar objects and two finger grasps for simplicity, we present a principled approach for selecting contact points by analyzing the risk of force closure failure. The key contribution of this paper is the development of a method that incorporates shape uncertainty into grasp stability analysis. We propose a grasp quality metric that can be used to identify stable contact regions in the face of shape and contact location uncertainty. The proposed method successfully distinguishes grasps that are equivalent without uncertainty, and we illustrate the properties of this technique with simulation experiments in two classes of objects.

Robust motion recovery in tracking multiple targets using image features is affected by difficulties in obtaining good correspondences over long sequences. Difficulties are introduced by occlusions, scale changes, as well as disappearance of features with the rotation of targets. In this work, we describe an adaptive geometric template-based method for robust motion recovery from features. A geometric template consists of nodes containing salient features (e.g., corner features). The spatial configuration of the features is modeled using a spanning tree. This paper makes the following two contributions: (i) an adaptive geometric template to model the varying number of features on a target, and (U) an iterative data association method for the features based on the uncertainties in the estimated template structure in conjunction with its individual features. We present experimental results for tracking multiple targets over long outdoor image sequences with multiple persistent occlusions. A comparison of the results of the data association method with a standard Mahalanobis distance gating applied to individual features is also presented

Perceptual Bistability refers to the phenomenon of spontaneously switching between two or more interpretations of an image under continuous viewing. Although switching behavior is increasingly well characterized, the origins remain elusive. We propose that perceptual switching naturally arises from the brain's search for best interpretations while performing Bayesian inference. In particular, we propose that the brain explores a posterior distribution over image interpretations at a rapid time scale via a sampling-like process and updates its interpretation when a sampled interpretation is better than the discounted value of its current interpretation. We formalize the theory, explicitly derive switching rate distributions and discuss qualitative properties of the theory including the effect of changes in the posterior distribution on switching rates. Finally, predictions of the theory are shown to be consistent with measured changes in human switching dynamics to Necker cube stimuli induced by context.

The performance of computer vision systems for measurement, surveillance, reconstruction, gait recognition, and many other applications, depends heavily on the placement of cameras observing the scene. This work addresses the question of the optimal placement of cameras to maximize the performance of real-world vision systems in a variety of applications. Specifically, our goal is to optimize the aggregate observability of the tasks being performed by the subjects in an area. We develop a general analytical formulation of the observation problem, in terms of the statistics of the motion in the scene and the total resolution of the observed actions that is applicable to many observation tasks and multi-camera systems. An optimization approach is used to find the internal and external (mounting position and orientation) camera parameters that optimize the observation criteria. We demonstrate the method for multi-camera systems in real-world monitoring applications, both indoor and outdoor.

The performance of systems for human activity recognition depends heavily on the placement of cameras observing the scene. This work addresses the question of the optimal placement of cameras to maximize the performance of these types of recognition tasks. Specifically, our goal is to optimize the quality of the joint observability of the tasks being performed by the subjects in an area. We develop a general analytical formulation of the observation problem, in terms of the statistics of the motion in the scene and the total resolution of the observed actions that is applicable to many observation tasks and multi-camera systems. A nonlinear optimization approach is used to find the internal and external (mounting position and orientation) camera parameters that optimize the recognition criteria. In these experiments, a single camera is repositioned using a mobile robot. Initial results for the problem of human activity recognition are presented.

This paper compares the ability of human observers to detect target im- age curves with that of an ideal observer. The target curves are sam- pled from a generative model which specifies (probabilistically) the ge- ometry and local intensity properties of the curve. The ideal observer performs Bayesian inference on the generative model using MAP esti- mation. Varying the probability model for the curve geometry enables us investigate whether human performance is best for target curves that obey specific shape statistics, in particular those observed on natural shapes. Experiments are performed with data on both rectangular and hexagonal lattices. Our results show that human observers’ performance approaches that of the ideal observer and are, in general, closest to the ideal for con- ditions where the target curve tends to be straight or similar to natural statistics on curves. This suggests a bias of human observers towards straight curves and natural statistics.

Modeling spatial context (e.g., autocorrelation) is a key challenge in classification problems that arise in geospatial domains. Markov random fields (MRF) is a popular model for incorporating spatial context into image segmentation and land-use classification problems. The spatial autoregression (SAR) model, which is an extension of the classical regression model for incorporating spatial dependence, is popular for prediction and classification of spatial data in regional economics, natural resources, and ecological studies. There is little literature comparing these alternative approaches to facilitate the exchange of ideas. We argue that the SAR model makes more restrictive assumptions about the distribution of feature values and class boundaries than MRF. The relationship between SAR and MRF is analogous to the relationship between regression and Bayesian classifiers. This paper provides comparisons between the two models using a probabilistic and an experimental framework.