2017/10/07 by Forrest Iandola, Kurt Keutzer, Iandola, Forrest +1 · 1 citation
Computer Science · Neuroscience · #Advanced Neural Network Applications #Brain Tumor Detection and Classification #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Neural Networks and Applications #cs.CV
paper · pdf · doi:10.48550/arxiv.1710.02759
Keynote at Embedded Systems Week (ESWEEK) 2017
arxiv created 2017/10/07 · openalex publication_date 2017/10/07 · arxiv updated 2017/10/10 · openalex created_date 2017/10/20 · openalex updated_date 2026/07/28
Over the last five years Deep Neural Nets have offered more accurate solutions to many problems in speech recognition, and computer vision, and these solutions have surpassed a threshold of acceptability for many applications. As a result, Deep Neural Networks have supplanted other approaches to solving problems in these areas, and enabled many new applications. While the design of Deep Neural Nets is still something of an art form, in our work we have found basic principles of design space exploration used to develop embedded microprocessor architectures to be highly applicable to the design of Deep Neural Net architectures. In particular, we have used these design principles to create a novel Deep Neural Net called SqueezeNet that requires as little as 480KB of storage for its model parameters. We have further integrated all these experiences to develop something of a playbook for creating small Deep Neural Nets for embedded systems.