We introduce a differentiable moving particle representation based on the multi-level partition of unity (MPU) to represent dynamic implicit geometries. At the core of our representation are two groups of particles, named feature particles and sample particles, which can move in space and produce dynamic surfaces according to external velocity fields or optimization gradients. These two particle groups iteratively guide and correct each other by alternating their roles as inputs and outputs. Each feature particle carries a set of coefficients for a local quadratic patch. These particle patches are assembled with partition-of-unity weights to derive a continuous implicit global shape. Each sampling particle carries its position and orientation, serving as dense surface samples for optimization tasks. Based on these moving particles, we develop a fully differentiable framework to infer and evolve highly detailed implicit geometries, enhanced by a multi-level background grid for particle adaptivity, across different inverse tasks. We demonstrated the efficacy of our representation through various benchmark comparisons with state-of-the-art neural representations, achieving lower memory consumption, fewer training iterations, and orders of magnitude higher accuracy in handling topologically complex objects and dynamic tracking tasks.

Automated surface anomaly detection is important in industry. The goal with this task is to classify the query image and its pixel as either “Normal” or “Anomaly” with high precision for industrial products. Unlike general two-class classification tasks, we can only obtain normal images (i.e., anomaly images cannot be obtained) for training because anomalies rarely occur in well-controlled production environments such as modern manufacturing factories. We propose a transfer-based anomaly detection method called Defect Representation Transfer-based Anomaly Detection (DRepT). This method can generate natural anomaly images for the target domain (i.e., real factory with only normal images) using knowledge of anomalies obtained in the source domain (i.e., known datasets with normal and anomaly images). We first focused on an anomaly image of an industrial product consisting of two elements: “background texture” and “defect representation”. At the source domain, a background texture image is generated from an anomaly image with texture invariance (i.e., defects are only removed) by using generative adversarial networks, and defect representation is modeled as the difference between an anomaly image and its background texture image with the newly proposed Gaussian mixture transmittance mask. At the target domain, anomaly images are generated by giving defect representation to normal images, and a anomaly detection model is finally trained. Compared with a method without real defects of other domains and a method based on pasting of the defect images, DRepT achieved highly precision.

Healthiness is a good old question in program logics that dates back to Dijkstra. It asks for an intrinsic characterization of those predicate transformers which arise as the (backward) interpretation of a certain class of programs. There are several results known for healthiness conditions: for deterministic programs, nondeterministic ones, probabilistic ones, etc. Building upon our previous works on so-called state-and-effect triangles, we contribute a unified categorical framework for investigating healthiness conditions. This framework is based on a dual adjunction induced by a dualizing object and on our notion of relative Eilenberg-Moore algebra. The latter notion seems interesting in its own right in the context of monads, Lawvere theories and enriched categories.

Abstract.We study about a method to describe knowledge for generating an adequate number of multiple-choice questions. We focus on the fact that instructors can easily explain concrete multiple-choice questions, even if they cannot describe the domain knowledge completely. We propose the Environment of Abstract Rule (EAR), which enables an instructor to describe abstract knowledge by explaining the difference among some concrete multiple-choice questions, and by representing the knowledge in the form of a diagram. In this paper, we describe the concept of EAR and report the results of a preliminary experiment in which we explored whether instructors could describe knowledge easily. As a result, we suggest that the EAR has the potential for generating appropriate knowledge.

Predictions of interactions between target proteins and potential leads are of great benefit in the drug discovery process. We present a comprehensively applicable statistical prediction method for interactions between any proteins and chemical compounds, which requires only protein sequence data and chemical structure data and utilizes the statistical learning method of support vector machines. In order to realize reasonable comprehensive predictions which can involve many false positives, we propose two approaches for reduction of false positives: (i) efficient use of multiple statistical prediction models in the framework of two-layer SVM and (ii) reasonable design of the negative data to construct statistical prediction models. In two-layer SVM, outputs produced by the first-layer SVM models, which are constructed with different negative samples and reflect different aspects of classifications, are utilized as inputs to the second-layer SVM. In order to design negative data which produce fewer false positive predictions, we iteratively construct SVM models or classification boundaries from positive and tentative negative samples and select additional negative sample candidates according to pre-determined rules. Moreover, in order to fully utilize the advantages of statistical learning methods, we propose a strategy to effectively feedback experimental results to computational predictions with consideration of biological effects of interest. We show the usefulness of our approach in predicting potential ligands binding to human androgen receptors from more than 19 million chemical compounds and verifying these predictions by in vitro binding. Moreover, we utilize this experimental validation as feedback to enhance subsequent computational predictions, and experimentally validate these predictions again. This efficient procedure of the iteration of the in silico prediction and in vitro or in vivo experimental verifications with the sufficient feedback enabled us to identify novel ligand candidates which were distant from known ligands in the chemical space.

We previously proposed a iris recognition system by a rotation spreading neural network (R-SAN net). The R-SAN net is suitable for orientation recognition of a concentric circular pattern such as iris image. The recognition characteristics of the R-SAN net for both learned and unlearned iris images were investigated. The RS-SAN net had fairly good orientation recognition characteristics only for learned irises, but not for unlearned irises. The recognized orientation for unlearned irises were heavily dispersed from the orientation of input iris although the orientation for learned irises were concentrated around learned orientation. By using the unique characteristics of orientation recognition, new recognition method with the imposter extraction using recognized orientation was developed. The experimental result of new recognition method indicated the false acceptance rate drastically decreased. The equal error rates obtained by the previous and proposed methods were 2.02% and 0.79%, respectively. The imposter rejection method using recognized orientation provided the effective improvement of iris recognition performance.

We previously proposed a rotation spreading neural network (R-SAN net). This neural net can recognize the orientation of an object irrespective of its shape, and its shape irrespective of its orientation. The characteristics of the R-SAN net are to spread information about the axis orientation of the object in relation to surrounding space by spreading weight with similar tuning characteristics to axis orientation neurons in the parietal cortex. The R-SAN net is suitable for orientation recognition of a concentric circular pattern such as iris image, because it uses polar conversion. Previously, variations of ambient lighting conditions affected iris detection. In this study, we introduced brightness normalization for accuracy improvement of iris detection in various lighting conditions. Brightness normalization provided high accuracy iris extraction in severe lighting conditions. We also attempted real-time individual identification with the iris patterns. In the recognition experiment, the R-SAN net combined with the minimum distance was able to accurately recognize the orientation and shape of iris images in arbitrary orientation. We suggest application of the R-SAN net as an iris recognition system.