English
Related papers

Related papers: Codebook Features: Sparse and Discrete Interpretab…

200 papers

This work proposes the first strategy to make distributed training of neural networks resilient to computing errors, a problem that has remained unsolved despite being first posed in 1956 by von Neumann. He also speculated that the…

Information Theory · Computer Science 2019-03-05 Sanghamitra Dutta , Ziqian Bai , Tze Meng Low , Pulkit Grover

The increasing use of complex machine learning models in education has led to concerns about their interpretability, which in turn has spurred interest in developing explainability techniques that are both faithful to the model's inner…

Machine Learning · Computer Science 2025-05-13 Juan D. Pinto , Luc Paquette

Machine learning models trained on code and related artifacts offer valuable support for software maintenance but suffer from interpretability issues due to their complex internal variables. These concerns are particularly significant in…

Software Engineering · Computer Science 2024-07-15 Vahid Majdinasab , Amin Nikanjam , Foutse Khomh

Representation is a core issue in artificial intelligence. Humans use discrete language to communicate and learn from each other, while machines use continuous features (like vector, matrix, or tensor in deep neural networks) to represent…

Computer Vision and Pattern Recognition · Computer Science 2022-01-17 Yuqi Wang , Xu-Yao Zhang , Cheng-Lin Liu , Zhaoxiang Zhang

Despite their impressive performance, contemporary neural networks often lack structural safeguards that promote stable learning and interpretable behavior. In this work, we introduce a reformulation of layer-level transformations that…

Machine Learning · Computer Science 2025-08-04 Saleh Nikooroo , Thomas Engel

We introduce methods for discovering and applying sparse feature circuits. These are causally implicated subnetworks of human-interpretable features for explaining language model behaviors. Circuits identified in prior work consist of…

Machine Learning · Computer Science 2025-03-28 Samuel Marks , Can Rager , Eric J. Michaud , Yonatan Belinkov , David Bau , Aaron Mueller

In a spiking neural network (SNN), individual neurons operate autonomously and only communicate with other neurons sparingly and asynchronously via spike signals. These characteristics render a massively parallel hardware implementation of…

Machine Learning · Computer Science 2017-05-17 Ping Tak Peter Tang , Tsung-Han Lin , Mike Davies

Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Xili Dai , Mingyang Li , Pengyuan Zhai , Shengbang Tong , Xingjian Gao , Shao-Lun Huang , Zhihui Zhu , Chong You , Yi Ma

How do we imagine visual objects and combine them to create new forms? To answer this question, we need to explore the cognitive, computational and neural mechanisms underlying imagery and creativity. The body of research on deep learning…

Neurons and Cognition · Quantitative Biology 2021-12-14 Shekoofeh Hedayati , Roger Beaty , Brad Wyble

The advent of neural audio codecs has increased in popularity due to their potential for efficiently modeling audio with transformers. Such advanced codecs represent audio from a highly continuous waveform to low-sampled discrete units. In…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-19 Samir Sadok , Julien Hauret , Éric Bavu

Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason they succeed, it also causes them to learn…

Computer Vision and Pattern Recognition · Computer Science 2014-02-20 Christian Szegedy , Wojciech Zaremba , Ilya Sutskever , Joan Bruna , Dumitru Erhan , Ian Goodfellow , Rob Fergus

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

Systems neuroscience relies on two complementary views of neural data, characterized by single neuron tuning curves and analysis of population activity. These two perspectives combine elegantly in neural latent variable models that…

Despite rapid adoption and deployment of large language models (LLMs), the internal computations of these models remain opaque and poorly understood. In this work, we seek to understand how high-level human-interpretable features are…

Machine Learning · Computer Science 2023-06-06 Wes Gurnee , Neel Nanda , Matthew Pauly , Katherine Harvey , Dmitrii Troitskii , Dimitris Bertsimas

Neural networks can be compressed to reduce memory and computational requirements, or to increase accuracy by facilitating the use of a larger base architecture. In this paper we focus on pruning individual neurons, which can simultaneously…

Computer Vision and Pattern Recognition · Computer Science 2018-04-20 Bin Dai , Chen Zhu , David Wipf

Although individual neurons and neural populations exhibit the phenomenon of representational drift, perceptual and behavioral outputs of many neural circuits can remain stable across time scales over which representational drift is…

Biological visual systems learn from limited experience, unlike deep learning models that rely on millions of training images. What learning principles make this possible? We tested whether efficient coding, the idea that neural…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Ananya Passi , Brian S. Robinson , Michael F. Bonner

Code-trained language models have proven to be highly effective for various code intelligence tasks. However, they can be challenging to train and deploy for many software engineering applications due to computational bottlenecks and memory…

Software Engineering · Computer Science 2024-02-19 Arushi Sharma , Zefu Hu , Christopher Quinn , Ali Jannesari

Latent representation learning has been an active field of study for decades in numerous applications. Inspired among others by the tokenization from Natural Language Processing and motivated by the research of a simple data representation,…

Signal Processing · Electrical Eng. & Systems 2024-09-26 Benoît Giniès , Xiaoyu Bie , Olivier Fercoq , Gaël Richard

Neural networks are often described as black boxes, reflecting the significant challenge of understanding their internal workings and interactions. We propose a different perspective that challenges the prevailing view: rather than being…

Machine Learning · Computer Science 2025-10-23 Shuchen Wu , Stephan Alaniz , Shyamgopal Karthik , Peter Dayan , Eric Schulz , Zeynep Akata