Originally developed as a theory of consciousness, integrated information theory provides a mathematical framework to quantify the causal irreducibility of systems and subsets of units in the system. Specifically, mechanism integrated information quantifies how much of the causal powers of a subset of units in a state, also referred to as a mechanism, cannot be accounted for by its parts. If the causal powers of the mechanism can be fully explained by its parts, it is reducible and its integrated information is zero. Here, we study the upper bound of this measure and how it is achieved. We study mechanisms in isolation, groups of mechanisms, and groups of causal relations among mechanisms. We put forward new theoretical results that show mechanisms that share parts with each other cannot all achieve their maximum. We also introduce techniques to design systems that can maximize the integrated information of a subset of their mechanisms or relations. Our results can potentially be used to exploit the symmetries and constraints to reduce the computations significantly and to compare different connectivity profiles in terms of their maximal achievable integrated information.

This paper presents Integrated Information Theory (IIT) 4.0. IIT aims to account for the properties of experience in physical (operational) terms. It identifies the essential properties of experience (axioms), infers the necessary and sufficient properties that its substrate must satisfy (postulates), and expresses them in mathematical terms. In principle, the postulates can be applied to any system of units in a state to determine whether it is conscious, to what degree, and in what way. IIT offers a parsimonious explanation of empirical evidence, makes testable predictions concerning both the presence and the quality of experience, and permits inferences and extrapolations. IIT 4.0 incorporates several developments of the past ten years, including a more accurate formulation of the axioms as postulates and mathematical expressions, the introduction of a unique measure of intrinsic information that is consistent with the postulates, and an explicit assessment of causal relations. By fully unfolding a system's irreducible cause-effect power, the distinctions and relations specified by a substrate can account for the quality of experience.

The goal of out-of-distribution (OOD) detection is to handle the situations where the test samples are drawn from a different distribution than the training data. In this paper, we argue that OOD samples can be detected more easily if the training data is embedded into a low-dimensional space, such that the embedded training samples lie on a union of 1-dimensional subspaces. We show that such embedding of the in-distribution (ID) samples provides us with two main advantages. First, due to compact representation in the feature space, OOD samples are less likely to occupy the same region as the known classes. Second, the first singular vector of ID samples belonging to a 1-dimensional subspace can be used as their robust representative. Motivated by these observations, we train a deep neural network such that the ID samples are embedded onto a union of 1-dimensional subspaces. At the test time, employing sampling techniques used for approximate Bayesian inference in deep learning, input samples are detected as OOD if they occupy the region corresponding to the ID samples with probability 0. Spectral components of the ID samples are used as robust representative of this region. Our method does not have any hyperparameter to be tuned using extra information and it can be applied on different modalities with minimal change. The effectiveness of the proposed method is demonstrated on different benchmark datasets, both in the image and video classification domains.

Current face image retrieval solutions are limited, since they treat different facial attributes the same and cannot incorporate user’s preference for a subset of attributes in their search criteria. This paper introduces a new face image retrieval framework, where the input face query is augmented by both an adjustment vector that specifies the desired modifications to the facial attributes, and a preference vector that assigns different levels of importance to different attributes. For example, a user can ask for retrieving images similar to a query image, but with a different hair color, and no preference for absence/presence of eyeglasses in the results. To achieve this, we propose to disentangle the semantics, corresponding to various attributes, by learning a set of sparse and orthogonal basis vectors in the latent space of StyleGAN. Such basis vectors are then employed to decompose the dissimilarity between face images in terms of dissimilarity between their attributes, assign preference to the attributes, and adjust the attributes in the query. Enforcing sparsity on the basis vectors helps us to disentangle the latent space and adjust each attribute independently from other attributes, while enforcing orthogonality facilitates preference assignment and the dissimilarity decomposition. The effectiveness of our approach is illustrated by achieving state-of-the-art results for the face image retrieval task.

Augmenting neural networks with skip connections, as introduced in the so-called ResNet architecture, surprised the community by enabling the training of networks of more than 1,000 layers with significant performance gains. This paper deciphers ResNet by analyzing the effect of skip connections, and puts forward new theoretical results on the advantages of identity skip connections in neural networks. We prove that the skip connections in the residual blocks facilitate preserving the norm of the gradient, and lead to stable back-propagation, which is desirable from optimization perspective. We also show that, perhaps surprisingly, as more residual blocks are stacked, the norm-preservation of the network is enhanced. Our theoretical arguments are supported by extensive empirical evidence. Can we push for extra norm-preservation? We answer this question by proposing an efficient method to regularize the singular values of the convolution operator and making the ResNet's transition layers extra norm-preserving. Our numerical investigations demonstrate that the learning dynamics and the classification performance of ResNet can be improved by making it even more norm preserving. Our results and the introduced modification for ResNet, referred to as Procrustes ResNets, can be used as a guide for training deeper networks and can also inspire new deeper architectures.

