8 Aug 2018

Siamese Neural Networks

2019-10-25T11:20:16+02:00Categories: Deep Learning|Tags: , , |1 Comment

Siamese networks were first introduced by Bromley and LeCun [1] in early 1990s to solve signature verification as an image matching problem. A similar Siamese architecture was independently proposed for fingerprint identification by Baldi and Chauvin [2] in 1992.  Later in 2015, Gregory Koch et al. [3] proposed to use Siamese neural networks for one-shot image recognition. Siamese neural networks are designed as two twin networks that are connected by their final layer by means of a distance layer that is trained to predict whether two images belong to the same category or not. The networks that compose the siamese architecture are called twins because all the weights and biases are tied, which means that both networks are symmetric. Symmetry is important as the network should be invariant to switching the input images. Moreover, this characteristic makes the networks much faster to train since the number of [...]

25 Apr 2017

Deeply Inspiring

2019-07-19T10:51:58+02:00Categories: Uncategorized|Tags: , , |0 Comments

Deep learning technologies are getting noticed out of the academic circles. A new post at Tecnalia inspiring blog provides a detailed analysis of these novel techniques. On that post, we summarize some key elements of the deep learning technology and give some insight on relevant companies and applications. Taking into consideration current growing figures of deep learning, the technology will be a key piece on current and future business.

18 Jun 2016

Deep Learning development setup for ubuntu 16.04 Xen

2019-07-19T12:09:31+02:00Categories: Uncategorized|Tags: , , , , , , , , |0 Comments

Last month we updated our deep learning servers into ubuntu 16.04 LTS Xenial. In this post we provide a summary of the steps we followed to have Theano, Caffe and Tensorflow under ubuntu 16.04. As ubuntu 16.04 is not yet supported by main deep learning environment and even CUDA drivers, we provide a step by step guideline to be able to build a deep learning environment with ubuntu 16.04. This is also valid for installing into 14.04 version just skipping the compiling files adaption. We have also included some of the configuration/test files described in this summary at link 1. Install prerequisites: This install prerequisites required to build the different dependencies and frameworks. sudo apt-get update sudo apt-get upgrade sudo apt-get install build-essential sudo apt-get autoremove sudo apt-get install git git config --global $MYNAME git config --global $MYMAIL 2. Install nvidia graphics driver: Download drivers Nvidia driver Start [...]