Mobile and Intelligent Computing Laboratory
Research

Research

Promoted by the evolution of artificial intelligence and deep learning, more and more intelligent applications have emerged on mobile devices. As one of the most representative deep learning technologies, deep neural networks (DNNs) have been widely applied to many fields such as computer vision, speech recognition, natural language processing, and audio recognition, where they have produced results comparable to and in some cases surpassing human expert performance. However, the heavy computation, memory, and energy demands of the deep learning model restrict their deployment on resource-constrained mobile devices.
The MIC Lab at SFSU performs research in efficient mobile computing, deep learning acceleration, and distributed edge computing. A key focus of MIC Lab is to achieve computational acceleration for deep learning on low-power hardware without heavy compute or storage capabilities. Our research addresses the efficiency, reliability, and security challenges in the algorithm design and system optimization as well as application development to create intelligent mobile edge computing system.

Efficient Mobile Computing

  • Deep Neural Networks (DNN) compression and acceleration
  • Dynamic DNN computation resource modeling for efficient mobile system
  • Task-adaptive DNN reconfiguration for high-performance mobile applications

Distributed Edge Computing

  • Decentralized collaborative edge learning system design by DNN model decoupling
  • Distributed DNN training phase adaptation on mobile device

Interpretable Deep Learning

  • DNN neuron functionality visualization for model structure decoupling
  • DNN computational flow redefinition for efficient inference