Unsupervised Representation Learning. Yann LeCun

  • 3 Replies
  • 575 Views
*

keghn

  • Trusty Member
  • ********
  • Replicant
  • *
  • 670
Unsupervised Representation Learning. Yann LeCun
« on: April 02, 2017, 11:05:45 pm »
Unsupervised Representation Learning:

*

yotamarker

  • Trusty Member
  • ********
  • Replicant
  • *
  • 593
    • battle programming
Re: Unsupervised Representation Learning. Yann LeCun
« Reply #1 on: April 11, 2017, 07:49:18 pm »
can someone explain 46:30

*

keghn

  • Trusty Member
  • ********
  • Replicant
  • *
  • 670
Re: Unsupervised Representation Learning. Yann LeCun
« Reply #2 on: April 11, 2017, 09:13:44 pm »
 The low point is where a trainable algorithm give the correct answer of y2 at y1. But correct answer change when y1 changes.

*

keghn

  • Trusty Member
  • ********
  • Replicant
  • *
  • 670
Re: Unsupervised Representation Learning. Yann LeCun
« Reply #3 on: April 12, 2017, 04:07:05 pm »
A Neural Network in 13 lines of Python (Part 2 - Gradient Descent): 

http://iamtrask.github.io/2015/07/27/python-network-part2/