Exponential Times

Exponential Times

The Future Comes Faster Than You Think
  • Videos
  • Books
  • News
  • Events
  • Sites
  • People
  • Store

Andrew Ng - Machine Learning via Large-scale Brain Simulations - Technion lecture

Submitted by Exponential Times on Mon, 2013-07-22 21:01
See video

Andrew Ng of Stanford University, Technion lecture: Machine Learning via Large-scale Brain Simulations Machine learning is a very successful technology, but applying it to a new problem usually means spending a long time hand-designing the input features to feed to the learning algorithm. This is true for applications in vision, audio, and text/NLP. To address this, researchers in machine learning have recently developed "deep learning" algorithms, which can automatically learn feature representations from unlabeled data, thus bypassing most of this time-consuming engineering. These algorithms are based on building massive artificial neural networks, that were loosely inspired by cortical (brain) computations. In this talk, I describe the key ideas behind deep learning, and also discuss the computational challenges of getting these algorithms to work. I'll also present a few case studies, and report on the results from a project that I led at Google to build massive deep learning algorithms, resulting in a highly distributed neural network trained on 16,000 CPU cores, and that learned by itself to discover high level concepts such as common objects in video.

  • Andrew Ng
  • 1898 reads
  • Most Seen
  • Recent
  • All
Views today
Scared of AI? You should be. | Sam Harris | TED Talks 6,756
R. Douglas Fields on Brain Mapping vs. Neuron Mapping 6,213
Kevin Kelly | 12 Inevitable Tech Forces That Will Shape Our Future |... 5,343
Ray Kurzweil At SENS 3 4,864
The last job on Earth: imagining a fully automated world | Guardian... 4,791


1 FREE Audiobook RISK-FREE from Audible