English
Related papers

Related papers: The Deleuzian Representation Hypothesis

200 papers

Definition Extraction (DE) is one of the well-known topics in Information Extraction that aims to identify terms and their corresponding definitions in unstructured texts. This task can be formalized either as a sentence classification task…

Computation and Language · Computer Science 2020-05-01 Amir Pouran Ben Veyseh , Franck Dernoncourt , Dejing Dou , Thien Huu Nguyen

Prior studies on text-to-text generation typically assume that the model could figure out what to attend to in the input and what to include in the output via seq2seq learning, with only the parallel training data and no additional…

Computation and Language · Computer Science 2021-09-06 Yuning Mao , Wenchang Ma , Deren Lei , Jiawei Han , Xiang Ren

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques such as \textit{sparse…

Computation and Language · Computer Science 2026-02-02 Aryaman Arora , Zhengxuan Wu , Jacob Steinhardt , Sarah Schwettmann

While sparse autoencoders (SAEs) successfully extract interpretable features from language models, applying them to audio generation faces unique challenges: audio's dense nature requires compression that obscures semantic meaning, and…

Machine Learning · Computer Science 2025-10-31 Nathan Paek , Yongyi Zang , Qihui Yang , Randal Leistikow

We present a novel deep neural network architecture for unsupervised subspace clustering. This architecture is built upon deep auto-encoders, which non-linearly map the input data into a latent space. Our key idea is to introduce a novel…

Computer Vision and Pattern Recognition · Computer Science 2017-09-11 Pan Ji , Tong Zhang , Hongdong Li , Mathieu Salzmann , Ian Reid

Recent work on sparse autoencoders (SAEs) has shown promise in extracting interpretable features from neural networks and addressing challenges with polysemantic neurons caused by superposition. In this paper, we apply SAEs to the early…

Machine Learning · Computer Science 2024-09-10 Liv Gorton

Classical supervised classification tasks search for a nonlinear mapping that maps each encoded feature directly to a probability mass over the labels. Such a learning framework typically lacks the intuition that encoded features from the…

Computer Vision and Pattern Recognition · Computer Science 2020-06-11 Cat P. Le , Yi Zhou , Jie Ding , Vahid Tarokh

Unsupervised relation extraction (URE) aims to extract relations between named entities from raw text without requiring manual annotations or pre-existing knowledge bases. In recent studies of URE, researchers put a notable emphasis on…

Computation and Language · Computer Science 2023-12-04 Qing Wang , Kang Zhou , Qiao Qiao , Yuepei Li , Qi Li

Recent self-supervised models have demonstrated equal or better performance than supervised methods, opening for AI systems to learn visual representations from practically unlimited data. However, these methods are typically…

Computer Vision and Pattern Recognition · Computer Science 2022-10-10 Robin Karlsson , Tomoki Hayashi , Keisuke Fujii , Alexander Carballo , Kento Ohtani , Kazuya Takeda

Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as…

Machine Learning · Computer Science 2026-03-04 Xuan Yang , Jiayu Liu , Yuhang Lai , Hao Xu , Zhenya Huang , Ning Miao

This paper evaluates whether training a decision tree based on concepts extracted from a concept-based explainer can increase interpretability for Convolutional Neural Networks (CNNs) models and boost the fidelity and performance of the…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Gayda Mutahar , Tim Miller

Sparse representations with learned dictionaries have been successful in several image analysis applications. In this paper, we propose and analyze the framework of ensemble sparse models, and demonstrate their utility in image restoration…

Computer Vision and Pattern Recognition · Computer Science 2013-02-28 Karthikeyan Natesan Ramamurthy , Jayaraman J. Thiagarajan , Prasanna Sattigeri , Andreas Spanias

We present a method for extracting \emph{monosemantic} neurons, defined as latent dimensions that align with coherent and interpretable concepts, from user and item embeddings in recommender systems. Our approach employs a Sparse…

Information Retrieval · Computer Science 2025-11-25 Dor Arviv , Yehonatan Elisha , Oren Barkan , Noam Koenigstein

Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions. Most of the current explanation methods provide explanations through feature…

Machine Learning · Statistics 2019-10-09 Amirata Ghorbani , James Wexler , James Zou , Been Kim

Convolutional neural networks have spatial representations which read patterns in the vision tasks. Squeeze and excitation links the channel wise representations by explicitly modeling on channel level. Multi layer perceptrons learn global…

Computer Vision and Pattern Recognition · Computer Science 2023-08-28 Mahendran N

Discriminative features extracted from the sparse coding model have been shown to perform well for classification. Recent deep learning architectures have further improved reconstruction in inverse problems by considering new dense priors…

Information Theory · Computer Science 2026-03-27 Abiy Tasissa , Emmanouil Theodosis , Bahareh Tolooshams , Demba Ba

Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks. However, the key component,…

Computer Vision and Pattern Recognition · Computer Science 2020-08-21 Weijie Chen , Shiliang Pu , Di Xie , Shicai Yang , Yilu Guo , Luojun Lin

Understanding the multilingual mechanisms of large language models (LLMs) provides insight into how they process different languages, yet this remains challenging. Existing studies often focus on individual neurons, but their polysemantic…

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for interpreting the features learned by large language models (LLMs). By reconstructing features with sparsely activated networks, SAEs aim to recover complex superposed…

Machine Learning · Computer Science 2026-03-05 Jingyi Cui , Qi Zhang , Yifei Wang , Yisen Wang

Sparse autoencoders (SAEs) interpret neural network representations by decomposing activations into sparse combinations of dictionary atoms. However, SAEs assume features combine additively through linear reconstruction, an assumption that…

Machine Learning · Computer Science 2026-05-26 Panagiotis Koromilas , Andreas D. Demou , James Oldfield , Yannis Panagakis , Mihalis Nicolaou