English
Related papers

Related papers: Using Degeneracy in the Loss Landscape for Mechani…

200 papers

Universality is a key hypothesis in mechanistic interpretability -- that different models learn similar features and circuits when trained on similar tasks. In this work, we study the universality hypothesis by examining how small neural…

Machine Learning · Computer Science 2023-05-26 Bilal Chughtai , Lawrence Chan , Neel Nanda

There is strong interest in developing mathematical methods that can be used to understand complex neural networks used in image analysis. In this paper, we introduce techniques from Linear Algebra to model neural network layers as maps…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Rebecca Pattichis , Marios S. Pattichis

Because of the pervasive usage of Neural Networks in human sensitive applications, their interpretability is becoming an increasingly important topic in machine learning. In this work we introduce a simple way to interpret the output…

Machine Learning · Computer Science 2021-02-08 Stefano Zamuner , Paolo De Los Rios

Sparse neural networks are often hypothesized to be more interpretable than dense models, motivated by findings that weight sparsity can produce compact circuits in language models. However, it remains unclear whether structural sparsity…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Siyu Zhang

Multiple Kernel Learning is a conventional way to learn the kernel function in kernel-based methods. MKL algorithms enhance the performance of kernel methods. However, these methods have a lower complexity compared to deep learning models…

Machine Learning · Computer Science 2023-05-05 Ahmad Navid Ghanizadeh , Kamaledin Ghiasi-Shirazi , Reza Monsefi , Mohammadreza Qaraei

Learning representations that capture the underlying data generating process is a key problem for data efficient and robust use of neural networks. One key property for robustness which the learned representation should capture and which…

Machine Learning · Computer Science 2022-06-24 Mathieu Chevalley , Charlotte Bunne , Andreas Krause , Stefan Bauer

The Hessian of a neural network captures parameter interactions through second-order derivatives of the loss. It is a fundamental object of study, closely tied to various problems in deep learning, including model design, optimization, and…

Machine Learning · Computer Science 2021-07-02 Sidak Pal Singh , Gregor Bachmann , Thomas Hofmann

Neural networks often operate in the overparameterized regime, in which there are far more parameters than training samples, allowing the training data to be fit perfectly. That is, training the network effectively learns an interpolating…

Machine Learning · Computer Science 2025-03-19 Suzanna Parkinson , Greg Ongie , Rebecca Willett

A neural network with fixed topology can be regarded as a parametrization of functions, which decides on the correlations between functional variations when parameters are adapted. We propose an analysis, based on a differential geometry…

Adaptation and Self-Organizing Systems · Physics 2007-05-23 Marc Toussaint

This paper proposes a new paradigm for learning a set of independent logical rules in disjunctive normal form as an interpretable model for classification. We consider the problem of learning an interpretable decision rule set as training a…

Machine Learning · Computer Science 2021-03-15 Litao Qiao , Weijia Wang , Bill Lin

Traditional neural networks have an impressive classification performance, but what they learn cannot be inspected, verified or extracted. Neural Logic Networks on the other hand have an interpretable structure that enables them to learn a…

Machine Learning · Computer Science 2026-01-26 Vincent Perreault , Katsumi Inoue , Richard Labib , Alain Hertz

Predictive coding networks are neural models that perform inference through an iterative energy minimization process, whose operations are local in space and time. While effective in shallow architectures, they suffer significant…

Machine Learning · Computer Science 2025-10-13 Chang Qi , Matteo Forasassi , Thomas Lukasiewicz , Tommaso Salvatori

The Linear Representation Hypothesis (LRH) states that neural networks learn to encode concepts as directions in activation space, and a strong version of the LRH states that models learn only such encodings. In this paper, we present a…

Machine Learning · Computer Science 2024-08-21 Róbert Csordás , Christopher Potts , Christopher D. Manning , Atticus Geiger

Memorization of training data is an active research area, yet our understanding of the inner workings of neural networks is still in its infancy. Recently, Haim et al. (2022) proposed a scheme to reconstruct training samples from multilayer…

Machine Learning · Computer Science 2023-11-06 Gon Buzaglo , Niv Haim , Gilad Yehudai , Gal Vardi , Yakir Oz , Yaniv Nikankin , Michal Irani

Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that…

Image and Video Processing · Electrical Eng. & Systems 2021-06-14 Mohammad Zalbagi Darestani , Akshay S. Chaudhari , Reinhard Heckel

There remains an important need for the development of image reconstruction methods that can produce diagnostically useful images from undersampled measurements. In magnetic resonance imaging (MRI), for example, such methods can facilitate…

Image and Video Processing · Electrical Eng. & Systems 2021-06-28 Varun A. Kelkar , Sayantan Bhadra , Mark A. Anastasio

Interpretability has become an important issue in the machine learning field, along with the success of layered neural networks in various practical tasks. Since a trained layered neural network consists of a complex nonlinear relationship…

Machine Learning · Statistics 2018-05-22 Chihiro Watanabe , Kaoru Hiramatsu , Kunio Kashino

Introduced is a methodology for adapting the topology of dense neural networks, enabled by isotropic activation functions. Achieved through prescribed reparameterisation symmetries and singular-value decomposition of affine maps, this…

Neural and Evolutionary Computing · Computer Science 2026-05-08 George Bird

Identifiability is a desirable property of a statistical model: it implies that the true model parameters may be estimated to any desired precision, given sufficient computational resources and data. We study identifiability in the context…

Machine Learning · Statistics 2020-07-09 Geoffrey Roeder , Luke Metz , Diederik P. Kingma

Deep Neural Networks (DNNs) have become very popular for prediction in many areas. Their strength is in representation with a high number of parameters that are commonly learned via gradient descent or similar optimization methods. However,…

Machine Learning · Statistics 2016-10-11 Anthony Caterini , Dong Eui Chang