English
Related papers

Related papers: Leveraging Convolutional Sparse Autoencoders for R…

200 papers

We present the first systematic study of Sparse Autoencoders (SAEs) on video representations. Standard SAEs decompose video into interpretable, monosemantic features but destroy temporal coherence: hard TopK selection produces unstable…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Atahan Dokme , Sriram Vishwanath

Sparse autoencoders (SAEs) are a recent technique for decomposing neural network activations into human-interpretable features. However, in order for SAEs to identify all features represented in frontier models, it will be necessary to…

Machine Learning · Computer Science 2025-06-04 Anish Mudide , Joshua Engels , Eric J. Michaud , Max Tegmark , Christian Schroeder de Witt

We propose GC-VASE, a graph convolutional-based variational autoencoder that leverages contrastive learning for subject representation learning from EEG data. Our method successfully learns robust subject-specific latent representations…

Signal Processing · Electrical Eng. & Systems 2025-01-29 Aditya Mishra , Ahnaf Mozib Samin , Ali Etemad , Javad Hashemi

For large language models (LLMs), sparse autoencoders (SAEs) have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of interpretable features, facilitating better control and…

Surface electromyography (sEMG) signals exhibit substantial inter-subject variability and are highly susceptible to noise, posing challenges for robust and interpretable decoding. To address these limitations, we propose a discrete…

Signal Processing · Electrical Eng. & Systems 2026-03-02 Yuepeng Chen , Kaili Zheng , Ji Wu , Zhuangzhuang Li , Ye Ma , Dongwei Liu , Chenyi Guo , Xiangling Fu

In this paper, we propose an easily trained yet powerful representation learning approach with performance highly competitive to deep neural networks in a digital pathology image segmentation task. The method, called sparse coding driven…

Computer Vision and Pattern Recognition · Computer Science 2020-08-14 Jie Song , Liang Xiao , Mohsen Molaei , Zhichao Lian

Sparse Autoencoders (SAEs) are a promising approach for extracting neural network representations by learning a sparse and overcomplete decomposition of the network's internal activations. However, SAEs are traditionally trained considering…

Machine Learning · Computer Science 2025-04-02 Jeffrey Olmo , Jared Wilson , Max Forsey , Bryce Hepner , Thomas Vin Howe , David Wingate

Objective: The objective of the study is to efficiently increase the expressivity of surface electromyography-based (sEMG) gesture recognition systems. Approach: We use a problem transformation approach, in which actions were subset into…

Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for…

Machine Learning · Computer Science 2026-04-17 Dongsheng Wang , Jinsen Zhang , Dawei Su , Hui Huang

Surface electromyography (sEMG) signals hold significant potential for gesture recognition and robust prosthetic hand development. However, sEMG signals are affected by various physiological and dynamic factors, including forearm…

Signal Processing · Electrical Eng. & Systems 2024-11-27 Umme Rumman , Arifa Ferdousi , Bipin Saha , Md. Sazzad Hossain , Md. Johirul Islam , Shamim Ahmad , Mamun Bin Ibne Reaz , Md. Rezaul Islam

This work is motivated by the recent advances in Deep Neural Networks (DNNs) and their widespread applications in human-machine interfaces. DNNs have been recently used for detecting the intended hand gesture through processing of surface…

Machine Learning · Computer Science 2020-11-13 Elahe Rahimian , Soheil Zabihi , Amir Asif , Dario Farina , Seyed Farokh Atashzar , Arash Mohammadi

Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large…

Machine Learning · Computer Science 2026-05-19 Michał Brzozowski , Neo Christopher Chung

Hand gesture classification using high-quality structured data such as videos, images, and hand skeletons is a well-explored problem in computer vision. Leveraging low-power, cost-effective biosignals, e.g. surface electromyography (sEMG),…

Sparse coding (Sc) has been studied very well as a powerful data representation method. It attempts to represent the feature vector of a data sample by reconstructing it as the sparse linear combination of some basic elements, and a $L_2$…

Machine Learning · Computer Science 2016-03-15 Mohua Zhang , Jianhua Peng , Xuejie Liu , Jim Jing-Yan Wang

High-density electromyography (HD-EMG) has emerged as a powerful modality for decoding fine-grained neuromuscular activity, enabling real-time neural-machine interfaces (NMIs) for applications such as prosthetic control, rehabilitation, and…

Machine Learning · Computer Science 2026-05-29 Peter Chudinov , Zhenyu Lin , Jay Motamarry , Srihita Panati , Xiaorong Zhang , Zhuwei Qin

Identifying the heterogeneous conductivity field and reconstructing the contaminant release history are key aspects of subsurface remediation. Achieving these two goals with limited and noisy hydraulic head and concentration measurements is…

Machine Learning · Computer Science 2022-09-29 Zitong Zhou , Nicholas Zabaras , Daniel M. Tartakovsky

To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Wei-Lun Chao , Tanya Berger-Wolf , Yu Su

In this work, we propose a novel convolutional autoencoder based architecture to generate subspace specific feature representations that are best suited for classification task. The class-specific data is assumed to lie in low dimensional…

Computer Vision and Pattern Recognition · Computer Science 2021-05-20 Krishan Sharma , Shikha Gupta , Renu Rameshan

Sparse Autoencoders (SAEs) have been proposed as an unsupervised approach to learn a decomposition of a model's latent space. This enables useful applications such as steering - influencing the output of a model towards a desired concept -…

Machine Learning · Computer Science 2025-12-23 Dana Arad , Aaron Mueller , Yonatan Belinkov

Sparse autoencoders (SAEs) are useful for detecting and steering interpretable features in neural networks, with particular potential for understanding complex multimodal representations. Given their ability to uncover interpretable…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Vladimir Zaigrajew , Hubert Baniecki , Przemyslaw Biecek