Hinton_G: 36 documents, from the least to the most probable paper
Perplexity score: Title:
8045.378543 Glove-TalkII: A neural network interface which maps gestures to parallel formant speech synthesizer controls
8038.663905 variables for regression and classification
5939.920552 Glove-Talk: A neural network interface between a data-glove and a speech synthesizer
5352.095610 Using Pairs of Data-Points to Define Splits for Decision Trees
5056.879348 Adaptive Elastic Models for Hand-Printed Character Recognition
4618.016048 Learning to Parse Images
4086.064471 Varieties of Helmholtz Machine
3885.475328 Using Mixtures of Factor Analyzers for Segmentation and Pose Estimation
3826.930981 Feudal Reinforcement Learning
2962.940095 Using Generative Models for Handwritten Digit Recognition
2724.751074 Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task
2486.949764 Spatial Coherence as an Internal Teacher for a Neural Network
2255.931061 Rate-coded Restricted Boltzmann Machines for Face Recognition
2237.946551 Learning Population Codes by Minimizing Description Length
2105.378710 Efficient Stochastic Source Coding and an Application to a Bayesian Network Source Model
2098.031433 Hierarchical Non-linear Factor Analysis and Topographic Maps
2055.818399 Making stochastic source coding efficient by recovering information
1991.607874 SMEM Algorithm for Mixture Models
1789.798603 Does the Wake-sleep Algorithm Produce Good Density Estimators?
1711.868839 Variational Learning for Switching State-Space Models
1609.472559 A New View of the EM Algorithm that Justifies Incremental and Other Variants
1448.569524 Switching State-Space Models
1397.422129 Variational Learning in Non-Linear Gaussian Belief Networks
1379.520545 Scaling in a Hierarchical Unsupervised Network
1367.892467 A Bayesian Unsupervised Learning Algorithm that Scales
1324.502747 A Simple Algorithm That Discovers Efficient Perceptual Codes
1301.633581 Products of Hidden Markov Models
1274.390306 Variational Learning in Nonlinear Gaussian Belief Networks
1256.905974 Autoencoders, Minimum Description Length and Helmholtz Free Energy
1187.757208 Minimizing Description Length in an Unsupervised Neural Network
1135.311045 Generative Models for Discovering Sparse Distributed Representations
1061.249225 The EM Algorithm for Mixtures of Factor Analyzers
993.799433 Training Products of Experts by Maximizing Contrastive Likelihood
970.592395 Training Products of Experts by Minimizing Contrastive Divergence
913.379282 Products of Experts
888.700578 Keeping Neural Networks Simple by Minimizing the Description Length of the Weights