doobwa
Re:DeepMind’s work in 2016: a round-up
on Wednesday January 04, 2017 @12:54AM (#13315981)
> We’re still a young company early in our mission...
What? Why don't they consider themselves part of Google?
Re:Deep Learning with Spark and TensorFlow
on Monday January 25, 2016 @03:02PM (#10969548)
Why not just use GNU Parallel (or something similar) instead of Spark?
Re:How to Evaluate Machine Learning Models: Hyperparameter Tuning
on Sunday May 31, 2015 @11:58PM (#9636740)
Spearmint, for example: https://github.com/JasperSnoek/spearmint/blob/master/spearmi...
Re:How to Evaluate Machine Learning Models: Hyperparameter Tuning
on Sunday May 31, 2015 @11:58PM (#9636736)
I think you mean https://www.whetlab.com/
Building a Python package for out-of-core LibFFM (a Kaggle-winning algorithm)
Content-based session recommender: Strata+Hadoop World
GraphLab Conference 2014: Live video stream
Re:How deep learning on GPUs wins datamining contest without feature e...
on Friday November 02, 2012 @02:42PM (#4734116)
I agree these methods still require a fair amount of expert knowledge and intuition in order to make the various choices you mention. On the other hand, Bayesian optimization can prove useful for exploring such a space. A recent paper (http://arxiv.org/pdf/1206.2944.pdf) used Bayesian optimization with GPs to find hyperparameter settings for a deep convolutional network. The resulting hyperparameters gave state of the art performance, beating those chosen by an expert (Krizhevsky, the researcher who recently won ImageNet).
Re:How deep learning on GPUs wins datamining contest without feature e...
on Friday November 02, 2012 @02:04PM (#4733931)
Given that pharma is a massive industry and that drug discovery often costs around 1 billion dollars, the top prize of $22,000 seems awfully low. Will we start to see larger prizes, or will startups take this technology and monetize better than academia currently does?
How deep learning on GPUs wins datamining contest without feature engineering
Kaggle transitioning competitors to become consultants
http://blog.kaggle.com/2012/10/23/join-the-chorus-data-consulting/
This seems like a logical next step for Kaggle. I wonder if Kaggle will successfully become the primary market-maker for this area, connecting data analysts and ML experts with corporations that need predictive analytics. Who are Kaggle's main competitors at this point?