Question: How can i choose the most confident samples in self-training with...
I want to Implement self-training method on a common multi-label dataset (e.g yeast.arff) . how can i choose the most confident samples to add them to label set for next iteration? Best regards...
View ArticleKernel Method Performance Comparable to Deep Learning?
So there have been kernels engineered for specific tasks that rival deep nets (e.g., http://arxiv.org/abs/1406.3332) which makes sense, since they do what is known to work well.But then this paper just...
View ArticleNon-Decomposable Bayesian Network Scoring Functions
I have been studying the property of decomposability that most Bayesian network scoring functions have. That is, the score assigned to the structure can be expressed as a sum of local values that...
View ArticleWhat are the axes in t-SNE?
I read the t-SNE paper and understood most (well, some) of it.I see how it can represent the structure of the data at lower dimensions but if I include it in a presentation and someone asks what the...
View ArticleClik here to view.
Graphlab full day training free via live stream
submitted by shonburton [link][1 comment]
View ArticleUsing OCR to read a receipt
I am looking to try and make an android app to pull out data from a receipt as an exercise. After some basic research I think tesseract may be a good choice, but it looks like some pre-processing is...
View ArticleClik here to view.
Artificial Intelligence used to provide a 10X improvement in personalized...
So we have an interesting problem that I want to get some advice on:Background: We are a nonprofit built by a bunch of tech startup founders and enthusiasts that want to do something for our kids: We...
View ArticleClik here to view.
Why is reinforcement learning so rare here?
It seems like machine learning is synonymous with supervised learning and a bit of unsupervised learning. Also deep learning is everything nowadays.I assume the reason for this is because it is good...
View ArticleClik here to view.
What are the state of the art techniques for speech based language...
Journal articles, conference papers would help. submitted by usernaamee [link][6 comments]
View ArticleClik here to view.
Is there a ML technique applicable to this problem? (knapsack variation with...
I'm very, very new to machine learning, but I'm dealing with a problem that seems like it might be a candidate for a ML approach. It's basically a knapsack problem, with a twist. I've got a set of...
View ArticleClik here to view.
MOE, the Metric Optimization Engine. An open source, Bayesian Global...
submitted by Zephyr314 [link][2 comments]
View ArticleWhat are some state of the art ML techniques in emotion recognition from speech?
submitted by holo11 [link][3 comments]
View ArticleClik here to view.
Machine Learning and the Big Data Ecosystem with Adam Drake of zanox
submitted by datacruncher1 [link][comment]
View ArticleQuestion about the max-norm constraint used with the Dropout technique
Maxout uses the max-norm constraint (or dropout does). Do you know when to enforce the constraint, during update ? or during calculating the pre-activation? submitted by rishok [link][3 comments]
View ArticleList of most important ML research labs?
what are the most important and famous machine learning, robotics, data mining research labs? submitted by makakimekaki [link][3 comments]
View Article