Latent Dirichlet Allocation
- D. Blei, A. Ng, Michael I. Jordan
- Computer ScienceJournal of machine learning research
- 3 January 2001
Reading Digits in Natural Images with Unsupervised Feature Learning
- Yuval Netzer, Tao Wang, Adam Coates, A. Bissacco, Bo Wu, A. Ng
- Computer Science
- 2011
A new benchmark dataset for research use is introduced containing over 600,000 labeled digits cropped from Street View images, and variants of two recently proposed unsupervised feature learning methods are employed, finding that they are convincingly superior on benchmarks.
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
- R. Socher, Alex Perelygin, Christopher Potts
- Computer ScienceConference on Empirical Methods in Natural…
- 1 October 2013
A Sentiment Treebank that includes fine grained sentiment labels for 215,154 phrases in the parse trees of 11,855 sentences and presents new challenges for sentiment compositionality, and introduces the Recursive Neural Tensor Network.
On Spectral Clustering: Analysis and an algorithm
- A. Ng, Michael I. Jordan, Yair Weiss
- Computer ScienceNIPS
- 3 January 2001
A simple spectral clustering algorithm that can be implemented using a few lines of Matlab is presented, and tools from matrix perturbation theory are used to analyze the algorithm, and give conditions under which it can be expected to do well.
An Analysis of Single-Layer Networks in Unsupervised Feature Learning
- Adam Coates, A. Ng, Honglak Lee
- Computer ScienceInternational Conference on Artificial…
- 1 December 2011
The results show that large numbers of hidden nodes and dense feature extraction are critical to achieving high performance—so critical, in fact, that when these parameters are pushed to their limits, they achieve state-of-the-art performance on both CIFAR-10 and NORB using only a single layer of features.
Learning Word Vectors for Sentiment Analysis
- Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, A. Ng, Christopher Potts
- Computer ScienceAnnual Meeting of the Association for…
- 19 June 2011
This work presents 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, and finds it out-performs several previously introduced methods for sentiment classification.
Apprenticeship learning via inverse reinforcement learning
This work thinks of the expert as trying to maximize a reward function that is expressible as a linear combination of known features, and gives an algorithm for learning the task demonstrated by the expert, based on using "inverse reinforcement learning" to try to recover the unknown reward function.
Pharmacokinetics of a novel formulation of ivermectin after administration to goats
- A. Ng, Stuart J. Russell
- Medicine, BiologyInternational Conference on Machine Learning
- 2000
The commercial formulation used in this study is a good option to consider when administering ivermectin to goats because of the high absorption, which is characterized by high values of F.
Large Scale Distributed Deep Networks
- J. Dean, G. Corrado, A. Ng
- Computer ScienceNIPS
- 3 December 2012
This paper considers the problem of training a deep network with billions of parameters using tens of thousands of CPU cores and develops two algorithms for large-scale distributed training, Downpour SGD and Sandblaster L-BFGS, which increase the scale and speed of deep network training.
Reasoning With Neural Tensor Networks for Knowledge Base Completion
- R. Socher, Danqi Chen, Christopher D. Manning, A. Ng
- Computer ScienceNIPS
- 5 December 2013
An expressive neural tensor network suitable for reasoning over relationships between two entities given a subset of the knowledge base is introduced and performance can be improved when entities are represented as an average of their constituting word vectors.
...
...