Hacker News Reader

doobwaon DeepMind’s work in 2016: a round-up

> We’re still a young company early in our mission...

What? Why don't they consider themselves part of Google?

doobwaon Deep Learning with Spark and TensorFlow

Why not just use GNU Parallel (or something similar) instead of Spark?

doobwaon How to Evaluate Machine Learning Models: Hyperparameter Tuning

Spearmint, for example: https://github.com/JasperSnoek/spearmint/blob/master/spearmi...

doobwaon How to Evaluate Machine Learning Models: Hyperparameter Tuning

I think you mean https://www.whetlab.com/

doobwaon How deep learning on GPUs wins datamining contest without feature engineering

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).

doobwaon How deep learning on GPUs wins datamining contest without feature engineering

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?