While I was reading an article on Google last Deep Learning achievement, I was reminded of a previous discussion with former colleagues about replacing reservoir simulations with neural networks. At the time, I dismissed the idea as ridiculous due to the complexity of the task and the requirement for the training.

But now, Google seems to have done it. Or have they?

Read More

This entry is part 2 of 2 in the series Deep adventures

A few weeks ago, on StackOverflow, a user asked for an accuracy measure on the embedded space for an autoencoder. This was with Keras, but I thought it would be a nice exercise for Tensorflow as well.

The idea in this case is to add a few layers to the embedded space to create a classifier and measure its accuracy while we optimize the autoencoder.

We will train the autoencoder in alternation with the classifier. When one is updated, the other will be frozen, and then we can measure classification accuracy and reconstruction loss concurrently in Tensorboard.

Read More

This entry is part 1 of 2 in the series Deep adventures

A few year ago, Packt Publishing contacted to be a technical reviewer for the first edition of Building Machine Learning Systems with Python, and I was impressed by the writing of Luis Pedro Coelho and Willi Richert. For the second edition, I was again a technical reviewer.

Writing is not easy, especially when it’s not your mother tongue, and scientific books are plagued with books that are not that great, with low technical content or bad English (that can be said for novels as well, the worst I ever read probably being the Hunger games series…). Even if I don’t like the books, I know that the authors did their best, having written in the past a book that I can say was not very great in terms of flow. Writing a book always deserves the deepest respect.

Read More