Neural networks curse of dimensionality
1. BasicRepresentationDBNs MRFs, multiple neural networks
1.1 Five reasons to explore deep learning#1 Learning representation: byond handcrafted features#2 Need for distributed representationsbinary features are fragiledistributional similarity based word clustersmulti-clustering (multiple clusters per data)curse of dimensionalityneural network learns kernel#3 unsupervised feature and weight learning#4 learn multiple levels of representation#5 why now? : New methods for unsupervised pre-training (RMB, autoencoders, etc)
1.2 From Logistic regression to neural networksnatural language modelTraining with backpropagation
1.3 Word Representations1.4 Unsupervised word vector learning1.5 Backpropagation Training
2. Recursive Neural NetworkLearn Structure and RepresentationSentiment AnalysisAutoencoder
3 Applicationsneural language modelsspeech and nlp applicationsresourcestricks of the tradediscussion
You might also like:
Stock market analysts on trial2002-02-09 14:24:25 by on-trial
The amount of poor and self-interested advice that is being issued by brokerages and their analysts. To this day, the majority of stockbrokers are compensated on the number of trades their customers make, not on the returns they generate for them or on the quality of the advice they provide. We believe that the price targets and analyst ratings are made with several masters in mind, none of whom are the individual investor. In a similar fashion, sell-side stock analysts are generally compensated based upon the overall profitability of their firms, not the quality or accuracy of their analysis. In the end, analysts have minimal structural incentive to be accurate in their predictions; rather their built-in incentive is to be as favorable to their corporate clients as possible. It is a...
Gurus' Results Stay Consistently Bad — Forbes
Investment gurus make their money selling market predictions, not following them. Their overall performance has been historically and consistently dismal. Why people pay for market predictions is a one of Wall Street's biggest mysteries.
Neural Information Processing: 13th International Conference, ICONIP 2006, Hong Kong, China, October 3-6, 2006, Proceedings, Part III (Lecture Notes ... Computer Science and General Issues)