Related papers: Leveraging Convolutional Sparse Autoencoders for R…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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 $L_2$…
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…
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…
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…
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…
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 -…
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…