Innovative Machine Learning Training Method Opens New Possibilities for Artificial Intelligence

From AZoRobotics:  As a result of a new machine learning algorithm formulated by engineering researchers Parham Aarabi (ECE) and Wenzhi Guo (ECE MASc 1T5) at University of Toronto, smartphones may soon be able to provide users with honest answers.

The researchers prepared an algorithm that was capable of learning directly from human instructions, instead of an existing set of examples, and surpassed conventional techniques of training neural networks by 160%.

But more astonishingly, their algorithm also surpassed its own training by 9% - it learned to identify hair in pictures with better reliability than that enabled by the training, signifying a major leap forward for artificial intelligence.  Cont'd...

Comments (0)

This post does not have any comments. Be the first to leave a comment below.


Post A Comment

You must be logged in before you can post a comment. Login now.

Featured Product

Schmalz Technology Development - The Right Gripper for Every Task

Schmalz Technology Development - The Right Gripper for Every Task

In order to interact with their environment and perform the tasks, lightweight robots, like all industrial robots, depend on tools - and in many cases these are vacuum grippers. These form the interface to the workpiece and are therefore a decisive part of the overall system. With their help, the robots can pick up, move, position, process, sort, stack and deposit a wide variety of goods and components. Vacuum gripping systems allow particularly gentle handling of workpieces, a compact and space-saving system design and gripping from above. Precisely because the object does not have to be gripped, the vacuum suction cupenables gapless positioning next to each other.