What does a neural network encode about a concept as we traverse through the layers? Interpretability in machine learning is undoubtedly important, but the calculations of neural networks are very challenging to understand. Attempts to see inside their hidden layers can either be misleading, unusable, or rely on the latent space to possess properties that it may not have. In this work, rather than attempting to analyze a neural network posthoc, we introduce a mechanism, called concept whitening (CW), to alter a given layer of the network to allow us to better understand the computation leading up to that layer. When a concept whitening module is added to a CNN, the axes of the latent space are aligned with known concepts of interest. By experiment, we show that CW can provide us a much clearer understanding for how the network gradually learns concepts over layers. CW is an alternative to a batch normalization layer in that it normalizes, and also decorrelates (whitens) the latent space. CW can be used in any layer of the network without hurting predictive performance.
We present here a new model and algorithm which performs an efficient Natural gradient descent for Multilayer Perceptrons. Natural gradient descent was originally proposed from a point of view of information geometry, and it performs the steepest descent updates on manifolds in a Riemannian space. In particular, we extend an approach taken by the "Whitened neural networks" model. We make the whitening process not only in feed-forward direction as in the original model, but also in the back-propagation phase. Its efficacy is shown by an application of this "Bidirectional whitened neural network…
University of British Columbia（不列颠哥伦比亚大学）；Tsinghua University（清华大学）
Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action recognition. For spatial attention, we learn a saliency mask to allow the model to focus on the most salient parts of the feature maps. For temporal attention, we employ a convolutional LSTM based attention mechanism to identify the most relevant frames from an input video. Further, we propose a set of regularizers to ensure that our attention mechanism attends to c…
After deep generative models were successfully applied to image generation tasks, learning disentangled latent variables of data has become a crucial part of deep generative model research. Many models have been proposed to learn an interpretable and factorized representation of latent variable by modifying their objective function or model architecture. To disentangle the latent variable, some models show lower quality of reconstructed images and others increase the model complexity which is hard to train. In this paper, we propose a simple disentangling method based on a traditional whitenin…
School of Computer Science and Engineering, UNSW Sydney, Australia（澳大利亚新南威尔士大学计算机科学与工程学院）；School of Information Technology, RMIT University, Australia（澳大利亚皇家墨尔本理工大学信息技术学院）；School of Computer Science, Northwestern Polytechnical University, China（中国西北工业大学计算机学院）；School of Software, Tsinghua University China（中国清华大学软件学院）
Multimodal features play a key role in wearable sensor-based human activity recognition (HAR). Selecting the most salient features adaptively is a promising way to maximize the effectiveness of multimodal sensor data. In this regard, we propose a "collect fully and select wisely" principle as well as an interpretable parallel recurrent model with convolutional attentions to improve the recognition performance. We first collect modality features and the relations between each pair of features to generate activity frames, and then introduce an attention mechanism to select the most prominent reg…
DAH-Net: A Dual-Attention Hybrid Network for Interpretable and Robust EEG-Based Emotion Recognition
Department of Electrical \& Computer Engineering University of Missouri Columbia, Missouri, USA；Department of Computer Science；Engineering City University Savar, Dhaka-1340, Bangladesh；Department of Computer Science University of Missouri Columbia, Missouri, USA
We present an interpretable deep model for fine-grained visual recognition. At the core of our method lies the integration of region-based part discovery and attribution within a deep neural network. Our model is trained using image-level object labels, and provides an interpretation of its results via the segmentation of object parts and the identification of their contributions towards classification. To facilitate the learning of object parts without direct supervision, we explore a simple prior of the occurrence of object parts. We demonstrate that this prior, when combined with our region…
Emotions play an important role in people's life. Understanding and recognising is not only important for interpersonal communication, but also has promising applications in Human-Computer Interaction, automobile safety and medical research. This project focuses on extending the emotion recognition database, and training the CNN + RNN emotion recognition neural networks with emotion category representation and valence \& arousal representation. The combined models are constructed by training the two representations simultaneously. The comparison and analysis between the three types of model ar…
