The surge of interest in reinforcement learning is great fun, but I often see confused choices in applying RL algorithms to solve problems. There are two purposes for which you might use a world simulator in reinforcement learning:

Steph is currently out of the office, teaching people cool Data Science stuff on a cruise at Tech Outbound. She counts on her team to keep the company’s Twitter account afloat in the meantime, so I had to think of a way to contribute. What about advertising existing content from her blog in the style of her Twitter role model Mara Averick, i.e. an informative tweet accompanied by appealing screenshots?

  ||

Thanks a lot to @aerinykim, @suzatweet and @hardmaru for the useful feedback!

Lately I’ve been getting pretty annoyed with an obsession with performance metrics. It’s like someone let the word out about what area under the ROC curve is and suddenly everyone thinks that’s the only measure of whether a data science project is ‘good’ or not.

We had recently published a large-scale machine learning benchmark using word2vec, comparing several popular hardware providers and ML frameworks in pragmatic aspects such as their cost, ease of use, stability, scalability and performance. Since that benchmark only looked at the CPUs, we also ran an analogous ML benchmark focused on GPUs.

I wanted to briefly highlight two recent papers on pruning neural networks (disclaimer, one of them is ours):

How are we making computers do the things we used to associated only with humans? Have we made a breakthrough in understanding human intelligence?

Humans physically interact with each other every day – from grabbing someone’s hand when they are about to spill their drink, to giving your friend a nudge to steer them in the right direction, physical interaction is an intuitive way to convey information about personal preferences and how to perform a task correctly.