BSC at the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

2017-11-11T13:41:17+00:00 July 26th, 2017|

The 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) is over.   CVPR'2017 is the premier annual computer vision event comprising the main conference and several co-located workshops, the best meeting point for students, academics and industry researchers in this area. This year Deep Learning and Artificial Intelligence were the focus of the conference, an this was the reason why BSC-CNS  has been present with contributions in two workshops: Disentangling Motion, Foreground and Background Features in Videos: Our model and source code are publicly available at this https URL  The paper that contains the detailed contribution can be downloaded from arxiv repository. SalGAN: Visual Saliency Prediction with Generative Adversarial Networks: Our model and source code are publicly available at this https URL .  The shorter extended abstract presented as spotlight in the CVPR 2017 Scene [...]

Barcelona will be present at CVPR’2017 with many contributions

2017-08-08T13:21:22+00:00 July 14th, 2017|

The IEEE Conference on Computer Vision and Pattern Recognition 2017, CVPR '2017 , is the premier annual computer vision event comprising the main conference and several co-located workshops, the best meeting point for students, academics and industry researchers in this area, where Deep Learning is gaining momentum.  This year the conference will be held between July 21-26, , in Honolulu (Hawaii, USA). Our research group at BSC-CNS  and UPC Barcelona Tech will be present at CVPR'2017 with contribution in two workshops. I'm happy to have this awesome opportunity, thanks to our collaboration with the research group at UPC Barcelona Tech  led by  Xavier Giró i Nieto.  We hope that with our effort and collaboration, we can help to turn Barcelona into an Deep Learning hub.  Throughout the next academic year, we will promote different initiatives in this direction. For [...]

New Deep Learning for Artificial Intelligence MSc course in Barcelona

2017-09-25T12:26:48+00:00 July 7th, 2017|

Deep Learning for Artificial Intelligence Master Course at Universitat Politècnica de Catalunya (Autumn 2017) Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks or Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles of deep learning from both an algorithmic and computational perspectives.  Complete learning systems in different Deep Learning frameworks and platforms will be introduced via hadns-on, projects and assignments. You will learn to solve new classes of problems [...]

Marenostrum 4 will come in production on July 1st

2017-08-17T16:34:28+00:00 June 29th, 2017|

    Today, Sergi Girona, Operations Director at BSC,  inform as that on July 1st  MareNostrum 4 will come in real production for the first research projects that uses the general purpose block of Marenostrum 4. Great new!  I want to thanks the Operations department for their maratonian work. MareNostrum IV peak power is 11.15 Petaflops, or what is the same, it is able to perform more than eleven thousand trillion operations per second, ten times more than the MareNostrum3, which was installed between 2012 and 2013. Although its power is ten times greater than that of its predecessor, it only increases energy consumption by a 30% and now is of 1.3 MWatt/year. It have two distinct parts: General Purpose part and Emerging Technologies part. General Purpose  MareNostrum IV is a supercomputer based [...]

Cursa BTT Repicacorriols d’Argentona

2017-11-11T16:22:16+00:00 June 24th, 2017|

Aquest  juny finalment hem tingut la cursa de BTT  Repicacorriols 2017 a Argentona, un gran èxit, sens dubte. Feia temps que en Piu ens perseguia amb l'idea de tornar a muntar una cursa de BTT com la que vàrem organitzar al 1990 una colla d'amics. Aleshores varen ser 20 km de recorregut amb sortida i arribada a la Plaça Nova (foto: Organitzadors de la cursa el 10 de juny de 1990). En Piu, el de vermell a la foto del 1990, ha sabut engrescar una munió de amics i amigues per a fer realitat la repicacorriols.cat 27 anys més tard. En Piu sap fer equip!. Però gens fàcil ha estat aconseguir que fos realitat la cursa, i per això aconsello llegir el post d'en Salva al blog BTT Argentona que ha sabut plasmar les intenses aventures viscudes durant el [...]

Primeros pasos en Keras

2017-11-11T16:05:36+00:00 June 20th, 2017|

Keras es una librería de Python que proporciona de manera limpia y sencilla la creación de una gama de modelos de Deep Learning encima de otras librerías TensorFlow, Theano o CNTK. Keras fue desarrollado y es mantenido por François Chollet, un ingeniero de Google, y su código ha sido liberado bajo la licencia permisiva del MIT. Características básicas de Keras (*) Desconozco si fue la intención de François Chollet, pero personalmente valoro la austeridad y simplicidad que presenta este modelo de programación, sin adornos y maximizando la legibilidad. Permite expresar redes neuronales de una manera muy modular, considerando un modelo como una secuencia o un solo grafo. Una buena aproximación, a mi entender, porque los componentes de un modelo de Deep Learning son elementos discretos que [...]

First contact with Keras

2017-10-11T09:24:42+00:00 June 18th, 2017|

. . 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 modify within [...]

Democratización del Deep Learning: su potencial al alcance de todos

2017-11-11T13:50:48+00:00 June 2nd, 2017|

 Democratización del Deep Learning: su potencial al alcance de todos UPDATE: Una versión modificada de este post ha sido publicado en  el portal TECNONEWS  el 04/07/2017 En 10 años, cuatro de las cinco empresas más grandes del mundo por capitalización de mercado han cambiado.  Exxon Mobil, General Electric, Citigroup y Shell Oil están fuera y Apple, Alphabet (la compañía matriz de Google), Amazon y Facebook han tomado su lugar. Solo Microsoft mantiene su posición.   Ya se han percatado que todas ellas son empresas  que dominan la nueva era digital en que nos encontramos inmersos. Estamos hablando de empresas que basan su poderío en inteligencia artificial en general, y en particular Deep Learning. Acuñada la palabra en 1950 por John McCarthy, la Inteligencia Artificial existe desde hace décadas. Sin [...]

TensorFlow counterattacks to Caffe2

2017-08-08T14:04:49+00:00 May 4th, 2017|

Few days ago appeared Caffe2 as a new player on the scene of Deep Learning frameworks with impressive performance scaling results on DGX-1. Tonight, Tensorflow shown the same numbers and the GitHub code to prove it yourself: My last post finished with this Q&A: "Will Caffe2 steal the supremacy that TensorFlow has right now? I do not have a crystal ball. My opinion is that It seems not easy, but it is the only one that could be a competitor for Google especially in the production arena in companies. We will see it soon, because Facebook has to hurry, the window of time to get it will be very small." Let me add: The window is about to close if Facebook does not work fast and hard!   UPDATE 9-May (thanks to Maurici Yagües): https://twitter.com/soumithchintala/status/861944937100722176  :-)       [...]

Caffe2: A new player on the scene of Deep Learning frameworks

2017-08-17T16:34:41+00:00 April 25th, 2017|

Few days ago Facebook announced Caffe2, a new open-source, cross-platform framework for deep learning. They say that Caffe2 is the successor to Caffe ( really?), the deep learning framework developed by Berkeley AI Research and community contributors. Caffe2’s GitHub page describes it as “an experimental refactoring of Caffe that allows a more flexible way to organize computation.” As my readers know, when appeared TensorFlow I decided to pay attention to it because it could change the scene of DL/AI frameworks. Now, we are in the same situation, Caffe2 could change the current scene that Francesc Sastre, one of my master students,  build for his master thesis:  "Frameworks popularity evolution in GitHub" No questions, right? Facebook launched Caffe2, an open-source deep learning framework made with expression, speed, and modularity in mind. It address the bottlenecks observed [...]