Google Colab is a great offering (at least at the moment is) because it is free and allows you seamless access to both GPU instances and...

#productivity #engineering Whenever you want to deal with cloud offerings (like #aws et. al.) you interact with the machines through an...

It is a well known fact that machine learning (and #deep-learning in particular) needs lots of compute power. If conditions are right...

When doing a hyperparameter optimisation using #gridsearch (or other tasks which involve an exhaustive evaluation of the search space)...

Displaying data requires creativity and practice at the same time otherwise you're bound to use only the techniques you already know. A...

When writing code you may want to quickly do performance analysis on your algorithms. The most likely tool that you need is obviously a...

Last year I discovered how easy it can be to trade with the Revolut app. I was playing for a couple of months, in the beginning, I did...

In the crypto world, this week Superfarm has launched his ICO(initial coin offering) on Polkastarter. As usual, after their ICO they...

This video is a sample of the materials covered in our Deep Learning (II) module. In it you can see an established technique for solving...

Training a neural network involves some form of optimisation (minimisation) of an objective function. The root strategy from which all...

Teacher forcing is a (really simple) way of #training an #rnn (a recurrent neural network) . RNNs have a variable length input and this...

It is sometimes useful to be able to convert a decision tree into an actual useful code snippet. This notebook shows how you’d go around...

On HackerNews there was a topic discussed at some point about ways to distill knowledge from a complex (almost black box) large tree...

Detecting faces in a still image is an important step that has various applications. As of now, a top of the SoTA on face detection seems...

The fastest way to convert an iterator to a list