Collaborative estimation of a sparse vector x by M potential measurements is considered. Each measurement is the projection of x obtained by a regressor, i.e., ym1/4 amTx. The problem of selecting K sensor measurements from a set of M potential sensors is studied where K ≫ M and K is less than the dimension of x. In other words, we aim to reduce the problem to an under-determined system of equations in which a sparse solution is desired. This paper suggests selecting sensors in a way that the reduced matrix construct a well conditioned measurement matrix. Our criterion is based on E-optimality, which is highly related to the restricted isometry property that provides some guarantees for sparse solution obtained by ℓ1minimization. The proposed basic E-optimal selection is vulnerable to outlier and noisy data. The robust version of the algorithm is presented for distributed selection for big data sets. Moreover, an online implementation is proposed that involves partially observed measurements in a sequential manner. Our simulation results show the proposed method outperforms the other criteria for collaborative spectrum sensing in cognitive radio networks (CRNs). Our suggested selection method is evaluated in machine learning applications. It is used to pick up the most informative features/data. Specifically, the proposed method is exploited for face recognition with partial training data.

The goal of data selection is to capture the most structural information from a set of data. This paper presents a fast and accurate data selection method, in which the selected samples are optimized to span the subspace of all data. We propose a new selection algorithm, referred to as iterative projection and matching (IPM), with linear complexity w.r.t. the number of data, and without any parameter to be tuned. In our algorithm, at each iteration, the maximum information from the structure of the data is captured by one selected sample, and the captured information is neglected in the next iterations by projection on the null-space of previously selected samples. The computational efficiency and the selection accuracy of our proposed algorithm outperform those of the conventional methods. Furthermore, the superiority of the proposed algorithm is shown on active learning for video action recognition dataset on UCF-101; learning using representatives on ImageNet; training a generative adversarial network (GAN) to generate multi-view images from a single-view input on CMU Multi-PIE dataset; and video summarization on UTE Egocentric dataset.

Recently, the promising aspects of compressive sensing have inspired new circuit-level approaches for their efficient realization within the literature. However, most of these recent advances involving novel sampling techniques have been proposed without considering hardware and signal constraints. Additionally, traditional hardware designs for generating non-uniform sampling clock incur large area overhead and power dissipation. Herein, we propose a novel non-uniform clock generator called Adaptive Quantization Rate (AQR) generator using Magnetic Random Access Memory (MRAM)-based stochastic oscillator devices. Our proposed AQR generator provides ~25-fold reduction in area, on average, while offering ~6-fold reduced power dissipation, on average, compared to the state-of-the-art non-uniform clock generators.

Reliable and efficient spectrum sensing through dynamic selection of a subset of spectrum sensors is studied. The problem of selecting K sensor measurements from a set of M potential sensors is considered where K ≪ M. In addition, K may be less than the dimension of the unknown variables of estimation. Through sensor selection, we reduce the problem to an under-determined system of equations with potentially infinite number of solutions. However, the sparsity of the underlying data facilitates limiting the set of solutions to a unique solution. Sparsity enables employing the emerging compressive sensing technique, where the compressed measurements are selected from a large number of potential sensors. This paper suggests selecting sensors in a way that the reduced system of equations constructs a well-conditioned measurement matrix. Our criterion for sensor selection is based on E-optimalily, which is highly related to the restricted isometry property that provides some guarantees for sparse solution obtained by ℓ1minimization. Moreover, the proposed framework exploits a feedback mechanism to evolve the selected sensors dynamically over time. The evolution aims to maximize the reliability of the sensed spectrum.

In this paper, the problem of target localization in the presence of outlying sensors is tackled. This problem is important in practice because in many real-world applications the sensors might report irrelevant data unintentionally or maliciously. The problem is formulated by applying robust statistics techniques on squared range measurements and two different approaches to solve the problem are proposed. The first approach is computationally efficient; however, only the objective convergence is guaranteed theoretically. On the other hand, the whole-sequence convergence of the second approach is established. To enjoy the benefit of both approaches, they are integrated to develop a hybrid algorithm that offers computational efficiency and theoretical guarantees. The algorithms are evaluated for different simulated and real-world scenarios. The numerical results show that the proposed methods meet the Cr'amer-Rao lower bound (CRLB) for a sufficiently large number of measurements. When the number of the measurements is small, the proposed position estimator does not achieve CRLB though it still outperforms several existing localization methods.