On the Expressive Power of Deep Architectures
From MaRDI portal
Publication:3093936
DOI10.1007/978-3-642-24412-4_3zbMath1348.68183OpenAlexW116068320MaRDI QIDQ3093936
Yoshua Bengio, Olivier Delalleau
Publication date: 19 October 2011
Published in: Lecture Notes in Computer Science (Search for Journal in Brave)
Full work available at URL: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.387.8383
Related Items
Universal approximation on the hypersphere, Deep extreme learning machine and its application in EEG classification, Why does deep and cheap learning work so well?, Deep Neural Network Surrogates for Nonsmooth Quantities of Interest in Shape Uncertainty Quantification, Two-layer contractive encodings for learning stable nonlinear features, Deep Compositional Spatial Models, A complete physics-informed neural network-based framework for structural topology optimization, Visualizing and understanding sum-product networks, Better Approximations of High Dimensional Smooth Functions by Deep Neural Networks with Rectified Power Units, Deep network based on stacked orthogonal convex incremental ELM autoencoders, Error bounds for approximations with deep ReLU networks, Fast generalization error bound of deep learning without scale invariance of activation functions, Sparse kernel deep stacking networks
