English
Related papers

Related papers: Finding Concept Representations in Neural Networks…

200 papers

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

The human ability to flexibly reason using analogies with domain-general content depends on mechanisms for identifying relations between concepts, and for mapping concepts and their relations across analogs. Building on a recent model of…

Artificial Intelligence · Computer Science 2021-10-06 Hongjing Lu , Nicholas Ichien , Keith J. Holyoak

What is a good visual representation for autonomous agents? We address this question in the context of semantic visual navigation, which is the problem of a robot finding its way through a complex environment to a target object, e.g. go to…

Computer Vision and Pattern Recognition · Computer Science 2019-07-04 Arsalan Mousavian , Alexander Toshev , Marek Fiser , Jana Kosecka , Ayzaan Wahid , James Davidson

Despite substantial progress in applying neural networks (NN) to a wide variety of areas, they still largely suffer from a lack of transparency and interpretability. While recent developments in explainable artificial intelligence attempt…

Computer Vision and Pattern Recognition · Computer Science 2021-05-04 Yunhao Ge , Yao Xiao , Zhi Xu , Meng Zheng , Srikrishna Karanam , Terrence Chen , Laurent Itti , Ziyan Wu

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

Existing research on making sense of deep neural networks often focuses on neuron-level interpretation, which may not adequately capture the bigger picture of how concepts are collectively encoded by multiple neurons. We present…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Haekyu Park , Nilaksh Das , Rahul Duggal , Austin P. Wright , Omar Shaikh , Fred Hohman , Duen Horng Chau

We describe how hierarchical concepts can be represented in three types of layered neural networks. The aim is to support recognition of the concepts when partial information about the concepts is presented, and also when some of the…

Neural and Evolutionary Computing · Computer Science 2025-03-25 Nancy A. Lynch

Coordinate-based Multilayer Perceptron (MLP) networks, despite being capable of learning neural implicit representations, are not performant for internal image synthesis applications. Convolutional Neural Networks (CNNs) are typically used…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Mikolaj Czerkawski , Javier Cardona , Robert Atkinson , Craig Michie , Ivan Andonovic , Carmine Clemente , Christos Tachtatzis

Understanding internal feature representations of deep neural networks (DNNs) is a fundamental step toward model interpretability. Inspired by neuroscience methods that probe biological neurons using visual stimuli, recent deep learning…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Hongbo Zhu , Angelo Cangelosi

The impressive performance of Convolutional Neural Networks (CNNs) when solving different vision problems is shadowed by their black-box nature and our consequent lack of understanding of the representations they build and how these…

Computer Vision and Pattern Recognition · Computer Science 2019-10-16 Ivet Rafegas , Maria Vanrell , Luis A. Alexandre , Guillem Arias

Maps are arguably one of the most fundamental concepts used to define and operate on manifold surfaces in differentiable geometry. Accordingly, in geometry processing, maps are ubiquitous and are used in many core applications, such as…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Luca Morreale , Noam Aigerman , Vladimir Kim , Niloy J. Mitra

Making sense of the world and acting in it relies on building simplified mental representations that abstract away aspects of reality. This principle of cognitive mapping is universal to agents with limited resources. Living organisms,…

Artificial Intelligence · Computer Science 2025-04-30 Marta Kryven , Cole Wyeth , Aidan Curtis , Kevin Ellis

Visual representations can be defined as the activations of neuronal populations in response to images. The activation of a neuron as a function over all image space has been described as a "tuning landscape". As a function over a…

Neurons and Cognition · Quantitative Biology 2022-12-29 Binxu Wang , Carlos R. Ponce

Understanding the deep representations of complex networks is an important step of building interpretable and trustworthy machine learning applications in the age of internet. Global surrogate models that approximate the predictions of a…

Machine Learning · Computer Science 2022-03-15 Baihan Lin

To interpret the meanings of colors in visualizations of categorical information, people must determine how distinct colors correspond to different concepts. This process is easier when assignments between colors and concepts in…

Human-Computer Interaction · Computer Science 2019-10-08 Ragini Rathore , Zachary Leggon , Laurent Lessard , Karen B. Schloss

The representations learned by deep neural networks are difficult to interpret in part due to their large parameter space and the complexities introduced by their multi-layer structure. We introduce a method for computing persistent…

Machine Learning · Computer Science 2019-05-31 Thomas Gebhart , Paul Schrater , Alan Hylton

The cognitive framework of conceptual spaces bridges the gap between symbolic and subsymbolic AI by proposing an intermediate conceptual layer where knowledge is represented geometrically. There are two main approaches for obtaining the…

Machine Learning · Computer Science 2019-08-08 Lucas Bechberger , Elektra Kypridemou

A longstanding problem for Deep Neural Networks (DNNs) is understanding their puzzling ability to generalize well. We approach this problem through the unconventional angle of \textit{cognitive abstraction mechanisms}, drawing inspiration…

Machine Learning · Computer Science 2020-04-20 Alex Gain , Hava Siegelmann

The same concept can mean different things or be instantiated in different forms depending on context, suggesting a degree of flexibility within the conceptual system. We propose that a compositional network model can be used to capture and…

Neurons and Cognition · Quantitative Biology 2019-03-21 Sarah H. Solomon , John D. Medaglia , Sharon L. Thompson-Schill

With the recent success of deep neural networks in computer vision, it is important to understand the internal working of these networks. What does a given neuron represent? The concepts captured by a neuron may be hard to understand or…

Computer Vision and Pattern Recognition · Computer Science 2020-12-29 Suryabhan Singh Hada , Miguel Á. Carreira-Perpiñán