In this research, researchers will study and improve an existing deep RL (reinforcement learning) network, developed by the Google Brain team, that will place deep learning operations of another deep learning network in the most efficient manner within a heterogeneous computing system or a multi-GPU system. Finding the most efficient placement will reduce the training
Faculty Mentor: Ming Zhao
Are Existing Knowledge Transfer Techniques Effective to Train Deep Networks On Edge Devices?
With the emergence of the edge computing paradigm, many edge applications, such as image recognition and augmented reality requires performing machine learning and artificial intelligence workloads on edge devices. Most ML models are large and computationally heavy, whereas edge devices are usually equipped with limited power and energy. Unfortunately, small models cannot perform well. Recent
