• Publications
  • Influence
Latent Dirichlet Allocation
TLDR
We propose a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams [6], and Hofmann's aspect model . Expand
  • 25,846
  • 5177
  • PDF
Reading Digits in Natural Images with Unsupervised Feature Learning
TLDR
We attack the problem of recognizing digits in a real application using unsupervised feature learning methods: reading house numbers from street level photos. Expand
  • 2,606
  • 948
  • PDF
On Spectral Clustering: Analysis and an algorithm
TLDR
We present a simple spectral clustering algorithm that can be implemented using a few lines of Matlab. Expand
  • 7,631
  • 661
  • PDF
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
TLDR
We introduce the Stanford Sentiment Treebank and a powerful Recursive Neural Tensor Network that can accurately predict the compositional semantic effects present in this new corpus. Expand
  • 4,117
  • 648
  • PDF
An Analysis of Single-Layer Networks in Unsupervised Feature Learning
TLDR
In this paper, we show that several simple factors, such as the number of hidden nodes in the model, may be more important to achieving high performance than the learning algorithm or the depth of the model. Expand
  • 2,023
  • 404
  • PDF
Large Scale Distributed Deep Networks
TLDR
We have developed a software framework called DistBelief that can utilize computing clusters with thousands of machines to train large models. Within this framework, we have developed two algorithms for large-scale distributed training: (i) Downpour SGD, an asynchronous stochastic gradient descent procedure supporting a large number of model replicas. Expand
  • 2,507
  • 265
  • PDF
Apprenticeship learning via inverse reinforcement learning
TLDR
We consider learning in a Markov decision process where we are not explicitly given a reward function, but where instead we can observe an expert demonstrating the task that we want to learn to perform. Expand
  • 2,021
  • 262
  • PDF
Distance Metric Learning with Application to Clustering with Side-Information
TLDR
In this paper, we present an algorithm that, given examples of similar (and, if desired, dissimilar) pairs of points in ℝn, learns a distance metric over ℜn that respects these relationships. Expand
  • 2,874
  • 259
  • PDF
Algorithms for Inverse Reinforcement Learning
TLDR
We evaluate the pharmacokinetics of a novel commercial formulation of ivermectin after administration to goats. Expand
  • 1,888
  • 255
  • PDF
Learning Word Vectors for Sentiment Analysis
TLDR
We present a model that uses a mix of unsupervised and supervised techniques to learn word vectors capturing semantic term--document information as well as rich sentiment content. Expand
  • 2,121
  • 247
  • PDF