English
Related papers

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

200 papers

Neural networks are powerful functions with widespread use, but the theoretical behaviour of these functions is not fully understood. Creating deep neural networks by stacking many layers has achieved exceptional performance in many…

Machine Learning · Computer Science 2024-08-16 Cameron Jakub , Mihai Nica

Mechanistic interpretability aims to explain what a neural network has learned at a nuts-and-bolts level. What are the fundamental primitives of neural network representations? Previous mechanistic descriptions have used individual neurons…

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning as the dual problem: given a desired form of generalization,…

Machine Learning · Computer Science 2026-01-21 George Wang , Daniel Murfet

The remarkable performance of convolutional neural networks (CNNs) is entangled with their huge number of uninterpretable parameters, which has become the bottleneck limiting the exploitation of their full potential. Towards network…

Computer Vision and Pattern Recognition · Computer Science 2020-08-26 Yuchao Li , Rongrong Ji , Shaohui Lin , Baochang Zhang , Chenqian Yan , Yongjian Wu , Feiyue Huang , Ling Shao

Mechanistic Interpretability (MI) promises a path toward fully understanding how neural networks make their predictions. Prior work demonstrates that even when trained to perform simple arithmetic, models can implement a variety of…

Machine Learning · Computer Science 2024-05-28 Ouail Kitouni , Niklas Nolte , Víctor Samuel Pérez-Díaz , Sokratis Trifinopoulos , Mike Williams

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Machine Learning · Computer Science 2025-03-17 Theodora-Mara Pîslar , Sara Magliacane , Atticus Geiger

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

The interpretability of neural networks (NNs) is a challenging but essential topic for transparency in the decision-making process using machine learning. One of the reasons for the lack of interpretability is random weight initialization,…

Machine Learning · Computer Science 2021-03-01 Shohei Kubota , Hideaki Hayashi , Tomohiro Hayase , Seiichi Uchida

Deep learning involves navigating a high-dimensional loss landscape over the neural network parameter space. Over the course of training, complex computational structures form and re-form inside the neural network, leading to shifts in…

Machine Learning · Computer Science 2025-08-04 Jesse Hoogland , George Wang , Matthew Farrugia-Roberts , Liam Carroll , Susan Wei , Daniel Murfet

It has been widely assumed that a neural network cannot be recovered from its outputs, as the network depends on its parameters in a highly nonlinear way. Here, we prove that in fact it is often possible to identify the architecture,…

Machine Learning · Computer Science 2020-02-25 David Rolnick , Konrad P. Kording

In this paper, we introduce a novel concept for learning of the parameters in a neural network. Our idea is grounded on modeling a learning problem that addresses a trade-off between (i) satisfying local objectives at each node and (ii)…

Machine Learning · Computer Science 2019-02-04 Dimche Kostadinov , Behrooz Razdehi , Slava Voloshynovskiy

As the discipline has evolved, research in machine learning has been focused more and more on creating more powerful neural networks, without regard for the interpretability of these networks. Such "black-box models" yield state-of-the-art…

Machine Learning · Computer Science 2021-09-02 Lachlan O'Neill , Simon Angus , Satya Borgohain , Nader Chmait , David L. Dowe

The practice of deep learning has shown that neural networks generalize remarkably well even with an extreme number of learned parameters. This appears to contradict traditional statistical wisdom, in which a trade-off between model…

Machine Learning · Computer Science 2023-02-21 Yifei Wang , Yixuan Hua , Emmanuel Candés , Mert Pilanci

Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features. However, many neurons exhibit $\textit{mixed selectivity}$, i.e., they represent multiple unrelated features. A…

Machine Learning · Statistics 2023-10-19 David Klindt , Sophia Sanborn , Francisco Acosta , Frédéric Poitevin , Nina Miolane

Interpretability is crucial for ensuring RL systems align with human values. However, it remains challenging to achieve in complex decision making domains. Existing methods frequently attempt interpretability at the level of fundamental…

Machine Learning · Computer Science 2025-06-03 Anna Soligo , Pietro Ferraro , David Boyle

We survey the model merging literature through the lens of loss landscape geometry to connect observations from empirical studies on model merging and loss landscape analysis to phenomena that govern neural network training and the…

An essential goal in mechanistic interpretability to decode a network, i.e., to convert a neural network's raw weights to an interpretable algorithm. Given the difficulty of the decoding problem, progress has been made to understand the…

Machine Learning · Computer Science 2023-12-07 Isaac Liao , Ziming Liu , Max Tegmark

Although image restoration has advanced significantly, most existing methods target only a single type of degradation. In real-world scenarios, images often contain multiple degradations simultaneously, such as rain, noise, and haze,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Hu Gao , Xiaoning Lei , Xichen Xu , Depeng Dang , Lizhuang Ma

Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures, recent evidence suggests that neural networks encode…

Machine Learning · Computer Science 2025-03-04 David Klindt , Charles O'Neill , Patrik Reizinger , Harald Maurer , Nina Miolane

Mechanistic interpretability aims to understand the internal mechanisms learned by neural networks. Despite recent progress toward this goal, it remains unclear how best to decompose neural network parameters into mechanistic components. We…

Machine Learning · Computer Science 2025-02-11 Dan Braun , Lucius Bushnaq , Stefan Heimersheim , Jake Mendel , Lee Sharkey
‹ Prev 1 2 3 10 Next ›