This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance in various tasks, the interpretability is always the Achilles' heel of deep neural networks. At present, deep neural networks obtain high discrimination power at the cost of low interpretability of their black-box representations. We believe that high model interpretability may help people to break several bottlenecks of deep learning, e.g., learning from very few annotations, learning via human-computer communications at the semantic level, and semantically debugging network representations. We focus on convolutional neural networks (CNNs), and we revisit the visualization of CNN representations, methods of diagnosing representations of pre-trained CNNs, approaches for disentangling pre-trained CNN representations, learning of CNNs with disentangled representations, and middle-to-end learning based on model interpretability. Finally, we discuss prospective trends in explainable artificial intelligence.

9
下载
关闭预览

相关内容

神经网络(Neural Networks)是世界上三个最古老的神经建模学会的档案期刊:国际神经网络学会(INNS)、欧洲神经网络学会(ENNS)和日本神经网络学会(JNNS)。神经网络提供了一个论坛,以发展和培育一个国际社会的学者和实践者感兴趣的所有方面的神经网络和相关方法的计算智能。神经网络欢迎高质量论文的提交,有助于全面的神经网络研究,从行为和大脑建模,学习算法,通过数学和计算分析,系统的工程和技术应用,大量使用神经网络的概念和技术。这一独特而广泛的范围促进了生物和技术研究之间的思想交流,并有助于促进对生物启发的计算智能感兴趣的跨学科社区的发展。因此,神经网络编委会代表的专家领域包括心理学,神经生物学,计算机科学,工程,数学,物理。该杂志发表文章、信件和评论以及给编辑的信件、社论、时事、软件调查和专利信息。文章发表在五个部分之一:认知科学,神经科学,学习系统,数学和计算分析、工程和应用。 官网地址:http://dblp.uni-trier.de/db/journals/nn/

A comprehensive artificial intelligence system needs to not only perceive the environment with different `senses' (e.g., seeing and hearing) but also infer the world's conditional (or even causal) relations and corresponding uncertainty. The past decade has seen major advances in many perception tasks such as visual object recognition and speech recognition using deep learning models. For higher-level inference, however, probabilistic graphical models with their Bayesian nature are still more powerful and flexible. In recent years, Bayesian deep learning has emerged as a unified probabilistic framework to tightly integrate deep learning and Bayesian models. In this general framework, the perception of text or images using deep learning can boost the performance of higher-level inference and in turn, the feedback from the inference process is able to enhance the perception of text or images. This survey provides a comprehensive introduction to Bayesian deep learning and reviews its recent applications on recommender systems, topic models, control, etc. Besides, we also discuss the relationship and differences between Bayesian deep learning and other related topics such as Bayesian treatment of neural networks.

0
25
下载
预览

Deep neural models in recent years have been successful in almost every field, including extremely complex problem statements. However, these models are huge in size, with millions (and even billions) of parameters, thus demanding more heavy computation power and failing to be deployed on edge devices. Besides, the performance boost is highly dependent on redundant labeled data. To achieve faster speeds and to handle the problems caused by the lack of data, knowledge distillation (KD) has been proposed to transfer information learned from one model to another. KD is often characterized by the so-called `Student-Teacher' (S-T) learning framework and has been broadly applied in model compression and knowledge transfer. This paper is about KD and S-T learning, which are being actively studied in recent years. First, we aim to provide explanations of what KD is and how/why it works. Then, we provide a comprehensive survey on the recent progress of KD methods together with S-T frameworks typically for vision tasks. In general, we consider some fundamental questions that have been driving this research area and thoroughly generalize the research progress and technical details. Additionally, we systematically analyze the research status of KD in vision applications. Finally, we discuss the potentials and open challenges of existing methods and prospect the future directions of KD and S-T learning.

0
4
下载
预览

This paper proposes a generic method to learn interpretable convolutional filters in a deep convolutional neural network (CNN) for object classification, where each interpretable filter encodes features of a specific object part. Our method does not require additional annotations of object parts or textures for supervision. Instead, we use the same training data as traditional CNNs. Our method automatically assigns each interpretable filter in a high conv-layer with an object part of a certain category during the learning process. Such explicit knowledge representations in conv-layers of CNN help people clarify the logic encoded in the CNN, i.e., answering what patterns the CNN extracts from an input image and uses for prediction. We have tested our method using different benchmark CNNs with various structures to demonstrate the broad applicability of our method. Experiments have shown that our interpretable filters are much more semantically meaningful than traditional filters.

