English
Related papers

Related papers: Softly Induced Functional Simplicity: Implications…

200 papers

Understanding specifically where a model focuses on within an image is critical for human interpretability of the decision-making process. Deep learning-based solutions are prone to learning coincidental correlations in training datasets,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Aidan Boyd , Mohamed Trabelsi , Huseyin Uzunalioglu , Dan Kushnir

Neural networks (NNs) are inherently multidimensional classifiers that learn complex, non-linear relationships among input observables. While their flexibility enables unprecedented performance in high-energy physics (HEP) analyses, it also…

Identifying the structural priors that enable Deep Neural Networks (DNNs) to overcome the curse of dimensionality is a fundamental challenge in machine learning theory. Existing literature suggests that effective high-dimensional learning…

Machine Learning · Computer Science 2026-05-15 Hongyu Lin , Antonio Briola , Yuanrong Wang , Tomaso Aste

We show how complexity theory can be introduced in machine learning to help bring together apparently disparate areas of current research. We show that this new approach requires less training data and is more generalizable as it shows…

Machine Learning · Computer Science 2019-10-10 Santiago Hernández-Orozco , Hector Zenil , Jürgen Riedel , Adam Uccello , Narsis A. Kiani , Jesper Tegnér

Physics-inspired neural networks (NNs), such as Hamiltonian or Lagrangian NNs, dramatically outperform other learned dynamics models by leveraging strong inductive biases. These models, however, are challenging to apply to many real world…

Machine Learning · Computer Science 2022-02-15 Nate Gruver , Marc Finzi , Samuel Stanton , Andrew Gordon Wilson

Recent work has found that adversarially-robust deep networks used for image classification are more interpretable: their feature attributions tend to be sharper, and are more concentrated on the objects associated with the image's…

Machine Learning · Computer Science 2021-10-07 Zifan Wang , Matt Fredrikson , Anupam Datta

Robustness of deep neural networks to input noise remains a critical challenge, as naive noise injection often degrades accuracy on clean (uncorrupted) data. We propose a novel training framework that addresses this trade-off through two…

Machine Learning · Statistics 2026-01-06 Hai-Vy Nguyen , Fabrice Gamboa , Sixin Zhang , Reda Chhaibi , Serge Gratton , Thierry Giaccone

Bayesian neural networks provide a direct and natural way to extend standard deep neural networks to support probabilistic deep learning through the use of probabilistic layers that, traditionally, encode weight (and bias) uncertainty. In…

Machine Learning · Computer Science 2021-07-16 Daniel T. Chang

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

The layered structure of deep neural networks hinders the use of numerous analysis tools and thus the development of its interpretability. Inspired by the success of functional brain networks, we propose a novel framework for…

Machine Learning · Computer Science 2022-05-25 Ben Zhang , Zhetong Dong , Junsong Zhang , Hongwei Lin

Hyperbolic geometry has emerged as a powerful tool for modeling complex, structured data, particularly where hierarchical or tree-like relationships are present. By enabling embeddings with lower distortion, hyperbolic neural networks offer…

Machine Learning · Computer Science 2025-06-18 Pol Arévalo , Alexis Molina , Álvaro Ciudad

Obtaining heteroscedastic predictive uncertainties from a Bayesian Neural Network (BNN) is vital to many applications. Often, heteroscedastic aleatoric uncertainties are learned as outputs of the BNN in addition to the predictive means,…

Machine Learning · Computer Science 2026-05-01 David J. Schodt , Ryan Brown , Michael Merritt , Samuel Park , Delsin Menolascino , Mark A. Peot

In decision-making systems, it is important to have classifiers that have calibrated uncertainties, with an optimisation objective that can be used for automated model selection and training. Gaussian processes (GPs) provide uncertainty…

Machine Learning · Statistics 2020-03-05 Vincent Dutordoir , Mark van der Wilk , Artem Artemev , James Hensman

While deep neural networks have achieved remarkable performance, they tend to lack transparency in prediction. The pursuit of greater interpretability in neural networks often results in a degradation of their original performance. Some…

Computer Vision and Pattern Recognition · Computer Science 2024-08-09 Hefeng Wu , Hao Jiang , Keze Wang , Ziyi Tang , Xianghuan He , Liang Lin

While deep neural networks are highly effective at solving complex tasks, large pre-trained models are commonly employed even to solve consistently simpler downstream tasks, which do not necessarily require a large model's complexity.…

Machine Learning · Computer Science 2024-06-06 Victor Quétu , Zhu Liao , Enzo Tartaglione

Rapidly learning abstract concepts from limited examples is a hallmark of human intelligence. This work investigates whether gradient-based meta-learning can equip neural networks with inductive biases for efficient few-shot acquisition of…

Machine Learning · Computer Science 2025-11-06 Max Gupta

Although modern deep learning often relies on massive over-parameterized models, the fundamental interplay between capacity, sparsity, and robustness in low-capacity networks remains a vital area of study. We introduce a controlled…

Machine Learning · Computer Science 2025-07-23 Yash Kumar

Hamiltonian neural networks (HNNs) are state-of-the-art models that regress the vector field of a dynamical system under the learning bias of Hamilton's equations. A recent observation is that embedding a bias regarding the additive…

Machine Learning · Computer Science 2024-08-16 Zi-Yu Khoo , Dawen Wu , Jonathan Sze Choong Low , Stéphane Bressan

Low-dimensional embeddings are a cornerstone in the modelling and analysis of complex networks. However, most existing approaches for mining network embedding spaces rely on computationally intensive machine learning systems to facilitate…

Social and Information Networks · Computer Science 2024-10-04 Alexandros Xenos , Noel-Malod Dognin , Natasa Przulj

Deep learning is a powerful tool whose applications in quantitative finance are growing every day. Yet, artificial neural networks behave as black boxes and this hinders validation and accountability processes. Being able to interpret the…

Pricing of Securities · Quantitative Finance 2021-04-20 Damiano Brigo , Xiaoshan Huang , Andrea Pallavicini , Haitz Saez de Ocariz Borde