English
Related papers

Related papers: Compositional Explanations of Neurons

200 papers

Compositional Explanations is a method for identifying logical formulas of concepts that approximate the neurons' behavior. However, these explanations are linked to the small spectrum of neuron activations (i.e., the highest ones) used to…

Machine Learning · Computer Science 2023-10-31 Biagio La Rosa , Leilani H. Gilpin , Roberto Capobianco

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

A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition. Humans can infer the structured relationships (e.g., grammatical rules) implicit in their sensory observations…

Machine Learning · Computer Science 2021-05-20 Jacob Russin , Roland Fernandez , Hamid Palangi , Eric Rosen , Nebojsa Jojic , Paul Smolensky , Jianfeng Gao

Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanations cannot be…

Machine Learning · Computer Science 2026-05-12 Ward Gauderis , Thomas Dooms , Steven T. Holmer , Kola Ayonrinde , Geraint A. Wiggins

Interpretability research often adopts a neuron-centric lens, treating individual neurons as the fundamental units of explanation. However, neuron-level explanations can be undermined by superposition, where single units respond to mixtures…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Julien Colin , Lore Goetschalckx , Thomas Fel , Victor Boutin , Thomas Serre , Nuria Oliver

The reasonable definition of semantic interpretability presents the core challenge in explainable AI. This paper proposes a method to modify a traditional convolutional neural network (CNN) into an interpretable compositional CNN, in order…

Computer Vision and Pattern Recognition · Computer Science 2021-07-12 Wen Shen , Zhihua Wei , Shikun Huang , Binbin Zhang , Jiaqi Fan , Ping Zhao , Quanshi Zhang

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

In recent years many methods have been developed to understand the internal workings of neural networks, often by describing the function of individual neurons in the model. However, these methods typically only focus on explaining the very…

Machine Learning · Computer Science 2024-05-14 Tuomas Oikarinen , Tsui-Wei Weng

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

Compositional learning, mastering the ability to combine basic concepts and construct more intricate ones, is crucial for human cognition, especially in human language comprehension and visual perception. This notion is tightly connected to…

Artificial Intelligence · Computer Science 2024-11-22 Sania Sinha , Tanawan Premsri , Parisa Kordjamshidi

Though modern neural networks have achieved impressive performance in both vision and language tasks, we know little about the functions that they implement. One possibility is that neural networks implicitly break down complex tasks into…

Computation and Language · Computer Science 2023-11-08 Michael A. Lepori , Thomas Serre , Ellie Pavlick

The mathematical representation of semantics is a key issue for Natural Language Processing (NLP). A lot of research has been devoted to finding ways of representing the semantics of individual words in vector spaces. Distributional…

Computation and Language · Computer Science 2014-11-13 Karl Moritz Hermann

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

Humans are highly efficient learners, with the ability to grasp the meaning of a new concept from just a few examples. Unlike popular computer vision systems, humans can flexibly leverage the compositional structure of the visual world,…

Computer Vision and Pattern Recognition · Computer Science 2021-05-21 Yanli Zhou , Brenden M. Lake

Deep neural networks (DNNs) have demonstrated impressive performance on a wide array of tasks, but they are usually considered opaque since internal structure and learned parameters are not interpretable. In this paper, we re-examine the…

Computer Vision and Pattern Recognition · Computer Science 2017-08-21 Yinpeng Dong , Hang Su , Jun Zhu , Fan Bao

Understanding the decision-making processes of neural networks is a central goal of mechanistic interpretability. In the context of Large Language Models (LLMs), this involves uncovering the underlying mechanisms and identifying the roles…

Computation and Language · Computer Science 2026-04-21 Nils Feldhus , Laura Kopf

Natural language is an appealing medium for explaining how large language models process and store information, but evaluating the faithfulness of such explanations is challenging. To help address this, we develop two modes of evaluation…

Computation and Language · Computer Science 2023-09-20 Jing Huang , Atticus Geiger , Karel D'Oosterlinck , Zhengxuan Wu , Christopher Potts

Compositional explanations are a family of methods that aim to describe the spatial alignment between neurons' receptive field activations and concepts through logical rules, typically computed via a search over all possible concept…

Artificial Intelligence · Computer Science 2026-05-28 Biagio La Rosa , Leilani H. Gilpin

In complex inferential tasks like question answering, machine learning models must confront two challenges: the need to implement a compositional reasoning process, and, in many applications, the need for this reasoning process to be…

Computer Vision and Pattern Recognition · Computer Science 2019-03-08 Ronghang Hu , Jacob Andreas , Trevor Darrell , Kate Saenko

While natural languages are compositional, how state-of-the-art neural models achieve compositionality is still unclear. We propose a deep network, which not only achieves competitive accuracy for text classification, but also exhibits…

Computation and Language · Computer Science 2017-07-07 Hongyu Guo
‹ Prev 1 2 3 10 Next ›