Illustrating power-law properties with Chinese Restaurant Process (PYP)
I often read that Pitman-Yor Process has power-law properties. Let's say I am interested in modelling English word's distribution (which follows power-law). Using CRP metaphor, words come and get...
View ArticleFeature Extraction from Kirzhevsky net in Theano/Pylearn?
Hi, People have been using libraries like caffe etc. where they can easily extract features from these large networks. Is there some similar wrapper to do this in a Theano/Pylearn framework. I agree we...
View ArticleThis would be a neat application of machine learning: An app that can...
submitted by MaunaLoona [link][comment]
View ArticleData Elixir, Issue 12: Data in the sciences, neural nets, data viz at TED
submitted by lonriesberg [link][3 comments]
View ArticleZero-bias autoencoders implemented by Roland Memisevic
submitted by galapag0 [link][comment]
View ArticleTheano for symbolic differentiation in general
As a Theano n00b, I'd like to take the liberty to ask if people are aware of projects where Theano has been used just for its symbolic differentiation capabilities, though not necessarily for deep...
View ArticleMicrosoft's Machine Learning technology covered in CIO mag, WIRED, KDnuggets...
submitted by MLBlogTeam [link][comment]
View ArticleIs RapidMiner any good?
Just looking for some opinions regarding its worth. submitted by DeLuhmer [link][1 comment]
View ArticleMachine Learning libraries for C++?
I am a newbie to machine learning and I would like to code up some of its algorithms on sample data sets that I have with me but preferably in C++ but I haven't been able to find a library that...
View ArticleCreating a future for autonomous robotics at the University of Birmingham
submitted by 5pin05auru5 [link][comment]
View ArticleImage pre processing for emotion classification
Hi! i want to do some emotion recognition from pictures, i am using the JAFFE database of Japanese models expressing different emotions in each picture. I want to work a genetic algorithm(GABIL) and...
View ArticleThey're looking for human volunteers to help them spot the higgs boson....
submitted by MaunaLoona [link][4 comments]
View ArticleZero-bias autoencoders and the benefits of co-adapting features
submitted by budhdub [link][1 comment]
View ArticleText classification - looking for approach suggestions
I'm trying classify short texts, using nltk and scikit-learn, but I am not sure yet how exactly approach it, and I am looking for advice. A particular text may belong to more then one class, or it may...
View ArticleMachine-Learning Algorithm Ranks the World's Most Notable Authors
submitted by futureisdata [link][comment]
View ArticleASK: Spatial data (Latitude and Longitude) as features
I want to use latitude and longitude as a feature for models like SVM or Logistic Regression (both for classification). Which is the most common approach to use latitude and longitude values as...
View Article[Question] K-fold cross validation with SVM
I am looking at this link and I am wondering if someone could explain to me what the point of testing with the same C and sigma values is every k iteration? Are you just making sure that the training...
View ArticleEE student (and electrician) interested in using human social and...
I'm a junior EE student and an apprentice electrician.I really want to be on a team with psychologists and biologists and other professionals with the purpose of analyzing human and animal behavior and...
View ArticleRandom feedback weights support learning in deep neural networks
submitted by zdwiel [link][1 comment]
View Article