Mining urban events from the tweet stream through a probabilistic mixture model

2017-09-11T12:02:51+00:00 September 10th, 2017|

Mining urban events from the tweet stream through a probabilistic mixture model We are pleased to inform that we can publicly share a full-text view-only version of our last paper  "Mining urban events from the tweet stream through a probabilistic mixture model" published in Data Mining and Knowledge Discovery journal, as part of the Springer Nature SharedIt initiative. This paper is part of the work that our brilliant PhD student Joan Capdevila is doing. His PhD is co-advised with Jesús Cerquides from the IIIA -CSIC research centre. The geographical identification of content in Social Networks have enabled to bridge the gap between online social platforms and the physical world. Although vast amounts of data in such networks are due to breaking news or global occurrences, local events witnessed by users [...]

Inteligencia Artificial: Aplicaciones que lo adivinan todo

2017-09-01T12:39:58+00:00 August 24th, 2017|

Hace unos dias en La Vanguardia apareció un excelente artículo titulado “Aplicaciones que lo adivinan todo” para el que me llamo Albert Molins  para contrastar alguna ideas mientras lo estaba escribiendo.  Siempre es un placer hablar con Albert. Soy consciente que esta vez la notícia llega un poco tarde a este blog que audita mis actividades, pero me cogió haciendo un receso obligado para cargar pilas.   Les dejo adjunto transcripción del texto en castellano y a continuación en catalán del diario LA VANGUARDIA.   Aplicaciones que lo adivinan todo Identifican todo tipo de cosas, pero también obtienen información sobre los usuarios Los más veteranos seguro que recuerdan a Akinator, el genio de la web. Una página donde un genio nos pedía que pensáramos en un personaje, real o no, que él [...]

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

2017-08-17T16:31:10+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

2017-08-17T16:31:21+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 [...]

Primeros pasos en Keras

2017-08-17T16:32:00+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

2017-08-08T14:01:17+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 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 do not know if it was Chollet's intention, but 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 to my understanding, because the components of a deep learning model are discrete elements that can be combined in arbitrary ways. New [...]

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 [...]

The importance of Supercomputing in Artificial Intelligence

2017-08-08T20:22:51+00:00 December 13th, 2016|

Today I gave a talk about the importance of Supercomputing in the area of Artificial Intelligence as keynote at  #27 CO-SESSION ARTIFICIAL INTELLIGENCE IN BUSINES event organised by co-society. Attached  you will find the slides of today's talk. In the past, a lot of companies wished they had started thinking earlier about their Internet strategy. I think in a few years from now there will be a number of companies that wish they had started thinking earlier about their AI strategy. I hope that you are not one of these companies.   The importance of Supercomputing in Artificial Intelligence from Barcelona Tech UPC - Barcelona Supercomputer Center BSC