San Francisco, July 29 (IANS) Alphabet-owned Waymo has partnered with UK-based computer programmes company DeepMind on a 'Population-Based Training' method for pedestrian detection that has the best neural networks like life forms do in natural selection, thus, saving time and effort.
According to the company, Waymo's self-driving vehicles employ neural networks to perform many driving tasks, from detecting objects and predicting how others will behave, to planning a car's next moves.
"Now, Waymo, in a research collaboration with DeepMind, has taken inspiration from Darwin's insights into evolution to make this training more effective and efficient," Yu-hsin Chen, Senior Software Engineer at Waymo recently wrote in a blog post.
"To make this process more efficient, researchers at DeepMind devised a way to automatically determine good hyperparameter schedules based on evolutionary competition (called 'Population-Based Training' or PBT), which combines the advantages of hand-tuning and random search," Chen added.
Like random search, PBT also starts with multiple networks initiated with random hyperparameters.
Gopi Adusumilli is a Programmer. He is the editor of SocialNews.XYZ and President of AGK Fire Inc.
He enjoys designing websites, developing mobile applications and publishing news articles on current events from various authenticated news sources.
When it comes to writing he likes to write about current world politics and Indian Movies. His future plans include developing SocialNews.XYZ into a News website that has no bias or judgment towards any.
He can be reached at gopi@socialnews.xyz
This website uses cookies.