Deep Learning

19 Dec 2019

OVER 70% OF COMPANIES HAVE INVESTED OR PLAN TO INVEST IN ADVANCED MANUFACTURING AND ARTIFICIAL INTELLIGENCE

2020-02-24T18:55:44+02:00Categories: Deep Learning|Tags: , , , |0 Comments

Deep Learning technology is changing the lives of millions of people all over the world. Deep Learning is technology that transfers artificial intelligence to a new generation thanks to its results and new applications: from natural language recognition to translation systems, including control systems in series (manufacturing processes), and artificial vision. Due to its great potential, many companies are planning large investments in advanced manufacturing and artificial intelligence. In the US over 70% of companies have invested in this technology or plan to do so. The implementation of Deep Learning will help to resolve problems by achieving results that were previously impossible to achieve. It is capable of changing the lives of millions of people all around the world, and its application covers several areas and sectors of activity – from industry 4.0 to personalised medicine, including precision agriculture, optimisation of energy consumption and recycling. At TECNALIA [...]

31 Oct 2019

CONSTELLATION LOSS

2019-12-10T19:05:24+02:00Categories: Deep Learning|Tags: , , , |0 Comments

Deep learning diagnostic algorithms are proving comparable results with human experts in a wide variety of tasks, they still require a huge amount of well annotated data for training which is often non-affordable. Metric learning techniques have allowed a reduction on the required annotated data allowing few-shot learning. Existing deep metric learning loss functions have made possible generating models capable of tackling complex scenarios with the presence of many classes and scarcity on the number of images per class, not only work for classification tasks, but to many other clinical applications where measuring similarity is the key. Currently used state-of-the-art loss functions still suffer from slow convergence due to the selection of effective training samples that has been partially solved by the multi-class N-pair loss by simultaneously adding additional samples from the different classes. The constellation loss goes one step further by simultaneously learning distances [...]