0
10
下载
预览

The Visual Question Answering (VQA) task combines challenges for processing data with both Visual and Linguistic processing, to answer basic `common sense' questions about given images. Given an image and a question in natural language, the VQA system tries to find the correct answer to it using visual elements of the image and inference gathered from textual questions. In this survey, we cover and discuss the recent datasets released in the VQA domain dealing with various types of question-formats and enabling robustness of the machine-learning models. Next, we discuss about new deep learning models that have shown promising results over the VQA datasets. At the end, we present and discuss some of the results computed by us over the vanilla VQA models, Stacked Attention Network and the VQA Challenge 2017 winner model. We also provide the detailed analysis along with the challenges and future research directions.

0
4
下载
预览

Deep learning has been shown successful in a number of domains, ranging from acoustics, images to natural language processing. However, applying deep learning to the ubiquitous graph data is non-trivial because of the unique characteristics of graphs. Recently, a significant amount of research efforts have been devoted to this area, greatly advancing graph analyzing techniques. In this survey, we comprehensively review different kinds of deep learning methods applied to graphs. We divide existing methods into three main categories: semi-supervised methods including Graph Neural Networks and Graph Convolutional Networks, unsupervised methods including Graph Autoencoders, and recent advancements including Graph Recurrent Neural Networks and Graph Reinforcement Learning. We then provide a comprehensive overview of these methods in a systematic manner following their history of developments. We also analyze the differences of these methods and how to composite different architectures. Finally, we briefly outline their applications and discuss potential future directions.

0
35
下载
预览

In structure learning, the output is generally a structure that is used as supervision information to achieve good performance. Considering the interpretation of deep learning models has raised extended attention these years, it will be beneficial if we can learn an interpretable structure from deep learning models. In this paper, we focus on Recurrent Neural Networks (RNNs) whose inner mechanism is still not clearly understood. We find that Finite State Automaton (FSA) that processes sequential data has more interpretable inner mechanism and can be learned from RNNs as the interpretable structure. We propose two methods to learn FSA from RNN based on two different clustering methods. We first give the graphical illustration of FSA for human beings to follow, which shows the interpretability. From the FSA's point of view, we then analyze how the performance of RNNs are affected by the number of gates, as well as the semantic meaning behind the transition of numerical hidden states. Our results suggest that RNNs with simple gated structure such as Minimal Gated Unit (MGU) is more desirable and the transitions in FSA leading to specific classification result are associated with corresponding words which are understandable by human beings.

0
16
下载
预览

As a new classification platform, deep learning has recently received increasing attention from researchers and has been successfully applied to many domains. In some domains, like bioinformatics and robotics, it is very difficult to construct a large-scale well-annotated dataset due to the expense of data acquisition and costly annotation, which limits its development. Transfer learning relaxes the hypothesis that the training data must be independent and identically distributed (i.i.d.) with the test data, which motivates us to use transfer learning to solve the problem of insufficient training data. This survey focuses on reviewing the current researches of transfer learning by using deep neural network and its applications. We defined deep transfer learning, category and review the recent research works based on the techniques used in deep transfer learning.

0
7
下载
预览

Visual Question answering is a challenging problem requiring a combination of concepts from Computer Vision and Natural Language Processing. Most existing approaches use a two streams strategy, computing image and question features that are consequently merged using a variety of techniques. Nonetheless, very few rely on higher level image representations, which allow to capture semantic and spatial relationships. In this paper, we propose a novel graph-based approach for Visual Question Answering. Our method combines a graph learner module, which learns a question specific graph representation of the input image, with the recent concept of graph convolutions, aiming to learn image representations that capture question specific interactions. We test our approach on the VQA v2 dataset using a simple baseline architecture enhanced by the proposed graph learner module. We obtain state of the art results with 65.77% accuracy and demonstrate the interpretability of the proposed method.

