English
Related papers

Related papers: Causal Interpretation of Neural Network Computatio…

200 papers

Color Appearance Models are biological networks that consist of a cascade of linear+nonlinear layers that modify the linear measurements at the retinal photo-receptors leading to an internal (nonlinear) representation of color that…

Neurons and Cognition · Quantitative Biology 2022-10-13 Jesus Malo

This article summarizes principles and ideas from the emerging area of applying \textit{conditional computation} methods to the design of neural networks. In particular, we focus on neural networks that can dynamically activate or…

Machine Learning · Computer Science 2024-07-09 Simone Scardapane , Alessandro Baiocchi , Alessio Devoto , Valerio Marsocci , Pasquale Minervini , Jary Pomponi

We propose a novel method that leverages sparse autoencoders (SAEs) and clustering techniques to analyze the internal token representations of large language models (LLMs) and guide generations in mathematical reasoning tasks. Our approach…

Artificial Intelligence · Computer Science 2025-10-03 Daniel Zhao , Abhilash Shankarampeta , Lanxiang Hu , Tajana Rosing , Hao Zhang

In this paper, we propose a novel Explanation Neural Network (XNN) to explain the predictions made by a deep network. The XNN works by learning a nonlinear embedding of a high-dimensional activation vector of a deep network layer into a…

Computer Vision and Pattern Recognition · Computer Science 2020-12-14 Zhongang Qi , Saeed Khorram , Fuxin Li

In computer vision, some attribution methods for explaining CNNs attempt to study how the intermediate features affect the network prediction. However, they usually ignore the feature hierarchies among the intermediate features. This paper…

Computer Vision and Pattern Recognition · Computer Science 2023-10-13 Ming-Ming Cheng , Peng-Tao Jiang , Ling-Hao Han , Liang Wang , Philip Torr

In general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are generally smoother than reflectance (albedo) changes, these methods may fail in…

Computer Vision and Pattern Recognition · Computer Science 2021-01-22 Anil S. Baslamisli , Partha Das , Hoang-An Le , Sezer Karaoglu , Theo Gevers

Recently Convolutional Neural Networks have been proposed for Sequence Modelling tasks such as Image Caption Generation. However, unlike Recurrent Neural Networks, the performance of Convolutional Neural Networks as Decoders for Image…

Computer Vision and Pattern Recognition · Computer Science 2021-03-09 Sulabh Katiyar , Samir Kumar Borgohain

We study the problem of explaining a rich class of behavioral properties of deep neural networks. Distinctively, our influence-directed explanations approach this problem by peering inside the network to identify neurons with high influence…

Machine Learning · Computer Science 2018-11-14 Klas Leino , Shayak Sen , Anupam Datta , Matt Fredrikson , Linyi Li

To understand sensory coding, we must ask not only how much information neurons encode, but also what that information is about. This requires decomposing mutual information into contributions from individual stimuli and stimulus features:…

Neurons and Cognition · Quantitative Biology 2025-10-23 Steeve Laquitaine , Simone Azeglio , Carlo Paris , Ulisse Ferrari , Matthew Chalk

Deep neural networks are widely used in various domains. However, the nature of computations at each layer of the deep networks is far from being well understood. Increasing the interpretability of deep neural networks is thus important.…

Machine Learning · Computer Science 2018-12-19 Haiping Huang

The standard approach to providing interpretability to deep convolutional neural networks (CNNs) consists of visualizing either their feature maps, or the image regions that contribute the most to the prediction. In this paper, we introduce…

Computer Vision and Pattern Recognition · Computer Science 2019-01-09 Krishna Kanth Nakka , Mathieu Salzmann

It has been proposed that, when processing a stream of events, humans divide their experiences in terms of inferred latent causes (LCs) to support context-dependent learning. However, when shared structure is present across contexts, it is…

Neurons and Cognition · Quantitative Biology 2024-06-10 Qihong Lu , Tan T. Nguyen , Qiong Zhang , Uri Hasson , Thomas L. Griffiths , Jeffrey M. Zacks , Samuel J. Gershman , Kenneth A. Norman

Interpretability of Deep Neural Networks using concept-based models offers a promising way to explain model behavior through human-understandable concepts. A parallel line of research focuses on disentangling the data distribution into its…

Machine Learning · Computer Science 2024-07-30 Sanchit Sinha , Guangzhi Xiong , Aidong Zhang

Deploying reliable deep learning techniques in interdisciplinary applications needs learned models to output accurate and (even more importantly) explainable predictions. Existing approaches typically explicate network outputs in a post-hoc…

Machine Learning · Computer Science 2023-05-26 Chenyu Xue , Fan Wang , Yuanzhuo Zhu , Hui Li , Deyu Meng , Dinggang Shen , Chunfeng Lian

We introduce Discovering Conceptual Network Explanations (DCNE), a new approach for generating human-comprehensible visual explanations to enhance the interpretability of deep neural image classifiers. Our method automatically finds visual…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Neehar Kondapaneni , Markus Marks , Oisin Mac Aodha , Pietro Perona

The impressive performance of neural networks on natural language processing tasks attributes to their ability to model complicated word and phrase compositions. To explain how the model handles semantic compositions, we study hierarchical…

Computation and Language · Computer Science 2020-06-16 Xisen Jin , Zhongyu Wei , Junyi Du , Xiangyang Xue , Xiang Ren

This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…

Computation and Language · Computer Science 2024-05-22 Charles O'Neill , Thang Bui

We present a new deep unfolding network for analysis-sparsity-based Compressed Sensing. The proposed network coined Decoding Network (DECONET) jointly learns a decoder that reconstructs vectors from their incomplete, noisy measurements and…

Information Theory · Computer Science 2023-06-21 Vicky Kouni , Yannis Panagakis

Neural networks are capable of superposition -- representing more features than there are dimensions. Recent work considers the analogous concept for computation instead of storage, proposing theoretical constructions. But there has been…

Machine Learning · Computer Science 2025-07-15 Adam Newgas

Revealing the transparency of Deep Neural Networks (DNNs) has been widely studied to describe the decision mechanisms of network inner structures. In this paper, we propose a novel post-hoc framework, Unfold and Conquer Attribution Guidance…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Jung-Ho Hong , Woo-Jeoung Nam , Kyu-Sung Jeon , Seong-Whan Lee