English
Related papers

Related papers: Universal Neurons in GPT2 Language Models

200 papers

Neural Module Networks, originally proposed for the task of visual question answering, are a class of neural network architectures that involve human-specified neural modules, each designed for a specific form of reasoning. In current…

Machine Learning · Computer Science 2019-11-11 Vardaan Pahuja , Jie Fu , Sarath Chandar , Christopher J. Pal

Measuring similarity of neural networks to understand and improve their behavior has become an issue of great importance and research interest. In this survey, we provide a comprehensive overview of two complementary perspectives of…

Machine Learning · Computer Science 2025-05-22 Max Klabunde , Tobias Schumacher , Markus Strohmaier , Florian Lemmerich

Recent artificial neural networks that process natural language achieve unprecedented performance in tasks requiring sentence-level understanding. As such, they could be interesting models of the integration of linguistic information in the…

Computation and Language · Computer Science 2023-02-17 Sophie Arana , Jacques Pesnot Lerousseau , Peter Hagoort

There is a wide variety of speech processing tasks ranging from extracting content information from speech signals to generating speech signals. For different tasks, model networks are usually designed and tuned separately. If a universal…

Computation and Language · Computer Science 2021-06-01 Yi-Chen Chen , Po-Han Chi , Shu-wen Yang , Kai-Wei Chang , Jheng-hao Lin , Sung-Feng Huang , Da-Rong Liu , Chi-Liang Liu , Cheng-Kuang Lee , Hung-yi Lee

Neural networks (NNs) and decision trees (DTs) are both popular models of machine learning, yet coming with mutually exclusive advantages and limitations. To bring the best of the two worlds, a variety of approaches are proposed to…

Machine Learning · Computer Science 2022-09-09 Haoling Li , Jie Song , Mengqi Xue , Haofei Zhang , Jingwen Ye , Lechao Cheng , Mingli Song

The human brain is a complex network of interconnected brain regions organized into functional modules with distinct roles in cognition and behavior. An important question concerns the persistence and stability of these modules over the…

Neurons and Cognition · Quantitative Biology 2015-10-28 Richard F. Betzel , Bratislav Mišić , Ye He , Jeffrey Rumschlag , Xi-Nian Zuo , Olaf Sporns

OthelloGPT, a transformer trained to predict valid moves in Othello, provides an ideal testbed for interpretability research. The model is complex enough to exhibit rich computational patterns, yet grounded in rule-based game logic that…

Machine Learning · Computer Science 2025-11-04 Aditya Singh , Zihang Wen , Srujananjali Medicherla , Adam Karvonen , Can Rager

One of the reasons why many neural networks are capable of replicating complicated tasks or functions is their universal property. Though the past few decades have seen tremendous advances in theories of neural networks, a single…

Machine Learning · Computer Science 2023-05-09 Tan Bui-Thanh

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

Sequential neuronal activity underlies a wide range of processes in the brain. Neuroscientific evidence for neuronal sequences has been reported in domains as diverse as perception, motor control, speech, spatial navigation and memory.…

Adaptation and Self-Organizing Systems · Physics 2020-04-03 Sascha Frölich , Dimitrije Marković , Stefan J. Kiebel

Humans represent scenes and objects in rich feature spaces, carrying information that allows us to generalise about category memberships and abstract functions with few examples. What determines whether a neural network model generalises…

How neural networks in the human brain represent commonsense knowledge, and complete related reasoning tasks is an important research topic in neuroscience, cognitive science, psychology, and artificial intelligence. Although the…

Neural and Evolutionary Computing · Computer Science 2022-07-13 Hongjian Fang , Yi Zeng , Jianbo Tang , Yuwei Wang , Yao Liang , Xin Liu

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

Much progress has been made in uncovering the computational capabilities of spiking neural networks. However, spiking neurons will always be more expensive to simulate compared to rate neurons because of the inherent disparity in time…

Neurons and Cognition · Quantitative Biology 2013-10-31 Michael A. Buice , Carson C. Chow

Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-box nature, it is often difficult to understand the prediction…

Machine Learning · Computer Science 2022-07-18 Xuhong Li , Haoyi Xiong , Xingjian Li , Xuanyu Wu , Xiao Zhang , Ji Liu , Jiang Bian , Dejing Dou

Mechanistic interpretability aims to understand the inner workings of large neural networks by identifying circuits, or minimal subgraphs within the model that implement algorithms responsible for performing specific tasks. These circuits…

Machine Learning · Computer Science 2024-12-06 Jatin Nainani , Sankaran Vaidyanathan , AJ Yeung , Kartik Gupta , David Jensen

The past few years have seen a surge in the application of quantum theory methodologies and quantum-like modeling in fields such as cognition, psychology, and decision-making. Despite the success of this approach in explaining various…

Physics and Society · Physics 2025-11-18 Andrei Khrennikov , Masanao Ozawa , Felix Benninger , Oded Shor

The interpretability of neural networks (NNs) is a challenging but essential topic for transparency in the decision-making process using machine learning. One of the reasons for the lack of interpretability is random weight initialization,…

Machine Learning · Computer Science 2021-03-01 Shohei Kubota , Hideaki Hayashi , Tomohiro Hayase , Seiichi Uchida

Neural pathways as model explanations consist of a sparse set of neurons that provide the same level of prediction performance as the whole model. Existing methods primarily focus on accuracy and sparsity but the generated pathways may…

Computer Vision and Pattern Recognition · Computer Science 2023-09-19 Xinmiao Lin , Wentao Bao , Qi Yu , Yu Kong

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