Skip navigation
Help

speech recognition

warning: Creating default object from empty value in /var/www/vhosts/sayforward.com/subdomains/recorder/httpdocs/modules/taxonomy/taxonomy.pages.inc on line 33.


Deep Learning of Representations

Google Tech Talk 11/13/2012 Presented by Yoshua Bengio ABSTRACT Yoshua Bengio will give an introduction to the area of Deep Learning, to which he has been one of the leading contributors. It is aimed at learning representations of data, at multiple levels of abstraction. Current machine learning algorithms are highly dependent on feature engineering (manual design of the representation fed as input to a learner), and it would be of high practical value to design algorithms that can do good feature learning. The ideal features are disentangling the unknown underlying factors that generated the data. It has been shown both through theoretical arguments and empirical studies that deep architectures can generalize better than too shallow ones. Since a 2006 breakthrough, a variety of learning algorithms have been proposed for deep learning and feature learning, mostly based on unsupervised learning of representations, often by stacking single-level learning algorithms. Several of these algorithms are based on probabilistic models but interesting challenges arise to handle the intractability of the likelihood itself, and alternatives to maximum likelihoods have been successfully explored, including criteria based on purely geometric intutions about manifolds and the concentration of probability mass that characterize many real-world learning tasks. Representation-learning algorithms are being applied to many tasks in computer vision, natural language processing, speech <b>...</b>
From:
GoogleTechTalks
Views:
2624

56
ratings
Time:
01:15:44
More in
Science & Technology

0
Your rating: None

Lucas123 writes "As anyone who's typed on a virtual keyboard — or yelled at a voice-control app like Siri — can attest, no current text input holds a candle to a traditional computer keyboard. From the reed switch keyboards of the early '70s to the buckling spring key mechanism that drove IBM's popular PC keyboards for years to ThinTouch technology that will have about half the travel of a MacBook Air's keys, the technology that drove data entry for decades isn't likely to go anywhere anytime soon. This article takes a look back on five decades of keyboard development and where it's likely to go in the future."


Share on Google+

Read more of this story at Slashdot.

0
Your rating: None

Today’s game consoles may offer subpar web experiences with little browser choice, but that doesn’t mean we can ignore them. More than one in eight internet users in the UK, US, and France—and nearly one in four American teens—uses a game console to get online. As more console makers offer internet-capable devices—and as smart TVs continue to enter the market—now is the time to plan how our sites will adapt to these new contexts. Learn how to test your web content on phone consoles; handheld consoles like Sony PSP and Nintendo DS; and TV consoles like Nintendo Wii, Sony PS3, and Microsoft Xbox 360.

0
Your rating: None

google x research project

Google has developed a virtual "neural network" that taught itself what a cat looks like by viewing images from YouTube. Developed at Google X, the research and development lab best known for Project Glass and self-driving cars, the neural network is a cluster of 1,000 computers with 16,000 cores between them. Google fed the cluster 200 x 200 pixel thumbnails taken from 10 million randomly selected YouTube videos and had it look for recurring features. Not only was its creation able to detect faces, but also "high-level concepts" such as cat faces and human bodies.

Google's machine was not taught, or given any data on what a face, body, or cat looks like before it started its analysis. Once it had discovered a recurring object, the...

Continue reading…

0
Your rating: None

Last week at Unite, the Unity team gave an overview of considerations developers need to take into account when targeting console platforms like XLBA, Wii, PS3, and when using input devices like the Kinect. In this article I'll break it down for you.

0
Your rating: None