English
Related papers

Related papers: Expressive architectures enhance interpretability …

200 papers

This work proposes an autoencoder neural network as a non-linear generalization of projection-based methods for solving Partial Differential Equations (PDEs). The proposed deep learning architecture presented is capable of generating the…

Computational Physics · Physics 2020-06-25 Jaime Lopez Garcia , Angel Rivero Jimenez

We show that in addition to providing effective and competitive closures, when analysed in terms of dynamics and physically-relevant diagnostics, artificial neural networks (ANNs) can be both interpretable and provide useful insights in the…

Computational Physics · Physics 2020-12-30 Gavin D. Portwood , Balasubramanya T. Nadiga , Juan A. Saenz , Daniel Livescu

We propose a new concept of rateless auto-encoders (RL-AEs) that enable a flexible latent dimensionality, which can be seamlessly adjusted for varying distortion and dimensionality requirements. In the proposed RL-AEs, instead of a…

Machine Learning · Computer Science 2020-05-07 Toshiaki Koike-Akino , Ye Wang

Sparse Autoencoders (SAEs) are a powerful dictionary learning technique for decomposing neural network activations, translating the hidden state into human ideas with high semantic value despite no external intervention or guidance.…

Machine Learning · Computer Science 2025-12-17 Albert Miao , Chenliang Zhou , Jiawei Zhou , Cengiz Oztireli

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

Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that are both sparse and semantically meaningful. However, many…

Machine Learning · Computer Science 2025-11-06 Xiaoqing Sun , Alessandro Stolfo , Joshua Engels , Ben Wu , Senthooran Rajamanoharan , Mrinmaya Sachan , Max Tegmark

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

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

In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavailability of annotated data. We choose to leverage…

Computation and Language · Computer Science 2023-05-05 Ghazi Felhi

Artificial Recurrent Neural Networks (RNNs) are widely used in neuroscience to model the collective activity of neurons during behavioral tasks. The high dimensionality of their parameter and activity spaces, however, often make it…

Dynamical Systems · Mathematics 2025-10-16 Alice Marraffa , Renate Krause , Valerio Mante , George Haller

The fidelity with which neural networks can now generate content such as music presents a scientific opportunity: these systems appear to have learned implicit theories of such content's structure through statistical learning alone. This…

Sound · Computer Science 2026-03-03 Nikhil Singh , Manuel Cherep , Pattie Maes

Sparse Autoencoders (SAEs) have emerged as a powerful framework for machine learning interpretability, enabling the unsupervised decomposition of model representations into a dictionary of abstract, human-interpretable concepts. However, we…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Thomas Fel , Ekdeep Singh Lubana , Jacob S. Prince , Matthew Kowal , Victor Boutin , Isabel Papadimitriou , Binxu Wang , Martin Wattenberg , Demba Ba , Talia Konkle

When the system is linear, why should learning be nonlinear? Linear dynamical systems, the analytical backbone of control theory, signal processing and circuit analysis, have exact closed-form solutions via the state transition matrix. Yet…

Machine Learning · Computer Science 2026-03-31 Shafayeth Jamil , Rehan Kapadia

Accurately modelling the dynamics of complex systems and discovering their governing differential equations are critical tasks for accelerating scientific discovery. Using noisy, synthetic data from two damped oscillatory systems, we…

Machine Learning · Computer Science 2026-01-29 Panayiotis Ioannou , Pietro Liò , Pietro Cicuta

This paper proposes a novel and interpretable recurrent neural-network structure using the echo-state network (ESN) paradigm for time-series prediction. While the traditional ESNs perform well for dynamical systems prediction, it needs a…

Machine Learning · Computer Science 2024-04-01 Debdipta Goswami

Recurrent neural networks (RNNs) are difficult to train on sequence processing tasks, not only because input noise may be amplified through feedback, but also because any inaccuracy in the weights has similar consequences as input noise. We…

Neural and Evolutionary Computing · Computer Science 2018-05-29 Michael C. Mozer , Denis Kazakov , Robert V. Lindsey

Learning identifiable representations in deep generative models remains a fundamental challenge, particularly for sequential data with regime-switching dynamics. Existing approaches establish identifiability under restrictive assumptions,…

Machine Learning · Statistics 2026-05-08 Carles Balsells-Rodas , Zhengrui Xiang , Xavier Sumba , Yingzhen Li

Discrete variational auto-encoders (VAEs) are able to represent semantic latent spaces in generative learning. In many real-life settings, the discrete latent space consists of high-dimensional structures, and propagating gradients through…

Machine Learning · Computer Science 2022-05-04 Alon Berliner , Guy Rotman , Yossi Adi , Roi Reichart , Tamir Hazan

Structured variational autoencoders (SVAEs) combine probabilistic graphical model priors on latent variables, deep neural networks to link latent variables to observed data, and structure-exploiting algorithms for approximate posterior…

Machine Learning · Statistics 2023-05-29 Yixiu Zhao , Scott W. Linderman

Sparse autoencoders (SAEs) are widely used to extract interpretable features from neural network representations, often under the implicit assumption that concepts correspond to independent linear directions. However, a growing body of…