English
Related papers

Related papers: Towards falsifiable interpretability research

200 papers

Faithfully summarizing the knowledge encoded by a deep neural network (DNN) into a few symbolic primitive patterns without losing much information represents a core challenge in explainable AI. To this end, Ren et al. (2024) have derived a…

Machine Learning · Computer Science 2024-09-16 Lu Chen , Siyu Lou , Benhao Huang , Quanshi Zhang

The widespread use of deep neural networks has achieved substantial success in many tasks. However, there still exists a huge gap between the operating mechanism of deep learning models and human-understandable decision making, so that…

Artificial Intelligence · Computer Science 2021-03-08 Xiaowei Zhou , Jie Yin , Ivor Tsang , Chen Wang

An important line of research attempts to explain CNN image classifier predictions and intermediate layer representations in terms of human-understandable concepts. Previous work supports that deep representations are linearly separable…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Alexandros Doumanoglou , Stylianos Asteriadis , Dimitrios Zarpalas

Imagine experiencing a crash as the passenger of an autonomous vehicle. Wouldn't you want to know why it happened? Current end-to-end optimizable deep neural networks (DNNs) in 3D detection, multi-object tracking, and motion forecasting…

Computer Vision and Pattern Recognition · Computer Science 2022-10-05 Benjamin Thérien , Krzysztof Czarnecki

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…

Machine Learning · Computer Science 2019-10-08 Yulong Wang , Xiaolin Hu , Hang Su

Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior. The interpretation of individual units, which are neurons in MLPs or convolution kernels in convolutional networks, has been paid…

Machine Learning · Computer Science 2019-11-14 Li Chen , Hailun Ding , Qi Li , Zhuo Li , Jian Peng , Haifeng Li

Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior. The interpretation of individual units, which are neurons in MLPs or convolution kernels in convolutional networks, has been paid…

Computer Vision and Pattern Recognition · Computer Science 2018-12-10 Li Chen , Hailun Ding , Qi Li , Zhuo Li , Jian Peng , Haifeng Li

With the growing complexity and capability of large language models, a need to understand model reasoning has emerged, often motivated by an underlying goal of controlling and aligning models. While numerous interpretability and steering…

Machine Learning · Computer Science 2025-02-12 Usha Bhalla , Suraj Srinivas , Asma Ghandeharioun , Himabindu Lakkaraju

Deep learning methods are achieving ever-increasing performance on many artificial intelligence tasks. A major limitation of deep models is that they are not amenable to interpretability. This limitation can be circumvented by developing…

Machine Learning · Computer Science 2022-07-05 Hao Yuan , Haiyang Yu , Shurui Gui , Shuiwang Ji

Deep neural networks (DNNs) achieve remarkable predictive performance but remain difficult to interpret, largely due to overparameterization that obscures the minimal structure required for interpretation. Here we introduce DeepIn, a…

Methodology · Statistics 2026-03-26 Zhiyao Tan , Liu Li , Huazhen Lin

Deep neural networks have exhibited remarkable performance across a wide range of real-world tasks. However, comprehending the underlying reasons for their effectiveness remains a challenging problem. Interpreting deep neural networks…

Computer Vision and Pattern Recognition · Computer Science 2023-10-18 Chenxu Zhao , Wei Qian , Yucheng Shi , Mengdi Huai , Ninghao Liu

Saliency methods aim to explain the predictions of deep neural networks. These methods lack reliability when the explanation is sensitive to factors that do not contribute to the model prediction. We use a simple and common pre-processing…

Deep neural networks have become essential for numerous applications due to their strong empirical performance such as vision, RL, and classification. Unfortunately, these networks are quite difficult to interpret, and this limits their…

Machine Learning · Computer Science 2021-10-12 Sina Alemohammad , Hossein Babaei , CJ Barberan , Naiming Liu , Lorenzo Luzi , Blake Mason , Richard G. Baraniuk

Image decomposition aims to analyze an image into elementary components, which is essential for numerous downstream tasks and also by nature provides certain interpretability to the analysis. Deep learning can be powerful for such tasks,…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Sihan Wang , Shangqi Gao , Fuping Wu , Xiahai Zhuang

Interpretable brain network models for disease prediction are of great value for the advancement of neuroscience. GNNs are promising to model complicated network data, but they are prone to overfitting and suffer from poor interpretability,…

Machine Learning · Computer Science 2021-07-13 Hejie Cui , Wei Dai , Yanqiao Zhu , Xiaoxiao Li , Lifang He , Carl Yang

State-of-the-art deep-learning-based approaches to Natural Language Processing (NLP) are credited with various capabilities that involve reasoning with natural language texts. In this paper we carry out a large-scale empirical study…

Computation and Language · Computer Science 2022-11-11 Viktor Schlegel , Kamen V. Pavlov , Ian Pratt-Hartmann

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Machine Learning · Computer Science 2025-03-17 Theodora-Mara Pîslar , Sara Magliacane , Atticus Geiger

Deep learning models are favored in many research and industry areas and have reached the accuracy of approximating or even surpassing human level. However they've long been considered by researchers as black-box models for their…

Machine Learning · Computer Science 2020-10-16 Xiaojian Wang , Jingyuan Wang , Ke Tang

NLP Interpretability aims to increase trust in model predictions. This makes evaluating interpretability approaches a pressing issue. There are multiple datasets for evaluating NLP Interpretability, but their dependence on human provided…

Computation and Language · Computer Science 2020-12-29 Yves Rychener , Xavier Renard , Djamé Seddah , Pascal Frossard , Marcin Detyniecki

Graph neural networks (GNNs) are powerful graph-based deep-learning models that have gained significant attention and demonstrated remarkable performance in various domains, including natural language processing, drug discovery, and…

Machine Learning · Computer Science 2023-06-06 Jaykumar Kakkad , Jaspal Jannu , Kartik Sharma , Charu Aggarwal , Sourav Medya