Guiding hidden layer representations for improved rule extraction from neural networks

Incorporation of Data-mined Knowledge into Black-box SVM for Interpretability

The lack of interpretability often makes black-box models challenging to be applied in many practical domains. For this reason, the current work, from the black-box model input port, proposes to incorporate data-mined knowledge into the black-box soft-margin SVM model to enhance accuracy and interpretability. The concept and incorporation mechanism of data-mined knowledge are successively developed, based on which a partially interpretable soft-margin SVM ( pTsm -SVM) optimization model is designed and then solved through reformulating the optimization problem as standard quadratic programming. An algorithm for mining linear positive (negative) class knowledge from general data sets is also proposed, which generates a linear two-dimensional discriminative rule with specificity (sensitivity) equal to 1 and the highest possible sensitivity (specificity) among all two-dimensional feature spaces. The knowledge-integrated pTsm -SVM works by achieving a good trade-off among the “large margin”, “high specificity”, and “high sensitivity”. Our experimental results on eight UCI datasets demonstrate the superiority of the proposed pTsm -SVM over the standard soft-margin SVM both in terms of accuracy and interpretability.

Supposed Maximum Mutual Information for Improving Generalization and Interpretation of Multi-Layered Neural Networks

The present paper1 aims to propose a new type of information-theoretic method to maximize mutual information between inputs and outputs. The importance of mutual information in neural networks is well known, but the actual implementation of mutual information maximization has been quite difficult to undertake. In addition, mutual information has not extensively been used in neural networks, meaning that its applicability is very limited. To overcome the shortcoming of mutual information maximization, we present it here in a very simplified manner by supposing that mutual information is already maximized before learning, or at least at the beginning of learning. The method was applied to three data sets (crab data set, wholesale data set, and human resources data set) and examined in terms of generalization performance and connection weights. The results showed that by disentangling connection weights, maximizing mutual information made it possible to explicitly interpret the relations between inputs and outputs.

Optimization of a multilayer neural network by using minimal redundancy maximal relevance-partial mutual information clustering with least square regression

In this paper, an optimized multilayer feed-forward network (MLFN) is developed to construct a soft sensor for controlling naphtha dry point. To overcome the two main flaws in the structure and weight of MLFNs, which are trained by a back-propagation learning algorithm, minimal redundancy maximal relevance-partial mutual information clustering (mPMIc) integrated with least square regression (LSR) is proposed to optimize the MLFN. The mPMIc can determine the location of hidden layer nodes using information in the hidden and output layers, as well as remove redundant hidden layer nodes. These selected nodes are highly related to output data, but are minimally correlated with other hidden layer nodes. The weights between the selected hidden layer nodes and output layer are then updated through LSR. When the redundant nodes from the hidden layer are removed, the ideal MLFN structure can be obtained according to the test error results. In actual applications, the naphtha dry point must be controlled accurately because it strongly affects the production yield and the stability of subsequent operational processes. The mPMIc-LSR MLFN with a simple network size performs better than other improved MLFN variants and existing efficient models.

Learning understandable neural networks with nonnegative weight constraints

People can understand complex structures if they relate to more isolated yet understandable concepts. Despite this fact, popular pattern recognition tools, such as decision tree or production rule learners, produce only flat models which do not build intermediate data representations. On the other hand, neural networks typically learn hierarchical but opaque models. We show how constraining neurons' weights to be nonnegative improves the interpretability of a network's operation. We analyze the proposed method on large data sets: the MNIST digit recognition data and the Reuters text categorization data. The patterns learned by traditional and constrained network are contrasted to those learned with principal component analysis and nonnegative matrix factorization.

MODIFIED FUZZY NEURAL NETWORK FOR THE CLASSIFICATION OF MURDER CASES IN CRIMINAL LAW USING GAUSSIAN MEMBERSHIP FUNCTION

This paper presents the problem of decision making by a judge in the case of murder cases in criminal law using single hidden layered fuzzy neural network algorithm. Since the membership functions (MFs) of fuzzy sets can affect the performance of the classification models, determination of MFs is crucial. In this paper, the MF selected is Triangular and Gaussian is proposed for evaluation to improve the classification results. To evaluate the effectiveness of the proposed Fuzzy Neural Network model for the classification of murder cases, sufficient number of real-world data sets of court decisions are trained and tested. The simulation model of different membership functions for the modified fuzzy neural network architecture is implemented in C++. Experimental results show that the proposed neuro-fuzzy classifier with Gaussian MF outperforms Triangular MF with higher accuracy. The proposed classification model is proved to be a suitable tool for classification of murder cases in criminal law.

The rise of machine consciousness: studying consciousness with computational models

Efforts to create computational models of consciousness have accelerated over the last two decades, creating a field that has become known as artificial consciousness. There have been two main motivations for this controversial work: to develop a better scientific understanding of the nature of human/animal consciousness and to produce machines that genuinely exhibit conscious awareness. This review begins by briefly explaining some of the concepts and terminology used by investigators working on machine consciousness, and summarizes key neurobiological correlates of human consciousness that are particularly relevant to past computational studies. Models of consciousness developed over the last twenty years are then surveyed. These models are largely found to fall into five categories based on the fundamental issue that their developers have selected as being most central to consciousness: a global workspace, information integration, an internal self-model, higher-level representations, or attention mechanisms. For each of these five categories, an overview of past work is given, a representative example is presented in some detail to illustrate the approach, and comments are provided on the contributions and limitations of the methodology. Three conclusions are offered about the state of the field based on this review: (1) computational modeling has become an effective and accepted methodology for the scientific study of consciousness, (2) existing computational models have successfully captured a number of neurobiological, cognitive, and behavioral correlates of conscious information processing as machine simulations, and (3) no existing approach to artificial consciousness has presented a compelling demonstration of phenomenal machine consciousness, or even clear evidence that artificial phenomenal consciousness will eventually be possible. The paper concludes by discussing the importance of continuing work in this area, considering the ethical issues it raises, and making predictions concerning future developments.

Symbolic representation of recurrent neural network dynamics

Simple recurrent error backpropagation networks have been widely used to learn temporal sequence data, including regular and context-free languages. However, the production of relatively large and opaque weight matrices during learning has inspired substantial research on how to extract symbolic human-readable interpretations from trained networks. Unlike feedforward networks, where research has focused mainly on rule extraction, most past work with recurrent networks has viewed them as dynamical systems that can be approximated symbolically by finite-state machine (FSMs). With this approach, the network's hidden layer activation space is typically divided into a finite number of regions. Past research has mainly focused on better techniques for dividing up this activation space. In contrast, very little work has tried to influence the network training process to produce a better representation in hidden layer activation space, and that which has been done has had only limited success. Here we propose a powerful general technique to bias the error backpropagation training process so that it learns an activation space representation from which it is easier to extract FSMs. Using four publicly available data sets that are based on regular and context-free languages, we show via computational experiments that the modified learning method helps to extract FSMs with substantially fewer states and less variance than unmodified backpropagation learning, without decreasing the neural networks' accuracy. We conclude that modifying error backpropagation so that it more effectively separates learned pattern encodings in the hidden layer is an effective way to improve contemporary FSM extraction methods.