Tiny machine learning design alleviates a bottleneck in memory usage on internet-of-things devices

An MIT team evaluated memory bottleneck to deploying machine learning on small "internet of things" devices and created a new method and device that outperforms other tinyML methods on image detection and classification tasks.

Related Keywords

Shan Cai ,Wei Ming Chen ,Ji Lin ,Samsung ,Watson Ai Lab ,National Science Foundation ,Department Of Electrical Engineering ,Cnn ,Woodside Energy ,Watson Ai Lab Research Scientist Chuang Gan ,Song Han ,Electrical Engineering ,Computer Science ,Neural Information Processing Systems ,National Science ,Mit Ibm Watson Ai Lab ,Nternet Of Things ,Edge Devices ,Tinyml ,Computer Vision ,Tiny Machine Learning ,Icrocontroller Unit Mcu ,Dong Han ,Onvolutional Neural Networks Cnns ,Cunetv2 ,Ryan Cai ,Chuang Gan ,