Explaining Neural Networks by Decoding Layer Activations
Institute of Information Systems, University of Liechtenstein（列支敦士登大学信息系统学院）；Department of Information Systems, HEC, University of Lausanne（洛桑大学高等商学院信息系统系）
We present a `CLAssifier-DECoder' architecture (\emph{ClaDec}) which facilitates the comprehension of the output of an arbitrary layer in a neural network (NN). It uses a decoder to transform the non-interpretable representation of the given layer to a representation that is more similar to the domain a human is familiar with. In an image recognition problem, one can recognize what information is represented by a layer by contrasting reconstructed images of \emph{ClaDec} with those of a conventional auto-encoder(AE) serving as reference. We also extend \emph{ClaDec} to allow the trade-off between human interpretability and fidelity. We evaluate our approach for image classification using Convolutional NNs. We show that reconstructed visualizations using encodings from a classifier capture more relevant information for classification than conventional AEs. Relevant code is available at \url{https://github.com/JohnTailor/ClaDec}
Sberbank AI Lab（俄罗斯联邦储蓄银行人工智能实验室）；Samsung AI Center in Moscow（三星莫斯科人工智能中心）；Stern School of Business, NYU（纽约大学斯特恩商学院）
We introduce a novel approach to feed-forward neural network interpretation based on partitioning the space of sequences of neuron activations. In line with this approach, we propose a model-specific interpretation method, called YASENN. Our method inherits many advantages of model-agnostic distillation, such as an ability to focus on the particular input region and to express an explanation in terms of features different from those observed by a neural network. Moreover, examination of distillation error makes the method applicable to the problems with low tolerance to interpretation mistakes…
Tel-Aviv University（特拉维夫大学）；Facebook AI Research（脸书人工智能研究院）
The problem of maximum likelihood decoding with a neural decoder for error-correcting code is considered. It is shown that the neural decoder can be improved with two novel loss terms on the node's activations. The first loss term imposes a sparse constraint on the node's activations. Whereas, the second loss term tried to mimic the node's activations from a teacher decoder which has better performance. The proposed method has the same run time complexity and model size as the neural Belief Propagation decoder, while improving the decoding performance by up to $1.1dB$ on BCH codes.
We consider the problem of explaining the decisions of deep neural networks for image recognition in terms of human-recognizable visual concepts. In particular, given a test set of images, we aim to explain each classification in terms of a small number of image regions, or activation maps, which have been associated with semantic concepts by a human annotator. This allows for generating summary views of the typical reasons for classifications, which can help build trust in a classifier and/or identify example types for which the classifier may not be trusted. For this purpose, we developed a …
Université Paris Cité（巴黎西岱大学）；EDF R&D（法国电力集团研发中心）；IUF（法国大学研究院）
Data series classification is an important and challenging problem in data science. Explaining the classification decisions by finding the discriminant parts of the input that led the algorithm to some decisions is a real need in many applications. Convolutional neural networks perform well for the data series classification task; though, the explanations provided by this type of algorithm are poor for the specific case of multivariate data series. Addressing this important limitation is a significant challenge. In this paper, we propose a novel method that solves this problem by highlighting …
Kansas State University（堪萨斯州立大学）；University of Hartford（哈特福德大学）
One of the current key challenges in Explainable AI is in correctly interpreting activations of hidden neurons. It seems evident that accurate interpretations thereof would provide insights into the question what a deep learning system has internally \emph{detected} as relevant on the input, thus lifting some of the black box character of deep learning systems. The state of the art on this front indicates that hidden node activations appear to be interpretable in a way that makes sense to humans, at least in some cases. Yet, systematic automated methods that would be able to first hypothesize …
We propose to explain the predictions of a deep neural network, by pointing to the set of what we call representer points in the training set, for a given test point prediction. Specifically, we show that we can decompose the pre-activation prediction of a neural network into a linear combination of activations of training points, with the weights corresponding to what we call representer values, which thus capture the importance of that training point on the learned parameters of the network. But it provides a deeper understanding of the network than simply training point influence: with posi…
NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models
Wuhan University（武汉大学）；Hong Kong Baptist University（香港 Baptist大学）；New Jersey Institute of Technology（新泽西理工学院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Few-shot learning addresses problems for which a limited number of training examples are available. So far, the field has been mostly driven by applications in computer vision. Here, we are interested in adapting recently introduced few-shot methods to solve problems dealing with neuroimaging data, a promising application field. To this end, we create a neuroimaging benchmark dataset for few-shot learning and compare multiple learning paradigms, including meta-learning, as well as various backbone networks. Our experiments show that few-shot methods are able to efficiently decode brain signals…
INRIA Saclay-Île-de-France（法国国家信息与自动化研究所 萨克莱-法兰西岛分院）；CEA（法国原子能和替代能源委员会）；INRIA Paris - Rocquencourt（法国国家信息与自动化研究所 巴黎-罗克库尔分院）；Institut Mines-Télécom（法国国立矿业电信学院）；Télécom ParisTech（巴黎高等电信学院）；CNRS（法国国家科学研究中心）
Extracting activation patterns from functional Magnetic Resonance Images (fMRI) datasets remains challenging in rapid-event designs due to the inherent delay of blood oxygen level-dependent (BOLD) signal. The general linear model (GLM) allows to estimate the activation from a design matrix and a fixed hemodynamic response function (HRF). However, the HRF is known to vary substantially between subjects and brain regions. In this paper, we propose a model for jointly estimating the hemodynamic response function (HRF) and the activation patterns via a low-rank representation of task effects.This …
Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions. We develop an approach to explaining deep neural networks by constructing causal models on salient concepts contained in a CNN. We develop methods to extract salient concepts throughout a target network by using autoencoders trained to extract human-understandable representations of network activations. We then build a bayesian causal model using these extracted concepts as variables in order to explain image class…
Clinical decision support using deep neural networks has become a topic of steadily growing interest. While recent work has repeatedly demonstrated that deep learning offers major advantages for medical image classification over traditional methods, clinicians are often hesitant to adopt the technology because its underlying decision-making process is considered to be intransparent and difficult to comprehend. In recent years, this has been addressed by a variety of approaches that have successfully contributed to providing deeper insight. Most notably, additive feature attribution methods are…
Slovak University of Technology（斯洛伐克理工大学）；Johannes Kepler University（约翰内斯·开普勒大学）
In many practical applications, deep neural networks have been typically deployed to operate as a black box predictor. Despite the high amount of work on interpretability and high demand on the reliability of these systems, they typically still have to include a human actor in the loop, to validate the decisions and handle unpredictable failures and unexpected corner cases. This is true in particular for failure-critical application domains, such as medical diagnosis. We present a novel approach to explain and support an interpretation of the decision-making process to a human expert operating…
Deep learning techniques are increasingly being adopted for classification tasks over the past decade, yet explaining how deep learning architectures can achieve state-of-the-art performance is still an elusive goal. While all the training information is embedded deeply in a trained model, we still do not understand much about its performance by only analyzing the model. This paper examines the neuron activation patterns of deep learning-based classification models and explores whether the models' performances can be explained through neurons' activation behavior. We propose two approaches: on…
Here, we present a novel approach to solve the problem of reconstructing perceived stimuli from brain responses by combining probabilistic inference with deep learning. Our approach first inverts the linear transformation from latent features to brain responses with maximum a posteriori estimation and then inverts the nonlinear transformation from perceived stimuli to latent features with adversarial training of convolutional neural networks. We test our approach with a functional magnetic resonance imaging experiment and show that it can generate state-of-the-art reconstructions of perceived …
