English
Related papers

Related papers: Linear Explanations for Individual Neurons

200 papers

Why do biological and artificial neurons sometimes modularise, each encoding a single meaningful variable, and sometimes entangle their representation of many variables? In this work, we develop a theory of when biologically inspired…

Neurons and Cognition · Quantitative Biology 2025-08-05 Will Dorrell , Kyle Hsu , Luke Hollingsworth , Jin Hwa Lee , Jiajun Wu , Chelsea Finn , Peter E Latham , Tim EJ Behrens , James CR Whittington

A central challenge in sensory neuroscience is describing how the activity of populations of neurons can represent useful features of the external environment. However, while neurophysiologists have long been able to record the responses of…

Neural and Evolutionary Computing · Computer Science 2015-02-18 Chuan-Yung Tsai , David D. Cox

Pervasive polysemanticity in large language models (LLMs) undermines discrete neuron-concept attribution, posing a significant challenge for model interpretation and control. We systematically analyze both encoder and decoder based LLMs…

Machine Learning · Computer Science 2026-04-13 Muhammad Umair Haider , Hammad Rizwan , Hassan Sajjad , Peizhong Ju , A. B. Siddique

Neurons are the fundamental building blocks of deep neural networks, and their interconnections allow AI to achieve unprecedented results. Motivated by the goal of understanding how neurons encode information, compositional explanations…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Biagio La Rosa , Leilani H. Gilpin

Graph neural networks (GNNs) are highly effective on a variety of graph-related tasks; however, they lack interpretability and transparency. Current explainability approaches are typically local and treat GNNs as black-boxes. They do not…

Machine Learning · Computer Science 2023-03-10 Han Xuanyuan , Pietro Barbiero , Dobrik Georgiev , Lucie Charlotte Magister , Pietro Lió

Neural networks leverage robust internal representations in order to generalise. Learning them is difficult, and often requires a large training set that covers the data distribution densely. We study a common setting where our task is not…

Implicit Neural Representations (INRs) are powerful to parameterize continuous signals in computer vision. However, almost all INRs methods are limited to low-level tasks, e.g., image/video compression, super-resolution, and image…

Computer Vision and Pattern Recognition · Computer Science 2023-12-04 Yiran Song , Qianyu Zhou , Lizhuang Ma

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 effectiveness of deep neural architectures has been widely supported in terms of both experimental and foundational principles. There is also clear evidence that the activation function (e.g. the rectifier and the LSTM units) plays a…

Machine Learning · Computer Science 2018-10-08 Giuseppe Marra , Dario Zanca , Alessandro Betti , Marco Gori

Dimensionality reduction, a form of compression, can simplify representations of information to increase efficiency and reveal general patterns. Yet, this simplification also forfeits information, thereby reducing representational capacity.…

The capacity with which a system of independent neuron-like units represents a given set of stimuli is studied by calculating the mutual information between the stimuli and the neural responses. Both discrete noiseless and continuous noisy…

Disordered Systems and Neural Networks · Physics 2007-05-23 Ines Samengo , Alessandro Treves

The principles of neural encoding and computations are inherently collective and usually involve large populations of interacting neurons with highly correlated activities. While theories of neural function have long recognized the…

Neurons and Cognition · Quantitative Biology 2019-05-14 Christophe Gardella , Olivier Marre , Thierry Mora

Abstraction is a key verification technique to improve scalability. However, its use for neural networks is so far extremely limited. Previous approaches for abstracting classification networks replace several neurons with one of them that…

Logic in Computer Science · Computer Science 2023-07-21 Calvin Chau , Jan Křetínský , Stefanie Mohr

In this paper, we propose a new scheme for modelling the diverse behavior of neurons. We introduce the conditional activation, in which a neurons activation function is dynamically modified by a control signal. We apply this method to…

Neural and Evolutionary Computing · Computer Science 2018-03-15 Albert Lee , Bonnie Lam , Wenyuan Li , Hochul Lee , Wei-Hao Chen , Meng-Fan Chang , Kang. -L. Wang

Computational modeling is becoming a widely used methodology in modern neuroscience. However, as the complexity of the phenomena under study increases, the analysis of the results emerging from the simulations concomitantly becomes more…

Neurons and Cognition · Quantitative Biology 2020-03-16 Sergio E. Galindo , Pablo Toharia , Oscar D. Robles , Eduardo Ros , Luis Pastor , Jesús A. Garrido

The stunning empirical successes of neural networks currently lack rigorous theoretical explanation. What form would such an explanation take, in the face of existing complexity-theoretic lower bounds? A first step might be to show that…

Machine Learning · Computer Science 2017-07-18 Le Song , Santosh Vempala , John Wilmes , Bo Xie

Brain-computer interfaces surged extraordinary developments in recent years, and a significant discrepancy now exists between the abundance of available data and the limited headway made in achieving a unified theoretical framework. This…

The many variations of Implicit Neural Representations (INRs), where a neural network is trained as a continuous representation of a signal, have tremendous practical utility for downstream tasks including novel view synthesis, video…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Namitha Padmanabhan , Matthew Gwilliam , Pulkit Kumar , Shishira R Maiya , Max Ehrlich , Abhinav Shrivastava

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

Encoding models are used for predicting brain activity in response to sensory stimuli with the objective of elucidating how sensory information is represented in the brain. Encoding models typically comprise a nonlinear transformation of…

Neurons and Cognition · Quantitative Biology 2017-03-13 Umut Güçlü , Marcel A. J. van Gerven
‹ Prev 1 4 5 6 7 8 10 Next ›