English
Related papers

Related papers: Sparse, Geometric Autoencoder Models of V1

200 papers

Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Xili Dai , Mingyang Li , Pengyuan Zhai , Shengbang Tong , Xingjian Gao , Shao-Lun Huang , Zhihui Zhu , Chong You , Yi Ma

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

The representation of images in the brain is known to be sparse. That is, as neural activity is recorded in a visual area ---for instance the primary visual cortex of primates--- only a few neurons are active at a given time with respect to…

Computer Vision and Pattern Recognition · Computer Science 2017-01-25 Laurent Perrinet

Autoencoders have been used for finding interpretable and disentangled features underlying neural network representations in both image and text domains. While the efficacy and pitfalls of such methods are well-studied in vision, there is a…

Machine Learning · Computer Science 2025-02-06 Abhinav Menon , Manish Shrivastava , David Krueger , Ekdeep Singh Lubana

In this note we present a generative model of natural images consisting of a deep hierarchy of layers of latent random variables, each of which follows a new type of distribution that we call rectified Gaussian. These rectified Gaussian…

Machine Learning · Statistics 2016-03-01 Tim Salimans

This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…

Computation and Language · Computer Science 2024-05-22 Charles O'Neill , Thang Bui

Scientific archives now contain hundreds of petabytes of data across genomics, ecology, climate, and molecular biology that could reveal undiscovered patterns if systematically analyzed at scale. Large-scale, weakly-supervised datasets in…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Jacob Beattie , Tanya Berger-Wolf , Yu Su

Sparse autoencoders (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural representations whose underlying structure is typically…

Machine Learning · Computer Science 2025-11-05 Valérie Costa , Thomas Fel , Ekdeep Singh Lubana , Bahareh Tolooshams , Demba Ba

In sparse coding, we attempt to extract features of input vectors, assuming that the data is inherently structured as a sparse superposition of basic building blocks. Similarly, neural networks perform a given task by learning features of…

Machine Learning · Computer Science 2022-02-16 Deborah Pereg , Israel Cohen , Anthony A. Vassiliou

Recently, convolutional auto-encoders (CAE) were introduced for image coding. They achieved performance improvements over the state-of-the-art JPEG2000 method. However, these performances were obtained using massive CAEs featuring a large…

Image and Video Processing · Electrical Eng. & Systems 2022-09-13 Cyprien Gille , Frédéric Guyard , Marc Antonini , Michel Barlaud

Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed with generic and weakly grounded features, while related…

Artificial Intelligence · Computer Science 2026-04-29 John Winnicki , Abeynaya Gnanasekaran , Eric Darve

Sparse code formation in the primary visual cortex (V1) has been inspiration for many state-of-the-art visual recognition systems. To stimulate this behavior, networks are trained networks under mathematical constraint of sparsity or…

Computer Vision and Pattern Recognition · Computer Science 2015-03-16 Nam Do-Hoang Le

Both neurophysiological and psychophysical experiments have pointed out the crucial role of recurrent and feedback connections to process context-dependent information in the early visual cortex. While numerous models have accounted for…

Computer Vision and Pattern Recognition · Computer Science 2019-10-18 Victor Boutin , Angelo Franciosini , Frederic Chavane , Franck Ruffier , Laurent Perrinet

Sparse autoencoders (SAEs) have emerged as a powerful tool for uncovering interpretable features in large language models (LLMs) through the sparse directions they learn. However, the sheer number of extracted directions makes comprehensive…

Computation and Language · Computer Science 2025-11-11 Xinyuan Yan , Shusen Liu , Kowshik Thopalli , Bei Wang

Sparse autoencoders (SAEs) have become a central tool for interpreting language models. However, two key SAE analyses that remain difficult to scale are (1) matching semantically similar features across multi-layers and (2) compressing…

Machine Learning · Computer Science 2026-05-28 Tue M. Cao , Nguyen Do , My T. Thai

In recent years, a large amount of multi-disciplinary research has been conducted on sparse models and their applications. In statistics and machine learning, the sparsity principle is used to perform model selection---that is,…

Computer Vision and Pattern Recognition · Computer Science 2014-12-09 Julien Mairal , Francis Bach , Jean Ponce

Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) provide a promising…

Computation and Language · Computer Science 2026-02-27 Usha Bhalla , Alex Oesterling , Claudio Mayrink Verdun , Himabindu Lakkaraju , Flavio P. Calmon

Combining simple elements from the literature, we define a linear model that is geared toward sparse data, in particular implicit feedback data for recommender systems. We show that its training objective has a closed-form solution, and…

Information Retrieval · Computer Science 2019-05-10 Harald Steck

Autoencoding has achieved great empirical success as a framework for learning generative models for natural images. Autoencoders often use generic deep networks as the encoder or decoder, which are difficult to interpret, and the learned…

Computer Vision and Pattern Recognition · Computer Science 2023-02-21 Xili Dai , Ke Chen , Shengbang Tong , Jingyuan Zhang , Xingjian Gao , Mingyang Li , Druv Pai , Yuexiang Zhai , XIaojun Yuan , Heung-Yeung Shum , Lionel M. Ni , Yi Ma

Sparse autoencoders (SAEs) extract human-interpretable features from deep neural networks by transforming their activations into a sparse, higher dimensional latent space, and then reconstructing the activations from these latents.…

Machine Learning · Computer Science 2025-02-13 Gonçalo Paulo , Stepan Shabalin , Nora Belrose