ST-Topo GAN: A Motor EEG-to-EMG Decoding Model Matched to Wrist Movement Complexity
Zhengzhou University（郑州大学）；HumVerse (Zhengzhou) Technologies Co., Ltd.（HumVerse（郑州）科技有限公司）；Henan Provincial Key Laboratory of Brain Science and Brain-Computer Interface Technology（河南省脑科学与脑机接口技术重点实验室）；Xi’an Jiaotong University（西安交通大学）；University of Electronic Science and Technology of China（电子科技大学）；Chinese Academy of Medical Sciences（中国医学科学院）
What is Missing? Explaining Neurons Activated by Absent Concepts
Max Planck Institute for Informatics, SIC（马克斯·普朗克信息研究所，SIC）；Department of Computer Science, Technical University of Darmstadt（达姆施塔特技术大学计算机科学系）；Leibniz Institute for Resilience Research（莱比锡韧性研究所）；Institute for Quantitative and Computational Biosciences, Johannes Gutenberg University Mainz（美因茨雅各布·冯·特利尔大学定量与计算生物科学研究所）；University Medical Center Mainz（美因茨大学医学中心）
Self-explaining models are models that reveal decision making parameters in an interpretable manner so that the model reasoning process can be directly understood by human beings. General Linear Models (GLMs) are self-explaining because the model weights directly show how each feature contributes to the output value. However, deep neural networks (DNNs) are in general not self-explaining due to the non-linearity of the activation functions, complex architectures, obscure feature extraction and transformation process. In this work, we illustrate the fact that existing deep architectures are har…
Direct decoding for task-oriented dialogue is known to suffer from the explaining-away effect, manifested in models that prefer short and generic responses. Here we argue for the use of Bayes' theorem to factorize the dialogue task into two models, the distribution of the context given the response, and the prior for the response itself. This approach, an instantiation of the noisy channel model, both mitigates the explaining-away effect and allows the principled incorporation of large pretrained models for the response prior. We present extensive experiments showing that a noisy channel model…
Graph Neural Networks (GNNs) have shown remarkable effectiveness in capturing abundant information in graph-structured data. However, the black-box nature of GNNs hinders users from understanding and trusting the models, thus leading to difficulties in their applications. While recent years witness the prosperity of the studies on explaining GNNs, most of them focus on static graphs, leaving the explanation of dynamic GNNs nearly unexplored. It is challenging to explain dynamic GNNs, due to their unique characteristic of time-varying graph structures. Directly using existing models designed fo…
Recent literature on unsupervised learning focused on designing structural priors with the aim of learning meaningful features, but without considering the description length of the representations. In this thesis, first we introduce the $φ$ metric that evaluates unsupervised models based on their reconstruction accuracy and the degree of compression of their internal representations. We then present and define two activation functions (Identity, ReLU) as base of reference and three sparse activation functions (top-k absolutes, Extrema-Pool indices, Extrema) as candidate structures that minimi…
University of Michigan（密歇根大学）；Stanford University（斯坦福大学）；NTT Research, Inc.（NTT研究院）
Inspired by BatchNorm, there has been an explosion of normalization layers in deep learning. Recent works have identified a multitude of beneficial properties in BatchNorm to explain its success. However, given the pursuit of alternative normalization layers, these properties need to be generalized so that any given layer's success/failure can be accurately predicted. In this work, we take a first step towards this goal by extending known properties of BatchNorm in randomly initialized deep neural networks (DNNs) to several recently proposed normalization layers. Our primary findings follow: (…
A main concern in cognitive neuroscience is to decode the overt neural spike train observations and infer latent representations under neural circuits. However, traditional methods entail strong prior on network structure and hardly meet the demand for real spike data. Here we propose a novel neural network approach called Neuron Activation Network that extracts neural information explicitly from single trial neuron population spike trains. Our proposed method consists of a spatiotemporal learning procedure on sensory environment and a message passing mechanism on population graph, followed by…
Indian Institute of Science（印度科学学院）；Indian Institute of Information Technology Kalyani（卡利亚尼印度信息技术学院）
