DeepMind Shows AI Has Trouble Seeing Homer Simpson’s Actions

By IEEE Spectrum

June 12, 2017

Comments

Deepmind algorithms can't capture actions performed by Homer Simpson as acurately as they do actions by normal humans.

DeepMind has correctly identified and tagged actions in the YouTube clips in its Kinetics dataset about 80% of the time (capture of actions taken by cartoon character Homer Simpson were accurately classified about 20% of the time … or less).

Although algorithms trained on the dataset were about 80% accurate in classifying actions such as “playing tennis,” “crawling baby,” “cutting watermelon,” and “bowling,” their accuracy fell to about 20% or less for actions performed by the animated character Homer Simpson.

Credit: FOX/Getty Images

DeepMind has created a YouTube dataset of 300,000 video clips and 400 human action classes, designed to train its deep-learning algorithms to better identify human activities and behaviors.

With the assistance of online workers via Amazon’s Mechanical Turk service, DeepMind has correctly identified and tagged the actions in the YouTube clips in its Kinetics dataset.

Although algorithms trained on the dataset were about 80% accurate in classifying actions such as “playing tennis,” “crawling baby,” “cutting watermelon,” and “bowling,” their accuracy fell to about 20% or less for actions performed by the animated character Homer Simpson.

Meanwhile, a preliminary study found the dataset appears to be to fairly gender-balanced, with neither gender dominating within 340 out of the 400 action classes–otherwise it was impossible to determine gender in those actions.

DeepMind wants outside researchers to help suggest new human action classes for the dataset, improving the identification accuracy of artificial intelligences trained on it.

From IEEE Spectrum
View Full Article

 

Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA


 

No entries found

from Communications of the ACM: Artificial Intelligence http://ift.tt/2rnMoQH

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s