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...
Featured Product
US Digital's New L2 Low Profile Motor Encoder
The L2 incremental encoder uses US Digital's proven EM1 optical encoder module and disk, which has billions of device-hours of dependable service in customer applications. This product continues US Digital's strong reputation for reliable, field-tested encoders. The L2 is US Digital's lowest height encoder that uses the EM1 module. It has a 0.75 in. bolt-spacing mount. The maximum resolution is 1250 CPR (5000 PPR with quadrature). The L2 comes with a single-ended output. Another benefit of the L2 incremental encoder is its fast installation. The cover snaps onto the base to secure the module. It is designed for use with a high-retention connector or cable (sold separately). Like all US Digital products, the L2 is designed and manufactured in Vancouver, Washington, USA. It is backed by prompt access to our technical and customer service teams with same-day shipping on most orders.
