Monday, June 17, 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
Soldier injured in ceasefire violation i...
Indian, Pakistani troops in heavy gun fi...
Three civilians injured in Pakistan firi...
Rifts in Hurriyat over fund collection, ...
High alert in J&K after Pak inputs on pr...
Xi says China wants Indo-Pak ties to imp...
More...
 
INDIA WORLD ASIA
Encounter underway in J-K's Anantnag...
WB doctors' strike: Mamata to meet 2 rep...
Mayawati hits out at UP Govt on proposed...
Keeping with tradition, PM Modi takes oa...
SC to hear tomorrow plea seeking securit...
Kejriwal, Amarinder Singh slam Delhi Pol...
More...    
 
 Top Stories
Tech firms can't dodge responsibili... 
Researchers build AI system to conn... 
Karnataka doctors on day-long strik... 
Netanyahu names Golan Heights estab... 
Sensex in red, Reliance Industries ... 
Environment-friendly battery golf c... 
Defence Ministry to streamline expo... 
Manipal in talks with Jigsaw Academ...