On invariance and selectivity in representation learning

DOI10.1093/imaiai/iaw009zbMath1426.68233arXiv1503.05938OpenAlexW1635792279MaRDI QIDQ4603721

Fabio Anselmi, Tomaso Poggio, Lorenzo Rosasco

Publication date: 19 February 2018

Published in: Information and Inference (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1503.05938

zbMATH Keywords

invariancemachine learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Physics-informed deep learning for simultaneous surrogate modeling and PDE-constrained optimization of an airfoil geometry, On the finite representation of linear group equivariant operators via permutant measures, A new paradigm for artificial intelligence based on group equivariant non-expansive operators, GSNs: generative stochastic networks, Neurally plausible mechanisms for learning selective and invariant representations, Unnamed Item, Some new methods to build group equivariant non-expansive operators in TDA, Unnamed Item, Universal approximations of invariant maps by neural networks

Uses Software

• OverFeat

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Support theorems for the Radon transform and Cramér-Wold theorems
• Neocognition: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
• Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
• Invariant kernel functions for pattern analysis and machine learning
• On the mathematical foundations of learning
• Hilbert space embeddings and metrics on probability measures
• Group Invariant Scattering
• Learning Deep Architectures for AI
• On the optimality of the bayes prediction policy in two-echelon multistation inventory models
• On the theory of reproducing kernel Hilbert spaces
• Efficient Sketches for Earth-Mover Distance, with Applications