University of Twente（特文特大学）；University of Duisburg-Essen（杜伊斯堡-埃森大学）
Prototype-based methods use interpretable representations to address the black-box nature of deep learning models, in contrast to post-hoc explanation methods that only approximate such models. We propose the Neural Prototype Tree (ProtoTree), an intrinsically interpretable deep learning method for fine-grained image recognition. ProtoTree combines prototype learning with decision trees, and thus results in a globally interpretable model by design. Additionally, ProtoTree can locally explain a single prediction by outlining a decision path through the tree. Each node in our binary tree contain…
Duke University（杜克大学）；MIT Lincoln Laboratory（麻省理工学院林肯实验室）
When we are faced with challenging image classification tasks, we often explain our reasoning by dissecting the image, and pointing out prototypical aspects of one class or another. The mounting evidence for each of the classes helps us make our final decision. In this work, we introduce a deep network architecture -- prototypical part network (ProtoPNet), that reasons in a similar way: the network dissects the image by finding prototypical parts, and combines evidence from the prototypes to make a final classification. The model thus reasons in a way that is qualitatively similar to the way o…
In this project, we created a database with two types of annotations used in the emotion recognition domain : Action Units and Valence Arousal to try to achieve better results than with only one model. The originality of the approach is also based on the type of architecture used to perform the prediction of the emotions : a categorical Generative Adversarial Network. This kind of dual network can generate images based on the pictures from the new dataset thanks to its generative network and decide if an image is fake or real thanks to its discriminative network as well as help to predict the …
University of Twente（特文特大学）；University of Duisburg-Essen（杜伊斯堡-埃森大学）
Image recognition with prototypes is considered an interpretable alternative for black box deep learning models. Classification depends on the extent to which a test image "looks like" a prototype. However, perceptual similarity for humans can be different from the similarity learned by the classification model. Hence, only visualising prototypes can be insufficient for a user to understand what a prototype exactly represents, and why the model considers a prototype and an image to be similar. We address this ambiguity and argue that prototypes should be explained. We improve interpretability …
Manchester Metropolitan University（曼彻斯特城市大学）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；Brunel University（布鲁内尔大学）
Spectral-spatial based deep learning models have recently proven to be effective in hyperspectral image (HSI) classification for various earth monitoring applications such as land cover classification and agricultural monitoring. However, due to the nature of "black-box" model representation, how to explain and interpret the learning process and the model decision, especially for vegetation classification, remains an open challenge. This study proposes a novel interpretable deep learning model -- a biologically interpretable two-stage deep neural network (BIT-DNN), by incorporating the prior-k…
Kasetsart University（农业大学）；Mahidol University（玛希隆大学）；Vidyasirimedhi Institute of Science & Technology（维迪亚西里梅迪科学技术研究所）
In the past few years, there are several researches on Parkinson's disease (PD) recognition using single-photon emission computed tomography (SPECT) images with deep learning (DL) approach. However, the DL model's complexity usually results in difficult model interpretation when used in clinical. Even though there are multiple interpretation methods available for the DL model, there is no evidence of which method is suitable for PD recognition application. This tutorial aims to demonstrate the procedure to choose a suitable interpretation method for the PD recognition model. We exhibit four DC…
Recent advances in tracking sensors and pose estimation software enable smart systems to use trajectories of skeleton joint locations for supervised learning. We study the problem of accurately recognizing sign language words, which is key to narrowing the communication gap between hard and non-hard of hearing people. Our method explores a geometric feature space that we call `sub-skeleton' aspects of movement. We assess similarity of feature space trajectories using natural, speed invariant distance measures, which enables clear and insightful nearest neighbor classification. The simplicity a…
University of Trento（特伦托大学）；Mila - Quebec Artifical Intelligence Institute（Mila -魁北克人工智能研究所）；StonyBrook University（石溪大学）
Machine learning methods, such as deep learning, show promising results in the medical domain. However, the lack of interpretability of these algorithms may hinder their applicability to medical decision support systems. This paper studies an interpretable deep learning technique, called SincNet. SincNet is a convolutional neural network that efficiently learns customized band-pass filters through trainable sinc-functions. In this study, we use SincNet to analyze the neural activity of individuals with Autism Spectrum Disorder (ASD), who experience characteristic differences in neural oscillat…
