Statistical mechanics of mutual information maximization

An unsupervised learning procedure based on maximizing the mutual information between the outputs of two networks receiving different but statistically dependent inputs is analyzed (Becker S. and Hinton G., Nature, 355 (1992) 161). By exploiting a formal analogy to supervised learning in parity machines, the theory of zero-temperature Gibbs learning for the unsupervised procedure is presented for the case that the networks are perceptrons and for the case of fully connected committees.

Hybrid sampling on mutual information entropy-based clustering ensembles for optimizations

In this paper, we focus on the design of bivariate EDAs for discrete optimization problems and propose a new approach named HSMIEC. While the current EDAs require much time in the statistical learning process as the relationships among the variables are too complicated, we employ the Selfish gene theory (SG) in this approach, as well as a Mutual Information and Entropy based Cluster (MIEC) model is also set to optimize the probability distribution of the virtual population. This model uses a hybrid sampling method by considering both the clustering accuracy and clustering diversity and an incremental learning and resample scheme is also set to optimize the parameters of the correlations of the variables. Compared with several benchmark problems, our experimental results demonstrate that HSMIEC often performs better than some other EDAs, such as BMDA, COMIT, MIMIC and ECGA. © 2009 Elsevier B.V. All rights reserved.

Mutual Information-based RBM Neural Networks

(Deep) neural networks are increasingly being used for various computer vision and pattern recognition tasks due to their strong ability to learn highly discriminative features. However, quantitative analysis of their classication ability and design philosophies are still nebulous. In this work, we use information theory to analyze the concatenated restricted Boltzmann machines (RBMs) and propose a mutual information-based RBM neural networks (MI-RBM). We develop a novel pretraining algorithm to maximize the mutual information between RBMs. Extensive experimental results on various classication tasks show the eectiveness of the proposed approach.

Calculation of mutual information for nonlinear communication channel at large signal-to-noise ratio

Using the path-integral technique we examine the mutual information for the communication channel modeled by the nonlinear Schrödinger equation with additive Gaussian noise. The nonlinear Schrödinger equation is one of the fundamental models in nonlinear physics, and it has a broad range of applications, including fiber optical communications - the backbone of the internet. At large signal-to-noise ratio we present the mutual information through the path-integral, which is convenient for the perturbative expansion in nonlinearity. In the limit of small noise and small nonlinearity we derive analytically the first nonzero nonlinear correction to the mutual information for the channel.

Conditional mutual inclusive information enables accurate quantification of associations in gene regulatory networks

International audience

Link discovery for Chinese/English cross-language web information retrieval

Nowadays people heavily rely on the Internet for information and knowledge. Wikipedia is an online multilingual encyclopaedia that contains a very large number of detailed articles covering most written languages. It is often considered to be a treasury of human knowledge. It includes extensive hypertext links between documents of the same language for easy navigation. However, the pages in different languages are rarely cross-linked except for direct equivalent pages on the same subject in different languages. This could pose serious difficulties to users seeking information or knowledge from different lingual sources, or where there is no equivalent page in one language or another. In this thesis, a new information retrieval task—cross-lingual link discovery (CLLD) is proposed to tackle the problem of the lack of cross-lingual anchored links in a knowledge base such as Wikipedia. In contrast to traditional information retrieval tasks, cross language link discovery algorithms actively recommend a set of meaningful anchors in a source document and establish links to documents in an alternative language. In other words, cross-lingual link discovery is a way of automatically finding hypertext links between documents in different languages, which is particularly helpful for knowledge discovery in different language domains. This study is specifically focused on Chinese / English link discovery (C/ELD). Chinese / English link discovery is a special case of cross-lingual link discovery task. It involves tasks including natural language processing (NLP), cross-lingual information retrieval (CLIR) and cross-lingual link discovery. To justify the effectiveness of CLLD, a standard evaluation framework is also proposed. The evaluation framework includes topics, document collections, a gold standard dataset, evaluation metrics, and toolkits for run pooling, link assessment and system evaluation. With the evaluation framework, performance of CLLD approaches and systems can be quantified. This thesis contributes to the research on natural language processing and cross-lingual information retrieval in CLLD: 1) a new simple, but effective Chinese segmentation method, n-gram mutual information, is presented for determining the boundaries of Chinese text; 2) a voting mechanism of name entity translation is demonstrated for achieving a high precision of English / Chinese machine translation; 3) a link mining approach that mines the existing link structure for anchor probabilities achieves encouraging results in suggesting cross-lingual Chinese / English links in Wikipedia. This approach was examined in the experiments for better, automatic generation of cross-lingual links that were carried out as part of the study. The overall major contribution of this thesis is the provision of a standard evaluation framework for cross-lingual link discovery research. It is important in CLLD evaluation to have this framework which helps in benchmarking the performance of various CLLD systems and in identifying good CLLD realisation approaches. The evaluation methods and the evaluation framework described in this thesis have been utilised to quantify the system performance in the NTCIR-9 Crosslink task which is the first information retrieval track of this kind.