This paper investigates how working of Convolutional Neural Network (CNN) can be explained through visualization in the context of machine perception of autonomous vehicles. We visualize what type of features are extracted in different convolution layers of CNN that helps to understand how CNN gradually increases spatial information in every layer. Thus, it concentrates on region of interests in every transformation. Visualizing heat map of activation helps us to understand how CNN classifies and localizes different objects in image. This study also helps us to reason behind low accuracy of a …
Decoding Covert Speech from EEG Using a Functional Areas Spatio-Temporal Transformer
College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；DSO National Laboratories（新加坡国防科技局实验室）；Lee Kong Chian School of Medicine, Nanyang Technological University（南洋理工大学李光前医学院）；National University Health System（国立大学卫生系统）；Division of Psychology, Nanyang Technological University（南洋理工大学心理学系）；Department of Pediatrics, University of Cambridge（剑桥大学儿科系）；Yong Loo Lin School of Medicine, National University of Singapore（新加坡国立大学杨潞龄医学院）；Department of Clinical Neuroscience, Karolinska Institutet（卡罗林斯卡学院临床神经科学系）
In traditional software programs, it is easy to trace program logic from variables back to input, apply assertion statements to block erroneous behavior, and compose programs together. Although deep learning programs have demonstrated strong performance on novel applications, they sacrifice many of the functionalities of traditional software programs. With this as motivation, we take a modest first step towards improving deep learning programs by jointly training a generative model to constrain neural network activations to "decode" back to inputs. We call this design a Decodable Neural Networ…
Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input. However, class-insensitivity of the earlier layers in a network only allows saliency computation with low resolution activation maps of the deeper layers, resulting in compromised image saliency. Remedifying this can lead to sanity failures. We propose CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors and preserving the map sanity. Our method systematically performs multi-scale accumulation …
NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of Hong Kong（香港大学）；Shenzhen Loop Area Institute（深圳河套学院）；Tsinghua University（清华大学）；Chinese University of Hong Kong（香港中文大学）
Explaining Intrinsic Moral Self-Correction with Mechanistic Interpretability
Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan（通讯工程研究院，国立台湾大学）；MediaTek Research, Taipei, Taiwan（联发科研究，台北，台湾）；Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan（电气工程系，国立台湾大学）；Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan（电气工程系，国立清华大学）；AI Research Center (AINTU), National Taiwan University, Taipei, Taiwan（人工智能研究中心（AINTU），国立台湾大学）
Middle East Technical University（中东技术大学）；Koc University（科奇大学）
Functional magnetic resonance imaging produces high dimensional data, with a less then ideal number of labelled samples for brain decoding tasks (predicting brain states). In this study, we propose a new deep temporal convolutional neural network architecture with spatial pooling for brain decoding which aims to reduce dimensionality of feature space along with improved classification performance. Temporal representations (filters) for each layer of the convolutional model are learned by leveraging unlabelled fMRI data in an unsupervised fashion with regularized autoencoders. Learned temporal …
TU Kaiserslautern（凯泽斯劳滕工业大学）；German Research Center for Artificial Intelligence GmbH (DFKI)（德国人工智能研究中心）
Human-centric explainability of AI-based Decision Support Systems (DSS) using visual input modalities is directly related to reliability and practicality of such algorithms. An otherwise accurate and robust DSS might not enjoy trust of experts in critical application areas if it is not able to provide reasonable justification of its predictions. This paper introduces Concept Localization Maps (CLMs), which is a novel approach towards explainable image classifiers employed as DSS. CLMs extend Concept Activation Vectors (CAVs) by locating significant regions corresponding to a learned concept in…
Deep learning is increasingly used in decision-making tasks. However, understanding how neural networks produce final predictions remains a fundamental challenge. Existing work on interpreting neural network predictions for images often focuses on explaining predictions for single images or neurons. As predictions are often computed from millions of weights that are optimized over millions of images, such explanations can easily miss a bigger picture. We present Summit, an interactive system that scalably and systematically summarizes and visualizes what features a deep learning model has lear…
