相关论文: Interpretable Textual Neuron Representations for N…

Understanding internal feature representations of deep neural networks (DNNs) is a fundamental step toward model interpretability. Inspired by neuroscience methods that probe biological neurons using visual stimuli, recent deep learning…

We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure…

We create a reusable Transformer, BrainBERT, for intracranial recordings bringing modern representation learning approaches to neuroscience. Much like in NLP and speech recognition, this Transformer enables classifying complex concepts,…

Humans are able to explain their reasoning. On the contrary, deep neural networks are not. This paper attempts to bridge this gap by introducing a new way to design interpretable neural networks for classification, inspired by physiological…

Recent NLP literature has seen growing interest in improving model interpretability. Along this direction, we propose a trainable neural network layer that learns a global interaction graph between words and then selects more informative…

Modern neuroimaging techniques, such as diffusion tensor imaging (DTI) and functional magnetic resonance imaging (fMRI), enable us to model the human brain as a brain network or connectome. Capturing brain networks' structural information…

Deep learning models for natural language processing (NLP) are inherently complex and often viewed as black box in nature. This paper develops an approach for interpreting convolutional neural networks for text classification problems by…

Recent advances in Deep Learning have led to a significant performance increase on several NLP tasks, however, the models become more and more computationally demanding. Therefore, this paper tackles the domain of computationally efficient…

Interpretability researchers have attempted to understand MLP neurons of language models based on both the contexts in which they activate and their output weight vectors. They have paid little attention to a complementary aspect: the…

Coordinate-based Multilayer Perceptron (MLP) networks, despite being capable of learning neural implicit representations, are not performant for internal image synthesis applications. Convolutional Neural Networks (CNNs) are typically used…

We propose a new kind of embedding for natural language text that deeply represents semantic meaning. Standard text embeddings use the outputs from hidden layers of a pretrained language model. In our method, we let a language model learn…

Natural Language Processing (NLP) is widely used in fields like machine translation and sentiment analysis. However, traditional NLP models struggle with accuracy and efficiency. This paper introduces Deep Convolutional Neural Networks…

The human visual system provides us with a rich and meaningful percept of the world, transforming retinal signals into visuo-semantic representations. For a model of these representations, here we leveraged a combination of two currently…

Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features. However, many neurons exhibit $\textit{mixed selectivity}$, i.e., they represent multiple unrelated features. A…

In this paper, we evaluate the quality of knowledge representations encoded in deep neural networks (DNNs) for 3D point cloud processing. We propose a method to disentangle the overall model vulnerability into the sensitivity to the…

Interpretable graph neural networks (XGNNs ) are widely adopted in various scientific applications involving graph-structured data. Existing XGNNs predominantly adopt the attention-based mechanism to learn edge or node importance for…

ConceptLens is an innovative tool designed to illuminate the intricate workings of deep neural networks (DNNs) by visualizing hidden neuron activations. By integrating deep learning with symbolic methods, ConceptLens offers users a unique…

Deep reinforcement learning (DRL), through learning policies or values represented by neural networks, has successfully addressed many complex control problems. However, the neural networks introduced by DRL lack interpretability and…

Providing textual concept-based explanations for neurons in deep neural networks (DNNs) is of importance in understanding how a DNN model works. Prior works have associated concepts with neurons based on examples of concepts or a…

Sometimes it is not enough for a DNN to produce an outcome. For example, in applications such as healthcare, users need to understand the rationale of the decisions. Therefore, it is imperative to develop algorithms to learn models with…