Some Questions from a Beginner...
I've been looking into Machine Learning and Data Science for a while, and I feel that it would be a very interesting field to get into. Anyways, I have some questions that need to be answered before I...
View ArticleReal valued Boltzmann machines
I've been reading about RBMs lately and one thing I realize I'd that almost all the examples assume binary visible units. The one exception was the Gaussian-binary RBM which can cope with real valued...
View ArticleClik here to view.
Machine learning in practice: predicting what users will answer on Stack...
submitted by rrenaud [link][comment]
View ArticleHad some questions on understanding multiple-instance learning (MIL)
Multiple-instance learning (MIL) has me sort of scratching my head. I feel like I'm not understanding something.So I get the problem formulation:Labeling can be labor unfeasible or impossible so we go...
View ArticleHow difficult is it to learn NLP with a solid background in ML?
I'm just curious as to how hard it is for someone with a solid ML background, but no specific NLP experience to pick it up? Thanks! submitted by AwesomeRecruiter [link][3 comments]
View ArticleClik here to view.
Clik here to view.
Clik here to view.
Striate: Simple convolutional neural networks in Python
submitted by cypherx [link][2 comments]
View ArticleIt's been just over a year since it was launched, and Kaggle's data science...
submitted by shaggorama [link][22 comments]
View ArticleDBN libraries in R or Python?
I have a bunch of data I think deep belief networks would work well on. I know the theory well, but I'm not in the mood to code up my own solution. I'd prefer something in R or Python because that's...
View ArticleWhich ML approach to take? Predicting real-valued (-1, 1) metric based on...
I'm fairly new to machine learning, and was wondering if any one could offer advice. I have several hundred speakers, each having a vector of ~250 relative phrase frequencies (#of times given phrase is...
View ArticleHow would one go about coding up a porn filter with existing technologies?
I'm mostly talking about images, of course.It doesn't have to be perfect. False positives aren't a huge issue. submitted by kurtgodelisdead [link][13 comments]
View ArticleIs this a multi-armed bandit problem or do I need a more unique active...
I know some of the basics of the multi-armed bandit problem, but I am not sure that my problem fits that paradigm.I am simulating a crowdsourcing platform in which I have k workers and n samples.The...
View Articlewhen it comes to large scale svm or kdtree training and testing, how do you...
I'm trying to figure out how to back a large scale svm (more than 100,000 images/ classes) with a database either a nosql kv or a relational database like postgresql.The idea of keeping this data in...
View ArticleGenetic algorithm crossover operator for a fixed number of "on" chromosomes?
I want to create a crossover operator for a genetic algorithm, such that exactly N genes are active in each of the offspring (exactly N genes would be active in each parent as well). Say that I have...
View ArticleBuilding a PC Mainly for Use With Machine Learning and Massive Data Problems,...
So I've been working on ML and NLP type problems for awhile now and I'd like to invest in some better hardware. I've built computers in the past, but they have mainly been for general purpose use. I've...
View ArticleA question about unsupervised bag of words method applied to images
I have read some recent articles about unsupervised recognition of objects. So, I began to think about unsupervised learning and tried the following algorithm for an unsupervised bag of words applied...
View Articlesuggestion for a classification algorithm
I would like to identify a given test signal from a stream of input data. Something on this lines. Which machine learning algorithm should I look into for correctly identifying? also would be nice if...
View Article