Vision models are interpretable when they classify objects on the basis of features that a person can directly understand. Recently, methods relying on visual feature prototypes have been developed for this purpose. However, in contrast to how humans categorize objects, these approaches have not yet made use of any taxonomical organization of class labels. With such an approach, for instance, we may see why a chimpanzee is classified as a chimpanzee, but not why it was considered to be a primate or even an animal. In this work we introduce a model that uses hierarchically organized prototypes …
This research project studies the impact of convolutional neural networks (CNN) in image classification tasks. We explore different architectures and training configurations with the use of ReLUs, Nesterov's accelerated gradient, dropout and maxout networks. We work with the CIFAR-10 dataset as part of a Kaggle competition to identify objects in images. Initial results show that CNNs outperform our baseline by acting as invariant feature detectors. Comparisons between different preprocessing procedures show better results for global contrast normalization and ZCA whitening. ReLUs are much fast…
Insight Centre for Data Analytics（洞察数据分析中心）；Dublin City University（都柏林城市大学）
The current gold standard for human activity recognition (HAR) is based on the use of cameras. However, the poor scalability of camera systems renders them impractical in pursuit of the goal of wider adoption of HAR in mobile computing contexts. Consequently, researchers instead rely on wearable sensors and in particular inertial sensors. A particularly prevalent wearable is the smart watch which due to its integrated inertial and optical sensing capabilities holds great potential for realising better HAR in a non-obtrusive way. This paper seeks to simplify the wearable approach to HAR through…
For EEG-based drowsiness recognition, it is desirable to use subject-independent recognition since conducting calibration on each subject is time-consuming. In this paper, we propose a novel Convolutional Neural Network (CNN)-Long Short-Term Memory (LSTM) model for subject-independent drowsiness recognition from single-channel EEG signals. Different from existing deep learning models that are mostly treated as black-box classifiers, the proposed model can explain its decisions for each input sample by revealing which parts of the sample contain important features identified by the model for cl…
Department of Electrical & Computer Engineering（电气与计算机工程系）；Department of Applied Mathematics（应用数学系）；University of Washington（华盛顿大学）；Seattle, WA 98195（西雅图, WA 98195（注意：地址信息按要求不应提取，此处仅为示例说明））
Encoder-decoder recurrent neural network models (RNN Seq2Seq) have achieved great success in ubiquitous areas of computation and applications. It was shown to be successful in modeling data with both temporal and spatial dependencies for translation or prediction tasks. In this study, we propose an embedding approach to visualize and interpret the representation of data by these models. Furthermore, we show that the embedding is an effective method for unsupervised learning and can be utilized to estimate the optimality of model training. In particular, we demonstrate that embedding space proj…
In the context of electroencephalogram (EEG)-based driver drowsiness recognition, it is still challenging to design a calibration-free system, since EEG signals vary significantly among different subjects and recording sessions. Many efforts have been made to use deep learning methods for mental state recognition from EEG signals. However, existing work mostly treats deep learning models as black-box classifiers, while what have been learned by the models and to which extent they are affected by the noise in EEG data are still underexplored. In this paper, we develop a novel convolutional neur…
Learning Interpretable Rules from Neural Networks: Neurosymbolic AI for Radar Hand Gesture Recognition
Technical University of Munich（慕尼黑技术大学）；Infineon Technologies AG（英飞凌科技有限公司）；Johannes Kepler University Linz（约翰·开普勒大学林茨分校）；Software Competence Center Hagenberg GmbH (SCCH)（哈根贝格软件竞争力中心（SCCH））
The current trend in automatic speech recognition is to leverage large amounts of labeled data to train supervised neural network models. Unfortunately, obtaining data for a wide range of domains to train robust models can be costly. However, it is relatively inexpensive to collect large amounts of unlabeled data from domains that we want the models to generalize to. In this paper, we propose a novel unsupervised adaptation method that learns to synthesize labeled data for the target domain from unlabeled in-domain data and labeled out-of-domain data. We first learn without supervision an inte…
Interpretable rationales for model predictions play a critical role in practical applications. In this study, we develop models possessing interpretable inference process for structured prediction. Specifically, we present a method of instance-based learning that learns similarities between spans. At inference time, each span is assigned a class label based on its similar spans in the training set, where it is easy to understand how much each training instance contributes to the predictions. Through empirical analysis on named entity recognition, we demonstrate that our method enables to build…
