Conferencia sobre Deep Learning en Barcelona con la visión de Google DeepMind y Facebook

2017-11-12T15:46:09+00:00 November 12th, 2017|

    A menudo me llegan peticiones de antiguos alumnos o compañeros del sector para poder asistir a alguna de nuestras clases de Deep Learning en la UPC. Por esta razón, junto con Xavier Giró-i-Nieto, y en el marco del curso Deep Learning for Artificial Intelligence del master MET de la escuela de Telecos de la UPC  y de los seminarios Severo Ochoa Research Seminars  del Barcelona Supercomputing Center, hemos creído oportuno realizar una clase abierta  a todos los interesados en el tema, aprovechando que el próximo lunes 20 de Noviembre a las 11:30 tenemos dos participantes de excepción.   En esta clase abierta (en inglés) se presentaran algunos de los últimos avances en el tema desde el punto de vista de dos laboratorios de investigación punteros, como son Google Deepmind y Facebook [...]

Deep Neural net with Keras on a GPU Cloud

2017-11-08T20:36:28+00:00 October 3rd, 2017|

Run a DNN with Keras on Google Cloud 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. VGG-19 VGG-19 is a deep convolutional network for object recognition developed and trained by Oxford's renowned Visual Geometry Group (VGG), which achieved very good performance on the ImageNet dataset. You can check Karen Simonyan and Andrew Zisserman publication: Very Deep Convolutional Networks for Large-Scale Image Recognition. Cifar-10 The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images [...]

First steps with TensorFlow

2017-11-08T20:41:26+00:00 October 3rd, 2017|

First steps with TensorFlow 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. TensorFlow TensorFlow is an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API. Task 1:  Update DLAI [...]

Factors that have triggered the potential of Deep Learning

2017-11-11T13:37:43+00:00 September 27th, 2017|

Artificial Intelligence and Neural Networks, are not a new concepts! Why, all of a sudden, have them become the next big thing that is changing our life again during this decade? Deep Learning is changing our life I'm sure you have doubtlessly noticed quantum leaps in the quality of a wide range of everyday technologies.   In Speech Recognition  the transcription of voice to text has experimented amazing advances, and it is already available in different devices. We are increasingly interacting with “our” computers by just talking to them.  Also there have been some spectacular advances in Natural Language Processing, for example, by simply clicking on the micro symbol of Google Translate, the system will transcribe what you are dictating to another language. Google Translate now renders spoken sentences in [...]

Programming Models for Deep Learning

2017-09-27T10:08:29+00:00 September 24th, 2017|

Programming Models for Deep Learning 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. Recent years, as a result of the increase of the popularity of Deep Learning, many frameworks have surged in order to ease the task of create and train models. Frameworks use different programing languages, strategies to train the models or compute the data and different characteristics as distribution or GPU acceleration support. Most of these frameworks are open sourced and their popularity can be shown in the following Figure from Francesc [...]

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

2017-11-11T16:04:00+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

2017-11-11T13:49:10+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)

2017-11-11T13:41:17+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 [...]

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 [...]