Energy and information in Hodgkin-Huxley neurons

[EN]The generation of spikes by neurons is energetically a costly process and the evaluation of the metabolic energy required to maintain the signaling activity of neurons a challenge of practical interest. Neuron models are frequently used to represent the dynamics of real neurons but hardly ever to evaluate the electrochemical energy required to maintain that dynamics. This paper discusses the interpretation of a Hodgkin-Huxley circuit as an energy model for real biological neurons and uses it to evaluate the consumption of metabolic energy in the transmission of information between neurons coupled by electrical synapses, i.e., gap junctions. We show that for a single postsynaptic neuron maximum energy efficiency, measured in bits of mutual information per molecule of adenosine triphosphate (ATP) consumed, requires maximum energy consumption. For groups of parallel postsynaptic neurons we determine values of the synaptic conductance at which the energy efficiency of the transmission presents clear maxima at relatively very low values of metabolic energy consumption. Contrary to what could be expected, the best performance occurs at a low energy cost.

Quantifying synergistic information

Within the microcosm of information theory, I explore what it means for a system to be functionally irreducible. This is operationalized as quantifying the extent to which cooperative or “synergistic” effects enable random variables X₁, ... , X_n to predict (have mutual information about) a single target random variable Y . In Chapter 1, we introduce the problem with some emblematic examples. In Chapter 2, we show how six different measures from the existing literature fail to quantify this notion of synergistic mutual information. In Chapter 3 we take a step towards a measure of synergy which yields the first nontrivial lowerbound on synergistic mutual information. In Chapter 4, we find that synergy is but the weakest notion of a broader concept of irreducibility. In Chapter 5, we apply our results from Chapters 3 and 4 towards grounding Giulio Tononi’s ambitious φ measure which attempts to quantify the magnitude of consciousness experience.

Predictive coding and the slowness principle: an information-theoretic approach.

Understanding the guiding principles of sensory coding strategies is a main goal in computational neuroscience. Among others, the principles of predictive coding and slowness appear to capture aspects of sensory processing. Predictive coding postulates that sensory systems are adapted to the structure of their input signals such that information about future inputs is encoded. Slow feature analysis (SFA) is a method for extracting slowly varying components from quickly varying input signals, thereby learning temporally invariant features. Here, we use the information bottleneck method to state an information-theoretic objective function for temporally local predictive coding. We then show that the linear case of SFA can be interpreted as a variant of predictive coding that maximizes the mutual information between the current output of the system and the input signal in the next time step. This demonstrates that the slowness principle and predictive coding are intimately related.

Communication system model for information rate evaluation of differential detection over time-varying channels

A communication system model for mutual information performance analysis of multiple-symbol differential M-phase shift keying over time-correlated, time-varying flat-fading communication channels is developed. This model is a finite-state Markov (FSM) equivalent channel representing the cascade of the differential encoder, FSM channel model and differential decoder. A state-space approach is used to model channel phase time correlations. The equivalent model falls in a class that facilitates the use of the forward backward algorithm, enabling the important information theoretic results to be evaluated. Using such a model, one is able to calculate mutual information for differential detection over time-varying fading channels with an essentially finite time set of correlations, including the Clarke fading channel. Using the equivalent channel, it is proved and corroborated by simulations that multiple-symbol differential detection preserves the channel information capacity when the observation interval approaches infinity.

Information theoretic measures of UHG graphs with low computational complexity

We introduce a novel graph class we call universal hierarchical graphs (UHG) whose topology can be found numerously in problems representing, e.g., temporal, spacial or general process structures of systems. For this graph class we show, that we can naturally assign two probability distributions, for nodes and for edges, which lead us directly to the definition of the entropy and joint entropy and, hence, mutual information establishing an information theory for this graph class. Furthermore, we provide some results under which conditions these constraint probability distributions maximize the corresponding entropy. Also, we demonstrate that these entropic measures can be computed efficiently which is a prerequisite for every large scale practical application and show some numerical examples. (c) 2007 Elsevier Inc. All rights reserved.

Image Segmentation Using Information Bottleneck Method

In image processing, segmentation algorithms constitute one of the main focuses of research. In this paper, new image segmentation algorithms based on a hard version of the information bottleneck method are presented. The objective of this method is to extract a compact representation of a variable, considered the input, with minimal loss of mutual information with respect to another variable, considered the output. First, we introduce a split-and-merge algorithm based on the definition of an information channel between a set of regions (input) of the image and the intensity histogram bins (output). From this channel, the maximization of the mutual information gain is used to optimize the image partitioning. Then, the merging process of the regions obtained in the previous phase is carried out by minimizing the loss of mutual information. From the inversion of the above channel, we also present a new histogram clustering algorithm based on the minimization of the mutual information loss, where now the input variable represents the histogram bins and the output is given by the set of regions obtained from the above split-and-merge algorithm. Finally, we introduce two new clustering algorithms which show how the information bottleneck method can be applied to the registration channel obtained when two multimodal images are correctly aligned. Different experiments on 2-D and 3-D images show the behavior of the proposed algorithms

View-dependent information theory quality measures for pixel sampling and scene discretization in flatland

In this paper, we present view-dependent information theory quality measures for pixel sampling and scene discretization in flatland. The measures are based on a definition for the mutual information of a line, and have a purely geometrical basis. Several algorithms exploiting them are presented and compare well with an existing one based on depth differences