Question for those familiar with Simon Funk's incremental SVD method...
I'm trying to implement this for a ratings dataset that's similar to Netflix, and I've gotten it to "work", in that the training error is driven toward 0 after each iteration / more features are...
View ArticleTrying to solve the extra-credit for the coursera machine learning course...
code is here: https://pastee.org/u878p(full code is here)https://github.com/gdoteof/machine_learning_week1J(Theta) is oscillating between ~0 and 6.2e6The way they have you do the homework you can...
View ArticleClik here to view.
Don't forget that UW's Introduction to Data Science (Coursera) starts 5/1. An...
submitted by edomo [link][5 comments]
View ArticleIs supervised classification a "solved" problem?
Assume we have infinite training data, where each feature has unknown correlations with other features. Have we already perfectly solved the problem of assigning class based on this data?For example,...
View ArticleClik here to view.
What are your thoughts on "Deep Learning"?
I've read a bit about deep learning, and it seems quite compelling. Basically, we finally figured out how to train the kinds of feedback networks everyone was excited about in the 70s. And surprise,...
View ArticleHow serious is Andrew Ng's Coursera course?
I have been looking at Andrew Ng's course on coursera. How serious a course is this? It is only 6 weeks, is it a dumbed down version of the course? How does it compare to if I did the real machine...
View ArticleGoogle have this week been granted a very broad patent on using Machine...
My app uses machine learning to predict people you are likely to call, as a way of enhancing the phone dialer.Google's shiny new patent gives them the exclusive right to use machine learning on phones...
View ArticleClik here to view.
Pulitzer prize given as a result of lengthy data-mining analysis on speeding...
submitted by bwana_singsong [link][1 comment]
View ArticleNeed advice: Very small sample
I'm looking for advice. I'm trying to predict the question mark using the following tiny data set.Tag1 Tag2 Tag3 Tag4 Score 1 0 0 0 2000 1 0 0 1 2400 0 1 0 0 3000 0 1 0 1 3600 0 0 1 0 4000 0 0 1 1 ?...
View ArticleAlternatives to Bag of Words representation for text documents?
I've seen in literature and practice that most machine learning systems in the text domain use Bag-of-Words representation of data. Is this really the best option? I really think we can come up with...
View ArticleReducing the number of Support Vectors.
I am working in an extremely memory constrained environment, and the number of support vectors my Matlab design is generating is just not something that scales. That led me to move to finding a way to...
View ArticleI need a simple experimental task to test my general planning system.
I'm working on a general planning system. It observes a sliding window of world states and it's own past actions. I apply a stacked de-noising auto-encoder to the whole input to decompose it into a few...
View ArticleClik here to view.
Numenta will open source their core algorithms
submitted by numenta [link][19 comments]
View ArticlePredicting with Relevance Vector Machines.
I am trying out this Matlab toolbox for Relevance Vector Machines by Tipping: http://www.miketipping.com/sparsebayes.htmThis has an implementation of Relevance Vector Machines, and generates pretty...
View ArticleWhat could be done with this data?
Hi, I parsed the webpage of the Stock Exchange of our country and mined this data.I really want to build something out of it, some prediction model or any other thing. Problem is I have no clue where...
View ArticleWhere does one start?
What can I read? What library's and languages do people use? Any people I should follow concerning Machine Learning?Thanks- Complete Noob submitted by gregimba [link][3 comments]
View ArticleDoes anyone know the name of the type of graphed formed by a multi-layer...
For example: here.And, given a graph of this sort, is there an efficient way to calculate an arborescence for it? submitted by gct [link][7 comments]
View ArticleWant to spend next 2-3 months in getting ready (skill and knowledgewise) for...
Hello everyone. I am joining graduate school come Fall. I would be studying NLP and ML. I reduced my commitment from my current job to part time, so that I can focus on skill development prior to...
View Article