Supercomputing, the heart of Deep Learning

2018-07-02T23:19:51+00:00 July 2nd, 2018|

Introduction of the book  First contact with DEEP LEARNING, Practical introduction with Keras Supercomputing, the heart of Deep Learning   The first GPU in the Imagenet competition An exponential growth of computing capacity Accelerating Deep Learning with parallel systems Accelerating Deep Learning with distributed systems  Will specialized hardware for deep learning be a game changer?  Tapping the Next Generation of Supercomputers  Surely, at this point, some readers have already posed the question: why has a researcher in supercomputing such as me, started to investigate Deep Learning? In fact, many years ago I started to be interested in how supercomputing could contribute to improving Machine Learning methods; Then, in 2006, I started co-directing PhD theses with a great friend, and professor at the Computer Science department of [...]

New Free Deep Learning Book in Spanish

2018-06-13T13:13:15+00:00 June 13th, 2018|

As I already announced, during the free time that my academic and research activity allows me, I have started to write a new book about Deep Learning. The book is in Spanish and it was supposed to come out in September. Much to my regret, I realized that it would be impossible for me to finish the whole book by September, so I took the decision to divide the book into two parts and focus my efforts on finishing the first part. It gives me great pleasure to announce that I finished it and the first free book on Deep Learning in Spanish is available at http://JordiTorres.Barcelona/DeepLearning. I hope to have the second part ready before Christmas. My motivation to work on this huge project [...]

A new book about Deep Learning in Spanish

2018-04-17T16:46:24+00:00 April 17th, 2018|

Much to my regret, the book won`t be finished in time for Saint George`s Day (Dia de san Jordi), which we celebrate in Barcelona with the book and the rose. However, it gives me great pleasure to celebrate this Saint George`s Day by sharing with you what we have completed to date; the index and contents of the first chapter. From then on, I will share chapters as and when they are finished. By September, you should have the whole book on your shelves at home! I have partially stopped my blog and my outreach activity since a few weeks ago. The reason is, that during the free time that my academic and research activity allows me, I have started to write a new book about [...]

First Steps with KERAS

2017-10-24T17:40:12+00:00 September 23rd, 2017|

First steps with KERAS In reality, this post was intended for my DLAI course's students, although I think it may be of interest to other students. I am going to share in this blog the teaching material that I am going to generate for the part of DLAI course that will cover the basic principles of Deep Learning from a computational perspective. This post provides a fast-paced introduction to the KERAS API required to follow the DLAI Labs (Master Course at UPC - Autumn 2017). I will teach the part of DLAI course that will cover the basic principles of deep learning from computational perspectives. In this part we will review the basics of KERAS, a high-level neural networks API, written in Python and capable of running on top of [...]

First contact with Keras

2018-06-19T12:31:05+00:00 June 18th, 2017|

www.JordiTorres.Barcelona/DeepLearning . . Keras is a Python library that provides a clean and convenient way to create a range of deep learning models on top of  powerful libraries such as TensorFlow, Theano (update about Theano) or CNTK. Keras was developed and maintained by François Chollet, a Google engineer and it is released under the permissive MIT license. Basic features of Keras (*) I value his austerity and simplicity, without frills approach and maximizing readability. It makes it possible to express neural networks in a very modular way, considering a model as a sequence or a graph alone. A good approximation for beginners, because the components of a Keras model are discrete elements that can be combined in arbitrary ways. New components are intentionally easy to add and [...]