English
Related papers

Related papers: Binary Autoencoder for Mechanistic Interpretabilit…

200 papers

We propose the Autoencoding Binary Classifiers (ABC), a novel supervised anomaly detector based on the Autoencoder (AE). There are two main approaches in anomaly detection: supervised and unsupervised. The supervised approach accurately…

Machine Learning · Statistics 2019-03-27 Yuki Yamanaka , Tomoharu Iwata , Hiroshi Takahashi , Masanori Yamada , Sekitoshi Kanai

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting neural networks by extracting the concepts represented in their activations. However, choosing the size of the SAE dictionary (i.e. number of learned concepts)…

Machine Learning · Computer Science 2025-03-25 Bart Bussmann , Noa Nabeshima , Adam Karvonen , Neel Nanda

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

Predicting protein function from amino acid sequence remains a central challenge in data-scarce (low-$N$) regimes, limiting machine learning-guided protein design when only small amounts of assay-labeled sequence-function data are…

Machine Learning · Computer Science 2025-08-27 Darin Tsui , Kunal Talreja , Amirali Aghazadeh

Real-time data collection and analysis in large experimental facilities present a great challenge across multiple domains, including high energy physics, nuclear physics, and cosmology. To address this, machine learning (ML)-based methods…

Machine Learning · Computer Science 2021-11-11 Yi Huang , Yihui Ren , Shinjae Yoo , Jin Huang

Variational autoencoders (VAE) represent a popular, flexible form of deep generative model that can be stochastically fit to samples from a given random process using an information-theoretic variational bound on the true underlying…

Machine Learning · Computer Science 2019-10-08 Bin Dai , Yu Wang , John Aston , Gang Hua , David Wipf

Variational AutoEncoders (VAEs) provide a means to generate representational latent embeddings. Previous research has highlighted the benefits of achieving representations that are disentangled, particularly for downstream tasks. However,…

Computer Vision and Pattern Recognition · Computer Science 2019-11-18 Matthew J. Vowels , Necati Cihan Camgoz , Richard Bowden

Variational Auto-encoders (VAEs) have been very successful as methods for forming compressed latent representations of complex, often high-dimensional, data. In this paper, we derive an alternative variational lower bound from the one…

Machine Learning · Computer Science 2019-03-20 Shuyu Lin , Ronald Clark , Robert Birke , Niki Trigoni , Stephen Roberts

This letter introduces a new denoiser that modifies the structure of denoising autoencoder (DAE), namely noise learning based DAE (nlDAE). The proposed nlDAE learns the noise of the input data. Then, the denoising is performed by…

Machine Learning · Computer Science 2022-01-24 Woong-Hee Lee , Mustafa Ozger , Ursula Challita , Ki Won Sung

Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. It operates by randomly masking image patches and reconstructing these masked patches using the unmasked ones. A key limitation…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Han Guo , Ramtin Hosseini , Ruiyi Zhang , Sai Ashish Somayajula , Ranak Roy Chowdhury , Rajesh K. Gupta , Pengtao Xie

Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absorption, where specialized features capture instances of…

Machine Learning · Computer Science 2025-09-29 Anton Korznikov , Andrey Galichin , Alexey Dontsov , Oleg Rogov , Elena Tutubalina , Ivan Oseledets

Variational Autoencoders (VAEs) typically rely on a probabilistic decoder with a predefined likelihood, most commonly an isotropic Gaussian, to model the data conditional on latent variables. While convenient for optimization, this choice…

Machine Learning · Statistics 2025-04-29 Chen Xu , Qiang Wang , Lijun Sun

This paper introduces a hybrid attention and autoencoder (AE) model for unsupervised online anomaly detection in time series. The autoencoder captures local structural patterns in short embeddings, while the attention model learns long-term…

Machine Learning · Computer Science 2024-01-09 Seyed Amirhossein Najafi , Mohammad Hassan Asemani , Peyman Setoodeh

Sparse Autoencoders (SAEs) are an interpretability technique aimed at decomposing neural network activations into interpretable units. However, a major bottleneck for SAE development has been the lack of high-quality performance metrics,…

Machine Learning · Computer Science 2024-12-02 Adam Karvonen , Can Rager , Samuel Marks , Neel Nanda

Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses. Despite their success, retrieval-augmented LLMs still face the distractibility issue,…

Computation and Language · Computer Science 2025-02-18 Zexuan Qiu , Zijing Ou , Bin Wu , Jingjing Li , Aiwei Liu , Irwin King

Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing…

Computer Vision and Pattern Recognition · Computer Science 2017-11-17 Tanmoy Mukherjee , Makoto Yamada , Timothy M. Hospedales

Autoencoders are certainly among the most studied and used Deep Learning models: the idea behind them is to train a model in order to reconstruct the same input data. The peculiarity of these models is to compress the information through a…

Machine Learning · Computer Science 2023-09-06 Gabriele Martino , Davide Moroni , Massimo Martinelli

Estimation of Distribution Algorithms (EDAs) require flexible probability models that can be efficiently learned and sampled. Autoencoders (AE) are generative stochastic networks with these desired properties. We integrate a special type of…

Neural and Evolutionary Computing · Computer Science 2015-09-22 Malte Probst

Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack…

Artificial Intelligence · Computer Science 2026-05-19 Ouns El Harzli , Hugo Wallner , Yoonsoo Nam , Haixuan Xavier Tao

Current sparse autoencoder (SAE) approaches to neural network interpretability assume that activations can be decomposed through linear superposition into sparse, interpretable features. Despite high reconstruction fidelity, SAEs…

Neurons and Cognition · Quantitative Biology 2025-12-10 Omar Claflin
‹ Prev 1 8 9 10 Next ›