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

uEye XC AUTOMATICALLY PERFECT IMAGES

uEye XC AUTOMATICALLY PERFECT IMAGES

Combining the ease of use of a webcam with the performance and reliability of an industrial camera? The uEye XC autofocus camera from IDS Imaging Development Systems proves that this is possible. Its high-resolution imaging, simple setup and adaptability make it an invaluable tool for improving quality control and streamlining workflows in industrial settings - especially for cases where users would normally employ a webcam. The uEye XC autofocus camera features a 13 MP onsemi sensor and supports two different protocols: USB3 Vision, which enables programmability and customization, and UVC (USB Video Class). The UVC functionality enables a single cable connection for easy setup and commissioning, while delivering high-resolution images and video. This makes the uEye XC camera an ideal option for applications that require quick setup and need to manage variable object distances. Additional features such as digital zoom, automatic white balance and color correction ensure precise detail capture, which is essential for quality control.