The UdeM-McGill-MITACS machine learning seminar serieshttp://www.iro.umontreal.ca/article.php3?id_article=107&lang=enis continuing its fall schedule. Next week's seminar:
*Sequence Processing with Recurrent Neural Networks * by Alex Graves Technische Universität München, Germany
Location: Pavillon André-Aisenstadt (UdeM), room AA-3195 Time: Tuesday, October 26, *14:00*
Abstract: The need to label, predict, model or otherwise process sequential data arises in many domains. Some obvious examples are speech and handwriting recognition, inferring protein structure from amino acid sequences, and making predictions about the stock market or the weather. Although the tasks and data vary greatly, certain properties seem to be universally beneficial for sequence processing algorithms. In particular the ability to 'remember' the context surrounding each point in the data sequence, and the ability to generalise to distorted versions of sequential patterns appear to be crucial. Recurrent neural networks are a promising architecture in this regard. Furthermore, they can be generalised to treat spatial, as well as temporal, dependencies in a sequential way, expanding the range of applicability to data such as images, video, and medical scans. This talk presents a generic framework for processing spatio-temporal data using recurrent neural networks, and shows how the framework can be tailored to specific tasks.
Afficher les réponses par date
Reminder for tomorrow's talk!
---------- Forwarded message ---------- From: Dumitru Erhan erhandum@iro.umontreal.ca Date: Sat, Oct 23, 2010 at 13:44 Subject: UdeM-McGill-MITACS machine learning seminar Tue Oct. 26@14h00, AA-3195 To: lisa_seminaires@iro.umontreal.ca
The UdeM-McGill-MITACS machine learning seminar serieshttp://www.iro.umontreal.ca/article.php3?id_article=107&lang=enis continuing its fall schedule. Next week's seminar:
*Sequence Processing with Recurrent Neural Networks * by Alex Graves Technische Universität München, Germany
Location: Pavillon André-Aisenstadt (UdeM), room AA-3195 Time: Tuesday, October 26, *14:00*
Abstract: The need to label, predict, model or otherwise process sequential data arises in many domains. Some obvious examples are speech and handwriting recognition, inferring protein structure from amino acid sequences, and making predictions about the stock market or the weather. Although the tasks and data vary greatly, certain properties seem to be universally beneficial for sequence processing algorithms. In particular the ability to 'remember' the context surrounding each point in the data sequence, and the ability to generalise to distorted versions of sequential patterns appear to be crucial. Recurrent neural networks are a promising architecture in this regard. Furthermore, they can be generalised to treat spatial, as well as temporal, dependencies in a sequential way, expanding the range of applicability to data such as images, video, and medical scans. This talk presents a generic framework for processing spatio-temporal data using recurrent neural networks, and shows how the framework can be tailored to specific tasks.
lisa_seminaires@iro.umontreal.ca
-
Dumitru Erhan