English
Related papers

Related papers: On the Symmetries of Deep Learning Models and thei…

200 papers

Deep learning has proven itself as a successful set of models for learning useful semantic representations of data. These, however, are mostly implicitly learned as part of a classification task. In this paper we propose the triplet network…

Machine Learning · Computer Science 2018-12-05 Elad Hoffer , Nir Ailon

Recent success in training deep neural networks have prompted active investigation into the features learned on their intermediate layers. Such research is difficult because it requires making sense of non-linear computations performed by…

Machine Learning · Computer Science 2016-03-01 Yixuan Li , Jason Yosinski , Jeff Clune , Hod Lipson , John Hopcroft

Deep neural networks use multiple layers of functions to map an object represented by an input vector progressively to different representations, and with sufficient training, eventually to a single score for each class that is the output…

Machine Learning · Computer Science 2022-09-02 Tin Kam Ho

Embedding of large but redundant data, such as images or text, in a hierarchy of lower-dimensional spaces is one of the key features of representation learning approaches, which nowadays provide state-of-the-art solutions to problems once…

Computer Vision and Pattern Recognition · Computer Science 2022-06-13 Gianluca Berardi , Luca De Luigi , Samuele Salti , Luigi Di Stefano

Using symmetry as an inductive bias in deep learning has been proven to be a principled approach for sample-efficient model design. However, the relationship between symmetry and the imperative for equivariance in neural networks is not…

Machine Learning · Computer Science 2024-03-25 Sékou-Oumar Kaba , Siamak Ravanbakhsh

This manuscript presents a novel framework that integrates higher-order symmetries and category theory into machine learning. We introduce new mathematical constructs, including hyper-symmetry categories and functorial representations, to…

Machine Learning · Computer Science 2024-09-19 Ronald Katende

Symmetry is an important feature of many constraint programs. We show that any problem symmetry acting on a set of symmetry breaking constraints can be used to break symmetry. Different symmetries pick out different solutions in each…

Artificial Intelligence · Computer Science 2010-05-31 George Katsirelos , Toby Walsh

Learning informative representations of data is one of the primary goals of deep learning, but there is still little understanding as to what representations a neural network actually learns. To better understand this, subspace match was…

Machine Learning · Computer Science 2019-01-07 Jeremiah Johnson

Deep neural network architectures often consist of repetitive structural elements. We introduce an approach that reveals these patterns and can be broadly applied to the study of deep learning. Similarly to how a power strip helps untangle…

Statistical Mechanics · Physics 2025-07-03 Donghee Lee , Hye-Sung Lee , Jaeok Yi

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

Deep learning algorithms demonstrate a surprising ability to learn high-dimensional tasks from limited examples. This is commonly attributed to the depth of neural networks, enabling them to build a hierarchy of abstract, low-dimensional…

Machine Learning · Computer Science 2024-07-04 Francesco Cagnetta , Leonardo Petrini , Umberto M. Tomasini , Alessandro Favero , Matthieu Wyart

Motivation: Thanks to the recent advances in structural biology, nowadays three-dimensional structures of various proteins are solved on a routine basis. A large portion of these contain structural repetitions or internal symmetries. To…

Quantitative Methods · Quantitative Biology 2018-10-30 Guillaume Pagès , Sergei Grudinin

A major ambition of systems science is to uncover the building blocks of any biological network to decipher how cellular function emerges from their interactions. Here, we introduce a graph representation of the information flow in these…

Molecular Networks · Quantitative Biology 2020-06-15 Flaviano Morone , Ian Leifer , Hernan A. Makse

In many physical systems, inputs related by intrinsic system symmetries are mapped to the same output. When inverting such systems, i.e., solving the associated inverse problems, there is no unique solution. This causes fundamental…

Machine Learning · Computer Science 2020-03-23 Kshitij Tayal , Chieh-Hsin Lai , Vipin Kumar , Ju Sun

It has been hypothesized that some form of "modular" structure in artificial neural networks should be useful for learning, compositionality, and generalization. However, defining and quantifying modularity remains an open problem. We cast…

Machine Learning · Computer Science 2022-06-23 Richard D. Lange , David S. Rolnick , Konrad P. Kording

Network theory has proven to be a powerful tool in describing and analyzing systems by modelling the relations between their constituent objects. In recent years great progress has been made by augmenting `traditional' network theory.…

Data Analysis, Statistics and Probability · Physics 2016-06-03 Dominik Traxl , Niklas Boers , Jürgen Kurths

This work proposes an algorithm for explicitly constructing a pair of neural networks that linearize and reconstruct an embedded submanifold, from finite samples of this manifold. Our such-generated neural networks, called Flattening…

Machine Learning · Computer Science 2023-09-11 Michael Psenka , Druv Pai , Vishal Raman , Shankar Sastry , Yi Ma

Symmetric functions, which take as input an unordered, fixed-size set, are known to be universally representable by neural networks that enforce permutation invariance. These architectures only give guarantees for fixed input sizes, yet in…

Machine Learning · Computer Science 2022-10-11 Aaron Zweig , Joan Bruna

It is widely believed that learning good representations is one of the main reasons for the success of deep neural networks. Although highly intuitive, there is a lack of theory and systematic approach quantitatively characterizing what…

Machine Learning · Computer Science 2018-11-30 Liwei Wang , Lunjia Hu , Jiayuan Gu , Yue Wu , Zhiqiang Hu , Kun He , John Hopcroft

The study of complex networks has been historically based on simple graph data models representing relationships between individuals. However, often reality cannot be accurately captured by a flat graph model. This has led to the…

Social and Information Networks · Computer Science 2013-03-21 Matteo Magnani , Barbora Micenkova , Luca Rossi