Wednesday, October 16, 2019
News

Facebook research wants to build more capable AI using self- learning methods

   SocialTwist Tell-a-Friend    Print this Page   COMMENT

| May 20, 2019 10:42:00 PM IST
Facebook is expanding its areas of research in robotics to build better AI with the help of self-supervised learning.

As Engadget reports, the social networking giant shared details about three additional areas of research, including model-based reinforcement learning (RL) to enable robots that can teach themselves through trial and error using direct input from sensors, teaching the ability to explore using human-like curiosity, and how to feel physically using predictive deep-learning model.

The researchers were able to get a six-legged robot to teach itself to walk. Using the RL algorithm, the hexapod learnt how to walk in a matter of hours instead of days. (ANI)

 
  LATEST COMMENTS ()
POST YOUR COMMENT
Comments Not Available
 
POST YOUR COMMENT
 
 
TRENDING TOPICS
 
 
CITY NEWS
MORE CITIES
 
 
 
MORE ASIA NEWS
India hands over two Mi 24V choppers to ...
New hub for NSG commandos to come up in ...
Modi to open Kartarpur Sahib corridor in...
Britain's royal couple in Pakistan for 5...
Imran heads to Riyadh to defuse Iran-Sau...
Pakistan offers to host Saudi-Iran talks...
More...
 
INDIA WORLD ASIA
SC likely to wrap up Ayodhya case hearin...
Telangana HC directs state govt, TSRTC e...
Video of 'drug party' inside Jodhpur jai...
Uttar Pradesh: Home Guard Minister assur...
Second PMC Bank depositor dies of heart ...
RSS to convene meeting of Pracharaks in ...
More...    
 
 Top Stories
US, Italy condemn deadly airstrike ... 
Second PMC Bank depositor dies of h... 
Will not be having a vote at this t... 
Uttar Pradesh: Home Guard Minister ... 
Will not be having a vote at this t... 
Qatar defends Turkey's incursion in... 
Banerjee's achievement bigger and t... 
Imperative now is to end incursion ...