Active Hackathon

Facebook Trains AI To Understand Human Reactions By Watching Skype Conversation Videos

Facebook has come up with yet another development in robotics and AI. The researchers at Facebook’s AI lab have now developed an expressive bot, the animations of which are controlled by an artificially intelligent algorithm.

THE BELAMY

Sign up for your weekly dose of what's up in emerging technology.

The algorithm that has been trained by making it watch hundreds of videos of Skype conversation could now mimic the way humans adjust their expressions while talking.

The work which Facebook plans to present at the International Conference on Intelligent Robots and Systems in Vancouver, Canada, later this month, has successfully developed bots that qualifies to be ‘human-like’.

As a part of the experiment, algorithm divided human face into 68 key points that it monitored through each Skype conversation. The system learnt how people naturally nod, blink and have mouth movements while engaging in a conversation. It could look at the video of human speaking and chose an appropriate facial response in real time.

The system was also tested by a panel who watched animations that included bot reacting to a human and human reacting to a human, and judged the bot and human to be equally natural and realistic.

Though it could produce basic animations, it has to be still found out if humanoid robot powered by this algorithm would have natural seeming reactions. Goren Gordon, faculty at Tel Aviv University believes that just learning basic rules of facial communication by these robots might not be enough in creating a realistic conversation partner.

Experts also believe that robots are not so good at mastering the subtle elements of human interactions, however with Facebook’s innovation, robot conversation might reach a next level.

Almost a month ago, it was reported that Facebook’s AI robots were no longer using coherent English to communicate and had developed a language of their own by eliminating unnecessary or repetitive words.

More Great AIM Stories

Srishti Deoras
Srishti currently works as Associate Editor at Analytics India Magazine. When not covering the analytics news, editing and writing articles, she could be found reading or capturing thoughts into pictures.

Our Upcoming Events

Conference, in-person (Bangalore)
Cypher 2022
21-23rd Sep

Conference, in-person (Bangalore)
Machine Learning Developers Summit (MLDS) 2023
19-20th Jan

Conference, in-person (Bangalore)
Data Engineering Summit (DES) 2023
21st Apr, 2023

3 Ways to Join our Community

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Telegram Channel

Discover special offers, top stories, upcoming events, and more.

Subscribe to our newsletter

Get the latest updates from AIM
MOST POPULAR

Ouch, Cognizant

The company has reduced its full-year 2022 revenue growth guidance to 8.5% – 9.5% in constant currency from the 9-11% in the previous quarter

The curious case of Google Cloud revenue

Porat had earlier said that Google Cloud was putting in money to make more money, but even with the bucket-loads of money that it was making, profitability was still elusive.

[class^="wpforms-"]
[class^="wpforms-"]