Center of Cognitive Interactive Technology (CITEC)（认知交互技术中心（CITEC））；Bielefeld University（比勒费尔德大学）；Eurodecision（欧洲决策公司）
Convolutional neural networks (CNNs) are deep learning frameworks which are well-known for their notable performance in classification tasks. Hence, many skeleton-based action recognition and segmentation (SBARS) algorithms benefit from them in their designs. However, a shortcoming of such applications is the general lack of spatial relationships between the input features in such data types. Besides, non-uniform temporal scalings is a common issue in skeleton-based data streams which leads to having different input sizes even within one specific action category. In this work, we propose a nov…
E^2-LLM: Bridging Neural Signals and Interpretable Affective Analysis
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东人工智能与数字经济实验室）；Zhejiang University（浙江大学）；Tsinghua University（清华大学）；Harbin Institute of Technology（哈尔滨工业大学）；Eastern Institute of Technology（东方技术研究所）；Huawei（华为）
Tecnologico de Monterrey（蒙特雷理工学院）；CHU Nancy（南锡大学中心医院）；Université de Lorraine（洛林大学）
Identifying the type of kidney stones can allow urologists to determine their formation cause, improving the early prescription of appropriate treatments to diminish future relapses. However, currently, the associated ex-vivo diagnosis (known as morpho-constitutional analysis, MCA) is time-consuming, expensive, and requires a great deal of experience, as it requires a visual analysis component that is highly operator dependant. Recently, machine learning methods have been developed for in-vivo endoscopic stone recognition. Shallow methods have been demonstrated to be reliable and interpretable…
University of Chinese Academy of Sciences（中国科学院大学）
Learning features from massive unlabelled data is a vast prevalent topic for high-level tasks in many machine learning applications. The recent great improvements on benchmark data sets achieved by increasingly complex unsupervised learning methods and deep learning models with lots of parameters usually requires many tedious tricks and much expertise to tune. However, filters learned by these complex architectures are quite similar to standard hand-crafted features visually. In this paper, unsupervised learning methods, such as PCA or auto-encoder, are employed as the building block to learn …
Max Planck Institute of Molecular Cell Biology and Genetics（马克斯·普朗克分子细胞生物学与遗传学研究所）；Center for Systems Biology Dresden（德累斯顿系统生物学中心）
Convolutional neural networks have become state-of-the-art in a wide range of image recognition tasks. The interpretation of their predictions, however, is an active area of research. Whereas various interpretation methods have been suggested for image classification, the interpretation of image segmentation still remains largely unexplored. To that end, we propose SEG-GRAD-CAM, a gradient-based method for interpreting semantic segmentation. Our method is an extension of the widely-used Grad-CAM method, applied locally to produce heatmaps showing the relevance of individual pixels for semantic…
Mode decomposition is a prototypical pattern recognition problem that can be addressed from the (a priori distinct) perspectives of numerical approximation, statistical inference and deep learning. Could its analysis through these combined perspectives be used as a Rosetta stone for deciphering mechanisms at play in deep learning? Motivated by this question we introduce programmable and interpretable regression networks for pattern recognition and address mode decomposition as a prototypical problem. The programming of these networks is achieved by assembling elementary modules decomposing and…
Otto von Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）
Deep Learning based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain better understanding of how Artificial Neural Networks (ANNs) accomplish their tasks, introspection methods have been proposed. Adapting such techniques from computer vision to speech recognition is not straight-forward, because speech data is more complex and less interpretable than image data. In this work, we introduce Gradient-adjusted Neuron Activation Profiles (GradNAPs) as means to interpret features and representations in Deep Neural Networks. GradNAPs are characteristic re…
Structured Contrastive Learning for Interpretable Latent Representations
Department of Electrical and Electronic Engineering, Imperial College London（帝国理工学院伦敦电子与电气工程系）；Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford（牛津大学生物医学工程研究所）
Deep learning is currently playing a crucial role toward higher levels of artificial intelligence. This paradigm allows neural networks to learn complex and abstract representations, that are progressively obtained by combining simpler ones. Nevertheless, the internal "black-box" representations automatically discovered by current neural architectures often suffer from a lack of interpretability, making of primary interest the study of explainable machine learning techniques. This paper summarizes our recent efforts to develop a more interpretable neural model for directly processing speech fr…
