English
Related papers

Related papers: Understanding polysemanticity in neural networks t…

200 papers

Mechanistic interpretability aims to explain what a neural network has learned at a nuts-and-bolts level. What are the fundamental primitives of neural network representations? Previous mechanistic descriptions have used individual neurons…

We propose a new interpretability method for neural networks, which is based on a novel mathematico-philosophical theory of reasons. Our method computes a vector for each neuron, called its reasons vector. We then can compute how strongly…

Machine Learning · Computer Science 2025-05-21 Levin Hornischer , Hannes Leitgeb

Individual neurons in neural networks often represent a mixture of unrelated features. This phenomenon, called polysemanticity, can make interpreting neural networks more difficult and so we aim to understand its causes. We propose doing so…

Neural and Evolutionary Computing · Computer Science 2025-03-26 Adam Scherlis , Kshitij Sachan , Adam S. Jermyn , Joe Benton , Buck Shlegeris

We introduce combinatorial interpretability, a methodology for understanding neural computation by analyzing the combinatorial structures in the sign-based categorization of a network's weights and biases. We demonstrate its power through…

Machine Learning · Computer Science 2025-05-07 Micah Adler , Dan Alistarh , Nir Shavit

One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise,…

Machine Learning · Computer Science 2023-10-05 Hoagy Cunningham , Aidan Ewart , Logan Riggs , Robert Huben , Lee Sharkey

Along with the great success of deep neural networks, there is also growing concern about their black-box nature. The interpretability issue affects people's trust on deep learning systems. It is also related to many ethical problems, e.g.,…

Machine Learning · Computer Science 2022-02-01 Yu Zhang , Peter Tiňo , Aleš Leonardis , Ke Tang

Mechanistic interpretability is concerned with analyzing individual components in a (convolutional) neural network (CNN) and how they form larger circuits representing decision mechanisms. These investigations are challenging since CNNs…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 Robin Hesse , Jonas Fischer , Simone Schaub-Meyer , Stefan Roth

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

Modeling the behavior of coupled networks is challenging due to their intricate dynamics. For example in neuroscience, it is of critical importance to understand the relationship between the functional neural processes and anatomical…

Machine Learning · Computer Science 2021-04-20 Hongyuan You , Sikun Lin , Ambuj K. Singh

The proliferation of deep neural networks in various domains has seen an increased need for interpretability of these models. Preliminary work done along this line and papers that surveyed such, are focused on high-level representation…

Computation and Language · Computer Science 2022-08-17 Hassan Sajjad , Nadir Durrani , Fahim Dalvi

Mechanistic interpretability aims to understand how models store representations by breaking down neural networks into interpretable units. However, the occurrence of polysemantic neurons, or neurons that respond to multiple unrelated…

Computer Vision and Pattern Recognition · Computer Science 2023-04-20 Laura O'Mahony , Vincent Andrearczyk , Henning Muller , Mara Graziani

Neural networks have achieved remarkable success across various fields. However, the lack of interpretability limits their practical use, particularly in critical decision-making scenarios. Post-hoc interpretability, which provides…

Machine Learning · Computer Science 2025-11-21 Yang Ji , Ying Sun , Yuting Zhang , Zhigaoyuan Wang , Yuanxin Zhuang , Zheng Gong , Dazhong Shen , Chuan Qin , Hengshu Zhu , Hui Xiong

Deep learning models often suffer from a lack of interpretability due to polysemanticity, where individual neurons are activated by multiple unrelated semantics, resulting in unclear attributions of model behavior. Recent advances in…

Machine Learning · Computer Science 2024-10-30 Qi Zhang , Yifei Wang , Jingyi Cui , Xiang Pan , Qi Lei , Stefanie Jegelka , Yisen Wang

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…

Machine Learning · Statistics 2023-10-19 David Klindt , Sophia Sanborn , Francisco Acosta , Frédéric Poitevin , Nina Miolane

We present an interpretable neural network approach to predicting and understanding politeness in natural language requests. Our models are based on simple convolutional neural networks directly on raw text, avoiding any manual…

Computation and Language · Computer Science 2016-10-11 Malika Aubakirova , Mohit Bansal

Modern deep networks are highly complex and their inferential outcome very hard to interpret. This is a serious obstacle to their transparent deployment in safety-critical or bias-aware applications. This work contributes to post-hoc…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Konstantinos P. Panousis , Sotirios Chatzis

Sustainable research on computational models of neuronal networks requires published models to be understandable, reproducible, and extendable. Missing details or ambiguities about mathematical concepts and assumptions, algorithmic…

We present neuron embeddings, a representation that can be used to tackle polysemanticity by identifying the distinct semantic behaviours in a neuron's characteristic dataset examples, making downstream manual or automatic interpretation…

Machine Learning · Computer Science 2024-11-14 Alex Foote

Neural networks have become increasingly prevalent within the geosciences, although a common limitation of their usage has been a lack of methods to interpret what the networks learn and how they make decisions. As such, neural networks…

Atmospheric and Oceanic Physics · Physics 2020-10-28 Benjamin A. Toms , Elizabeth A. Barnes , Imme Ebert-Uphoff

Neural networks are becoming a popular tool for solving many real-world problems such as object recognition and machine translation, thanks to its exceptional performance as an end-to-end solution. However, neural networks are complex…

Machine Learning · Computer Science 2020-09-29 Guoliang Dong , Jingyi Wang , Jun Sun , Yang Zhang , Xinyu Wang , Ting Dai , Jin Song Dong , Xingen Wang
‹ Prev 1 2 3 10 Next ›