First contact with TensorBoard

2017-09-23T23:12:38+00:00 September 23rd, 2017|

First contact with TensorBoard TensorBoard is a suite of visualization tools that allows to visualize your TensorFlow/Keras graph, plot quantitative metrics about the execution of your graph, and show additional data like images that pass through it (*). TensorBoard operates by reading TensorFlow events files, which contain summary data that you can generate when running TensorFlow.  The general lifecycle for summary data within TensorBoard starts with the creation of the TensorFlow graph that you'd like to collect summary data from, and decide which nodes you would like to annotate with summary operations: tf.summary.tensor_summary tf.summary.scalar tf.summary.histogram tf.summary.audio tf.summary.image tf.summary.merge tf.summary.merge_all tf.summary.FileWriter tf.summary.FileWriterCache For example, by attaching tf.summary.scalar ops to the nodes that output the learning rate and loss respectively, we record how the learning rate varies over time, [...]

First Steps with KERAS

2017-09-23T20:19:06+00:00 September 23rd, 2017|

First steps with KERAS Actually this post is intended for my students of the DLAI course, although as 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. As you will see, the practical component is an important part of this part, where the "learn by doing" method is used, with a set of Hands-on that will starts with this post. 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 [...]

A stroll through Marenostrum IV computing resources

2017-09-23T17:35:24+00:00 September 18th, 2017|

Enclosed you will find the slides that I used in my last visit to the Torre Girona chapel with UPC students. The slides show the awesome computational power of the Marenostrum IV supercomputer and the presentation of the architecture required to get it.  I have posted these transparencies (and photo) for my students as I promised them. But anyone who wants to know a little more about the Marenostrum can take a look at them to realize the magnitude of this supercomputer.      SLIDESHARE slides

Getting started with DLAI course labs

2017-09-23T17:31:35+00:00 September 15th, 2017|

Getting Started With DLAI Course Labs Actually this post is intended for my students of the DLAI course, although as 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. As you will see, the practical component is an important part of this part, where the "learn by doing" method is used, with a set of Hands-on that will starts with this post. This post provides a fast-paced introduction to the basic technologies and knowledge 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 [...]

El nuevo iPhone X y su hardware especializado en Deep Learning e Inteligencia Artificial

2017-09-13T23:09:15+00:00 September 13th, 2017|

El nuevo iPhone X y su hardware especializado en Deep Learning e Inteligencia Artificial Ayer, 12 de septiembre,  tuvo lugar el evento de presentación de productos de Apple para anunciar el lanzamiento de sus nuevos modelos de Apple Watch, Apple TV, sistemas operativos, y , para finalizar, nuevas versiones de su producto estrella el iPhone , y en especial su espectacular iPhone X.  Hoy todos los medios destacaban el evento y daban diferentes respuestas a porqué el mercado está dispuesto a pagar más de mil euros por un iPhone. Quizás porque el nuevo iPhone X dispone de nuevas prestaciones, tales como el reconocimiento facial o realidad aumentada que le permiten considerarse "el futuro del smartphone" que ofrecen inteligencia artificial en el dispositivo. Para ello hace falta un hardware avanzado que me gustaría presentarles puesto [...]

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 [...]