Creating data compatible with MNIST digit dataset from raw images
I'm new to ML and have a small project, where I have a million or so images containing handwritten texts in some uncommon languages. I'd like to experiment using the code that been written to process...
View ArticleAre there any design principals for creating descriptor vectors?
I am thinking about creating a new descriptor vector using some rather irregular biological data for classification via SVM. For example one property I want to measure may occur from zero to may times....
View ArticleNew data set for analysis and visualization: the BFF project on campaign...
submitted by DevFRus [link][1 comment]
View ArticleWhat to do with many super sparse features, in a classification problem?
I am facing a classification problem. There might be 50K observations and 1M factor (only in 0 or 1)features, while those features are all sparse, with little 1 and many 0 (the proportion of 1 is...
View ArticleAsk ML: Next step after Andrews Ng's course
I recently finished Andrew Ng's course on machine learning offered at cousera. Im blown away with the applications of ML and I want to learn more. What should my next step be in continuing to learn...
View ArticleWhat is the simplest to implement (from scratch) yet reasonably effective...
submitted by sanity [link][45 comments]
View ArticleIs this a reasonable approach to handling nominal attributes in a decision...
A while back I needed a decision tree learning implementation in Java and wasn't satisfied with any of the options out there, so I decided to roll my own, you can find the result here. My goals were to...
View ArticleMachine Learning: Under the hood. Blog post explains the principles of...
submitted by jamesjoyceroseroyce [link][9 comments]
View ArticleData Visualization tools (in Java preferably) for capturing Dynamic Clustering.
I was looking for a Data Visualization tool, preferably in Java, that can capture Dynamically growing clusters for streaming data. In addition, can i superimpose that visualization over some kind of...
View ArticleHow to factor in tf-idf with Naive Bayes?
From my understanding of naive bayes (multinomial edition), it has to deal with the count of the word for each class and the total count of all words in the class for the following part of the formula,...
View ArticleIs there a ml environment (like RapidMiner) that supports bi-normal separation?
Bi-normal seperation (http://jmlr.org/papers/volume3/forman03a/forman03a.pdf) seems to be a nice feature selection method and I would like to try it on my data set to see if it actually works. Does...
View Articleimage processing toolkit and training data suggestions
Hey all, I am interested in writing my own skeleton tracker for kinnect data, but I don't want to reinvent too many wheels. I want to do this because in my experience openni is only good when directly...
View ArticleResearcher Proposes Using Machine Learning to Improve Network Defense
submitted by alexcpsec [link][comment]
View ArticleUsing Less Data -- Loss Proportional Subsampling
submitted by rrenaud [link][1 comment]
View ArticleMatrix Calculus for Machine Learning
In the last two weeks I studied Matrix Calculus, i.e. the set of rules and methods for differentiating functions involving vectors and matrices. It wasn't easy to make sense of the various methods. Not...
View Articlefastcluster: Fast Hierarchical, Agglomerative Clustering Routines for R and...
submitted by turnersr [link][comment]
View ArticleVideos of all the talks of ICML 2013 are now available
submitted by urish [link][7 comments]
View ArticleQ: What is Evolutionary Computation Good For? A: A versatile form of...
submitted by kburjorj [link][3 comments]
View Article[Question] Best resources for feature selection when classifying text using...
Hey /r/machinelearning--I don't see too many [question] posts here, so I hope I'm not in the wrong sub. If so, please point me to a better option.Currently I am using SciKit Learn to classify text...
View Article