Where do features come from? Geoffrey Hinton Department of Computer Science, University of Toronto 6 King’s College Rd, M5S 3G4, Canada February 18, 2013

Source URL: www.cs.toronto.edu

• Artificial neural networks
• Restricted Boltzmann machine
• Boltzmann machine
• Autoencoder
• Backpropagation
• Feedforward neural network
• Generative model
• Connectionism
• Supervised learning
• Graphical model
• Machine learning
• Hidden Markov model

Journal of Machine Learning Research1958 Submitted 11/13; Published 6/14 Dropout: A Simple Way to Prevent Neural Networks from Overfitting

Source URL: www.cs.toronto.edu

• Artificial neural networks
• Artificial intelligence
• Machine learning
• Learning
• Computational neuroscience
• Computer vision
• Convolutional neural network
• Computational statistics
• Deep learning
• Dropout
• Backpropagation
• Autoencoder

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation Kyunghyun Cho Bart van Merri¨enboer Caglar Gulcehre Universit´e de Montr´eal

Source URL: arxiv.org

• Artificial neural networks
• Artificial intelligence
• Machine learning
• Applied mathematics
• Deep learning
• Recurrent neural network
• Recursive neural network
• Feature learning
• Word embedding
• Statistical machine translation
• Language model
• Autoencoder

Real-time Hebbian Learning from Autoencoder Features for Control Tasks To appear in: Proc. of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems (ALIFE 14). Cambridge, MA: MIT Press

Source URL: eplex.cs.ucf.edu

• Artificial neural networks
• Neuroscience
• Applied mathematics
• Cybernetics
• Autoencoder
• Hebbian theory
• Feature learning
• Deep learning
• Restricted Boltzmann machine
• Unsupervised learning
• Biological neural network
• Backpropagation

arXiv:1506.02216v3 [cs.LG] 19 JunA Recurrent Latent Variable Model for Sequential Data Junyoung Chung, Kyle Kastner, Laurent Dinh, Kratarth Goel∗, Aaron Courville, Yoshua Bengio†

Source URL: arxiv.org

• Statistics
• Probability
• Artificial neural networks
• Machine learning
• Statistical models
• Markov models
• Artificial intelligence
• Computational statistics
• Recurrent neural network
• Deep learning
• Long short-term memory
• Autoencoder

CS294A Lecture notes Andrew Ng Sparse autoencoder 1

Source URL: web.stanford.edu

PDF Document

Source URL: www.neurotheory.columbia.edu

• Artificial neural networks
• Applied mathematics
• Cybernetics
• Learning
• Backpropagation
• Restricted Boltzmann machine
• Autoencoder
• Recurrent neural network
• Boltzmann machine
• Perceptron
• Supervised learning
• Deep learning

MADE: Masked Autoencoder for Distribution Estimation Mathieu Germain Universit´e de Sherbrooke, Canada Karol Gregor Google DeepMind

Source URL: jmlr.org

Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition Marc’Aurelio Ranzato, Fu Jie Huang, Y-Lan Boureau, Yann LeCun Courant Institute of Mathematical Sciences, New York Universi

Source URL: www.cs.toronto.edu

• Neural networks
• Learning
• Statistical classification
• Pattern recognition
• Supervised learning
• Autoencoder
• Unsupervised learning
• Caltech 101
• Support vector machine
• Machine learning
• Statistics
• Artificial intelligence

IMPROVEMENTS TO DEEP CONVOLUTIONAL NEURAL NETWORKS FOR LVCSR Tara N. Sainath1 , Brian Kingsbury1 , Abdel-rahman Mohamed2 , George E. Dahl2 , George Saon1 Hagen Soltau1 , Tomas Beran1 , Aleksandr Y. Aravkin1 , Bhuvana Ram

Source URL: www.cs.toronto.edu

• Network architecture
• Networks
• Speech recognition
• Autoencoder
• Science
• Cybernetics
• Computing
• Neural networks
• Computational neuroscience
• Econometrics