Structured Bayesian Compression for Deep models in mobile enabled devices for connected healthcare
This work targets the problem of computational inefficiency in deep models for mobile healthcare applications, presenting an incremental improvement in model compression techniques.
The paper addresses the challenge of deploying deep neural networks on mobile devices for connected healthcare by proposing a structured Bayesian compression method to reduce the models' millions of parameters, aiming to improve energy cost-effectiveness and computational efficiency.
Deep Models, typically Deep neural networks, have millions of parameters, analyze medical data accurately, yet in a time-consuming method. However, energy cost effectiveness and computational efficiency are important for prerequisites developing and deploying mobile-enabled devices, the mainstream trend in connected healthcare.