Face representations via tensorfaces of various complexities

DOI10.1162/NECO_A_01258MaRDI QIDQ5131175zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Sidney R. Lehky, Anh-Huy Phan, Keiji Tanaka, Andrzej Cichocki

Publication date 2 November 2020

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/neco_a_01258

zbMATH Keywords

complexitiesface representationtensorfaces

Mathematics Subject Classification ID

Vector and tensor algebra, theory of invariants (15A72) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• Stimulus space complexity determines the ratio of specialist and generalist neurons during pattern recognition
• Replicating neuroscience observations on ML/MF and AM face patches by deep generative model
• scientific article; zbMATH DE number 5262972
• Memoryless Optimality: Neurons Do Not Need Adaptation to Optimally Encode Stimuli With Arbitrarily Complex Statistics
• Convolutional neural network models of V1 responses to complex patterns

Cites work

• A formal theory of inductive inference. Part I
• Alternating local search based VNS for linear classification
• An introduction to Kolmogorov complexity and its applications
• Analysis of individual differences in multidimensional scaling via an \(n\)-way generalization of ``Eckart-Young decomposition
• Between order and chaos: The quest for meaningful information
• Decompositions of a Higher-Order Tensor in Block Terms—Part I: Lemmas for Partitioned Matrices
• Decompositions of a Higher-Order Tensor in Block Terms—Part II: Definitions and Uniqueness
• Elements of Information Theory
• Hadamard, Khatri-Rao, Kronecker and other matrix products
• scientific article; zbMATH DE number 193560 (Why is no real title available?)
• scientific article; zbMATH DE number 2045481 (Why is no real title available?)
• Improved Uniqueness Conditions for Canonical Tensor Decompositions with Linearly Dependent Loadings
• Learning as Data Compression
• Learning the parts of objects by non-negative matrix factorization
• On the Complexity of Finite Sequences
• On the Length of Programs for Computing Finite Binary Sequences
• Optimization-based algorithms for tensor decompositions: canonical polyadic decomposition, decomposition in rank-(L_r,L_r,1) terms, and a new generalization
• Projected Gradient Methods for Nonnegative Matrix Factorization
• Tensor Decomposition for Signal Processing and Machine Learning
• Tensor Decompositions and Applications
• The ubiquitous Kronecker product
• Uni-mode and partial uniqueness conditions for CANDECOMP/PARAFAC of three-way arrays with linearly dependent loadings

This page was built for publication: Face representations via tensorfaces of various complexities

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5131175)