English
Related papers

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

200 papers

Underpinning the past decades of work on the design, initialization, and optimization of neural networks is a seemingly innocuous assumption: that the network is trained on a \textit{stationary} data distribution. In settings where this…

Machine Learning · Computer Science 2024-03-01 Clare Lyle , Zeyu Zheng , Khimya Khetarpal , Hado van Hasselt , Razvan Pascanu , James Martens , Will Dabney

In various learning-based image restoration tasks, such as image denoising and image super-resolution, the degradation representations were widely used to model the degradation process and handle complicated degradation patterns. However,…

Computer Vision and Pattern Recognition · Computer Science 2022-08-15 Dasong Li , Yi Zhang , Ka Chun Cheung , Xiaogang Wang , Hongwei Qin , Hongsheng Li

Deep neural networks are widely used in various domains. However, the nature of computations at each layer of the deep networks is far from being well understood. Increasing the interpretability of deep neural networks is thus important.…

Machine Learning · Computer Science 2018-12-19 Haiping Huang

There exist many problem domains where the interpretability of neural network models is essential for deployment. Here we introduce a recurrent architecture composed of input-switched affine transformations - in other words an RNN without…

Artificial Intelligence · Computer Science 2017-06-14 Jakob N. Foerster , Justin Gilmer , Jan Chorowski , Jascha Sohl-Dickstein , David Sussillo

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

Deep learning is regarded as a promising solution for reversible steganography. There is an accelerating trend of representing a reversible steo-system by monolithic neural networks, which bypass intermediate operations in traditional…

Multimedia · Computer Science 2023-03-08 Ching-Chun Chang , Xu Wang , Sisheng Chen , Isao Echizen , Victor Sanchez , Chang-Tsun Li

Mechanistic interpretability seeks to reverse engineer a trained neural network by identifying the minimal subset of internal components. We perform a mechanistic interpretability analysis of the Particle Transformer architecture, trained…

High Energy Physics - Phenomenology · Physics 2026-05-12 Saurabh Rai , Sanmay Ganguly

Pruning is a standard technique for removing unnecessary structure from a neural network to reduce its storage footprint, computational demands, or energy consumption. Pruning can reduce the parameter-counts of many state-of-the-art neural…

Machine Learning · Computer Science 2019-07-02 Jonathan Frankle , David Bau

Adoption of deep neural networks in fields such as economics or finance has been constrained by the lack of interpretability of model outcomes. This paper proposes a generative neural network architecture - the parameter encoder neural…

Machine Learning · Statistics 2021-06-11 Johann Pfitzinger

In this work, we investigate the fundamental trade-off regarding accuracy and parameter efficiency in the parameterization of neural network weights using predictor networks. We present a surprising finding that, when recovering the…

Machine Learning · Computer Science 2024-07-02 Hongjun Choi , Jayaraman J. Thiagarajan , Ruben Glatt , Shusen Liu

We propose and study a method for learning interpretable representations for the task of regression. Features are represented as networks of multi-type expression trees comprised of activation functions common in neural networks in addition…

Neural and Evolutionary Computing · Computer Science 2019-03-26 William La Cava , Tilak Raj Singh , James Taggart , Srinivas Suri , Jason H. Moore

Image decomposition aims to analyze an image into elementary components, which is essential for numerous downstream tasks and also by nature provides certain interpretability to the analysis. Deep learning can be powerful for such tasks,…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Sihan Wang , Shangqi Gao , Fuping Wu , Xiahai Zhuang

Susceptibilities are a technique for neural network interpretability that studies the response of posterior expectation values of observables to perturbations of the loss. We generalize this construction to the setting of the regret in deep…

Machine Learning · Computer Science 2026-05-11 Chris Elliott , Einar Urdshals , David Quarel , Daniel Murfet

Scaling model capacity has been vital in the success of deep learning. For a typical network, necessary compute resources and training time grow dramatically with model size. Conditional computation is a promising way to increase the number…

Machine Learning · Computer Science 2018-11-14 Louis Kirsch , Julius Kunze , David Barber

We introduce switched linear projections for expressing the activity of a neuron in a deep neural network in terms of a single linear projection in the input space. The method works by isolating the active subnetwork, a series of linear…

Machine Learning · Computer Science 2020-02-10 Lech Szymanski , Brendan McCane , Craig Atkinson

Linear Regression and neural networks are widely used to model data. Neural networks distinguish themselves from linear regression with their use of activation functions that enable modeling nonlinear functions. The standard argument for…

Machine Learning · Computer Science 2024-01-02 Anish Lakkapragada

Monolithic neural networks that make use of a single set of weights to learn useful representations for downstream tasks explicitly dismiss the compositional nature of data generation processes. This characteristic exists in data where…

Computer Vision and Pattern Recognition · Computer Science 2023-06-05 Hamed Damirchi , Forest Agostinelli , Pooyan Jamshidi

Machine learning methods are commonly used to solve inverse problems, wherein an unknown signal must be estimated from few indirect measurements generated via a known acquisition procedure. In particular, neural networks perform well…

Machine Learning · Computer Science 2025-12-05 Hannah Laus , Suzanna Parkinson , Vasileios Charisopoulos , Felix Krahmer , Rebecca Willett

Mechanistic interpretability (MI) aims to understand AI models by reverse-engineering the exact algorithms neural networks learn. Most works in MI so far have studied behaviors and capabilities that are trivial and token-aligned. However,…

Machine Learning · Computer Science 2024-07-15 Satvik Golechha , James Dao

Recurrent neural networks (RNNs) are notoriously difficult to train. When the eigenvalues of the hidden to hidden weight matrix deviate from absolute value 1, optimization becomes difficult due to the well studied issue of vanishing and…

Machine Learning · Computer Science 2016-10-13 Martin Arjovsky , Amar Shah , Yoshua Bengio