0
4
下载
预览

This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each filter in a high conv-layer represents a certain object part. We do not need any annotations of object parts or textures to supervise the learning process. Instead, the interpretable CNN automatically assigns each filter in a high conv-layer with an object part during the learning process. Our method can be applied to different types of CNNs with different structures. The clear knowledge representation in an interpretable CNN can help people understand the logics inside a CNN, i.e., based on which patterns the CNN makes the decision. Experiments showed that filters in an interpretable CNN were more semantically meaningful than those in traditional CNNs.

0
13
下载
预览

This paper presents a method of learning qualitatively interpretable models in object detection using popular two-stage region-based ConvNet detection systems (i.e., R-CNN). R-CNN consists of a region proposal network and a RoI (Region-of-Interest) prediction network.By interpretable models, we focus on weakly-supervised extractive rationale generation, that is learning to unfold latent discriminative part configurations of object instances automatically and simultaneously in detection without using any supervision for part configurations. We utilize a top-down hierarchical and compositional grammar model embedded in a directed acyclic AND-OR Graph (AOG) to explore and unfold the space of latent part configurations of RoIs. We propose an AOGParsing operator to substitute the RoIPooling operator widely used in R-CNN, so the proposed method is applicable to many state-of-the-art ConvNet based detection systems. The AOGParsing operator aims to harness both the explainable rigor of top-down hierarchical and compositional grammar models and the discriminative power of bottom-up deep neural networks through end-to-end training. In detection, a bounding box is interpreted by the best parse tree derived from the AOG on-the-fly, which is treated as the extractive rationale generated for interpreting detection. In learning, we propose a folding-unfolding method to train the AOG and ConvNet end-to-end. In experiments, we build on top of the R-FCN and test the proposed method on the PASCAL VOC 2007 and 2012 datasets with performance comparable to state-of-the-art methods.

0
3
下载
预览
小贴士
相关论文
A Survey on Bayesian Deep Learning
Hao Wang,Dit-Yan Yeung
25+阅读 · 7月2日
Interpretable CNNs for Object Classification
Quanshi Zhang,Xin Wang,Ying Nian Wu,Huilin Zhou,Song-Chun Zhu
10+阅读 · 3月12日
Yash Srivastava,Vaishnav Murali,Shiv Ram Dubey,Snehasis Mukherjee
4+阅读 · 2019年8月27日
Ziwei Zhang,Peng Cui,Wenwu Zhu
35+阅读 · 2018年12月11日
Bo-Jian Hou,Zhi-Hua Zhou
16+阅读 · 2018年10月25日
A Survey on Deep Transfer Learning
Chuanqi Tan,Fuchun Sun,Tao Kong,Wenchang Zhang,Chao Yang,Chunfang Liu
7+阅读 · 2018年8月6日
Will Norcliffe-Brown,Efstathios Vafeias,Sarah Parisot
4+阅读 · 2018年6月20日
Quanshi Zhang,Ying Nian Wu,Song-Chun Zhu
13+阅读 · 2018年2月14日
Tianfu Wu,Xilai Li,Xi Song,Wei Sun,Liang Dong,Bo Li
3+阅读 · 2017年11月14日
相关资讯
AI可解释性文献列表
专知
33+阅读 · 2019年10月7日
强化学习三篇论文 避免遗忘等
CreateAMind
9+阅读 · 2019年5月24日
Transferring Knowledge across Learning Processes
CreateAMind
5+阅读 · 2019年5月18日
Unsupervised Learning via Meta-Learning
CreateAMind
24+阅读 · 2019年1月3日
A Technical Overview of AI & ML in 2018 & Trends for 2019
待字闺中
10+阅读 · 2018年12月24日
Disentangled的假设的探讨
CreateAMind
5+阅读 · 2018年12月10日
计算机视觉近一年进展综述
机器学习研究会
6+阅读 · 2017年11月25日
【深度】可解释性与deep learning的发展
机器学习研究会
4+阅读 · 2017年10月15日
可解释的CNN
CreateAMind
9+阅读 · 2017年10月5日
Top