Deep Belief Networks

You are currently browsing the archive for the Deep Belief Networks category.

NIPS was pretty fantastic this year.  There were a number of breakthroughs in the areas that interest me most:  Markov Decision Processes, Game Theory, Multi-Armed Bandits, and Deep Belief Networks.  Here is the list of papers, workshops, and presentations I found the most interesting or potentially useful:

 

  1. Representation, Inference and Learning in Structured Statistical Models
  2. Stochastic Search and Optimization
  3. Quantum information and the Brain
  4. Relax and Randomize : From Value to Algorithms  (Great)
  5. Classification with Deep Invariant Scattering Networks
  6. Discriminative Learning of Sum-Product Networks
  7. On the Use of Non-Stationary Policies for Stationary Infinite-Horizon Markov Decision Processes
  8. A Unifying Perspective of Parametric Policy Search Methods for Markov Decision Processes
  9. Regularized Off-Policy TD-Learning
  10. Multi-Stage Multi-Task Feature Learning
  11. Graphical Models via Generalized Linear Models (Great)
  12. No voodoo here! Learning discrete graphical models via inverse covariance estimation (Great)
  13. Gradient Weights help Nonparametric Regressors
  14. Dropout: A simple and effective way to improve neural networks (Great)
  15. Efficient Monte Carlo Counterfactual Regret Minimization in Games with Many Player Actions
  16. A Better Way to Pre-Train Deep Boltzmann Machines
  17. Bayesian Optimization and Decision Making
  18. Practical Bayesian Optimization of Machine Learning Algorithms
  19. Modern Nonparametric Methods in Machine Learning
  20. Deep Learning and Unsupervised Feature Learning
Unfortunately, when you have 30 full day workshops in a two day period, you miss most of them.  I could only attend the three listed above.  There were many other great ones.

 

 

In “Semantic Hashing“, Salakhutdinov and Hinton (2007) show how to classify documents with binary vectors.  They combine deep learning and graphical models to assign each document a binary vector.  Similar documents can be found by using the L1 difference between the binary vectors.  Here is their abstract.

We show how to learn a deep graphical model of the word-count vectors obtained from a large set of documents. The values of the latent variables in the deepest layer are easy to infer and give a much better representation of each document than Latent Semantic Analysis. When the deepest layer is forced to use a small number of binary variables (e.g. 32), the graphical model performs “semantic hashing”: Documents are mapped to memory addresses in such away that semantically similar documents are located at nearby addresses. Documents similar to a query document can then be found by simply accessing all the addresses that differ by only a few bits from the address of the query document. This way of extending the efficiency of hash-coding to approximate matching is much faster than locality sensitive hashing, which is the fastest current method. By using semantic hashing to filter the documents given to TF-IDF, we achieve higher accuracy than applying TF-IDF to the entire document set.

Hinton has a new Google tech talk “Brains, Sex, and Machine Learning“.  I think that if you are into neural nets, you’ve got to watch this video.  Here’s the abstract.

   Recent advances in machine learning cast new light on two puzzling biological phenomena. Neurons can use the precise time of a spike to communicate a real value very accurately, but it appears that cortical neurons do not do this. Instead they send single, randomly timed spikes. This seems like a clumsy way to perform signal processing, but a recent advance in machine learning shows that sending stochastic spikes actually works better than sending precise real numbers for the kind of signal processing that the brain needs to do. A closely related advance in machine learning provides strong support for a recently proposed theory of the function of sexual reproduction. Sexual reproduction breaks up large sets of co-adapted genes and this seems like a bad way to improve fitness. However, it is a very good way to make organisms robust to changes in their environment because it forces important functions to be achieved redundantly by multiple small sets of genes and some of these sets may still work when the environment changes. For artificial neural networks, complex co-adaptations between learned feature detectors give good performance on training data but not on new test data. Complex co-adaptations can be reduced by randomly omitting each feature detector with a probability of a half for each training case. This random “dropout” makes the network perform worse on the training data but the number of errors on the test data is typically decreased by about 10%. Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever and Ruslan Salakhutdinov have shown that this leads to large improvements in speech recognition and object recognition.

 

Hinton has a lot of great ideas in this video including this slide on a massively parallel approach to neural nets.

And this one

And, as mentioned in the abstract, the idea of “dropouts” is very important. (Similar to denoising.)

I wonder if the idea of dropouts can be applied to create more robust Bayesian networks / Probabilistic Graphical Models.  Maybe the same effect can be achieved by introducing a bias (regularization) against connections between edges (similar to the idea of sparsity).

 

 

John Markoff at the NY times writes about recent advances in and implications of deep neural nets in “Scientists See Promise in Deep-Learning Programs“.  He reviews the recent activities of  Hinton, LeCun, and Ng as well as applications of deep learning in speech recognition, computer vision, chemistry (Kaggel Merck Prize), and near real-time natural language processing and machine translation.

Andrew Ng / Stanford has a great wiki tutorial on sparse deep neural nets.

“How Many Computers to Identify a Cat? 16,000” is a New York Times article about Deep Belief Networks, “the hottest thing in the speech recognition field these days.”

Newer entries »