English
Related papers

Related papers: Expressive architectures enhance interpretability …

200 papers

Recurrent Neural Networks (RNN) are ubiquitous computing systems for sequences and multivariate time series data. While several robust architectures of RNN are known, it is unclear how to relate RNN initialization, architecture, and other…

Machine Learning · Computer Science 2023-12-29 Ryan Vogt , Yang Zheng , Eli Shlizerman

Sparse Autoencoders (SAEs) have emerged as a popular tool for interpreting the hidden states of large language models (LLMs). By learning to reconstruct activations from a sparse bottleneck layer, SAEs discover interpretable features from…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Matthew Lyle Olson , Musashi Hinck , Neale Ratzlaff , Changbai Li , Phillip Howard , Vasudev Lal , Shao-Yen Tseng

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their…

Information Retrieval · Computer Science 2026-02-18 Anton Klenitskiy , Konstantin Polev , Daria Denisova , Alexey Vasilev , Dmitry Simakov , Gleb Gusev

Neural population activity is theorized to reflect an underlying dynamical structure. This structure can be accurately captured using state space models with explicit dynamics, such as those based on recurrent neural networks (RNNs).…

Neurons and Cognition · Quantitative Biology 2023-07-21 Joel Ye , Chethan Pandarinath

Dense embeddings deliver strong retrieval performance but often lack interpretability and controllability. This paper introduces a novel approach using sparse autoencoders (SAE) to interpret and control dense embeddings via the learned…

Information Retrieval · Computer Science 2025-02-25 Hao Kang , Tevin Wang , Chenyan Xiong

Due to their high computational efficiency on a continuous space, gradient optimization methods have shown great potential in the neural architecture search (NAS) domain. The mapping of network representation from the discrete space to a…

Machine Learning · Computer Science 2020-06-20 Jian Li , Yong Liu , Jiankun Liu , Weiping Wang

Stochastic recurrent neural networks with latent random variables of complex dependency structures have shown to be more successful in modeling sequential data than deterministic deep models. However, the majority of existing methods have…

Machine Learning · Computer Science 2020-04-24 Ehsan Hajiramezanali , Arman Hasanzadeh , Nick Duffield , Krishna Narayanan , Mingyuan Zhou , Xiaoning Qian

System identification in scenarios where the observed number of variables is less than the degrees of freedom in the dynamics is an important challenge. In this work we tackle this problem by using a recognition network to increase the…

Computational Physics · Physics 2020-10-14 Constantino A. Garcia , Paulo Felix , Jesus M. Presedo , Abraham Otero

We present a VAE architecture for encoding and generating high dimensional sequential data, such as video or audio. Our deep generative model learns a latent representation of the data which is split into a static and dynamic part, allowing…

Machine Learning · Computer Science 2018-06-13 Yingzhen Li , Stephan Mandt

Sparse autoencoders (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural representations whose underlying structure is typically…

Machine Learning · Computer Science 2025-11-05 Valérie Costa , Thomas Fel , Ekdeep Singh Lubana , Bahareh Tolooshams , Demba Ba

Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors or biases in training data. Current methods often rely on costly LLM-based techniques (e.g.…

Artificial Intelligence · Computer Science 2025-12-12 Nick Jiang , Xiaoqing Sun , Lisa Dunlap , Lewis Smith , Neel Nanda

Interpretable mathematical expressions defining discrete-time dynamical systems (iterated maps) can model many phenomena of scientific interest, enabling a deeper understanding of system behaviors. Since formulating governing expressions…

Machine Learning · Computer Science 2024-06-12 Adarsh Iyer , Nibodh Boddupalli , Jeff Moehlis

Deep learning became the method of choice in recent year for solving a wide variety of predictive analytics tasks. For sequence prediction, recurrent neural networks (RNN) are often the go-to architecture for exploiting sequential…

Machine Learning · Computer Science 2016-11-09 Kin Gwn Lore , Daniel Stoecklein , Michael Davies , Baskar Ganapathysubramanian , Soumik Sarkar

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

We investigate neural ordinary and stochastic differential equations (neural ODEs and SDEs) to model stochastic dynamics in fully and partially observed environments within a model-based reinforcement learning (RL) framework. Through a…

Machine Learning · Computer Science 2026-03-25 Chao Han , Stefanos Ioannou , Luca Manneschi , T. J. Hayward , Michael Mangan , Aditya Gilra , Eleni Vasilaki

Recurrent neural networks (RNNs) are a widely used tool for modeling sequential data, yet they are often treated as inscrutable black boxes. Given a trained recurrent network, we would like to reverse engineer it--to obtain a quantitative,…

Machine Learning · Computer Science 2019-12-06 Niru Maheswaranathan , Alex Williams , Matthew D. Golub , Surya Ganguli , David Sussillo

Recurrent neural networks (RNNs) provide a powerful approach in neuroscience to infer latent dynamics in neural populations and to generate hypotheses about the neural computations underlying behavior. However, past work has focused on…

Machine Learning · Computer Science 2025-10-30 Elia Torre , Michele Viscione , Lucas Pompe , Benjamin F Grewe , Valerio Mante

Integrating physics models within machine learning models holds considerable promise toward learning robust models with improved interpretability and abilities to extrapolate. In this work, we focus on the integration of incomplete physics…

Machine Learning · Computer Science 2021-10-28 Naoya Takeishi , Alexandros Kalousis

Classical methods of solving spatiotemporal dynamical systems include statistical approaches such as autoregressive integrated moving average, which assume linear and stationary relationships between systems' previous outputs. Development…

Dynamical Systems · Mathematics 2022-02-16 Yonggi Park , Kelum Gajamannage , Dilhani I. Jayathilake , Erik M. Bollt

Sparse Autoencoders (SAEs) have emerged as a promising approach for interpreting neural network representations by learning sparse, human-interpretable features from dense activations. We investigate whether incorporating variational…

Machine Learning · Computer Science 2025-10-03 Zachary Baker , Yuxiao Li