Algorithms, Architecture, and Hardware for AI

Track Chair(s)

Lan-Da Van (NCTU, Taiwan)

Topic of Interest

AI as a field has experienced significant advancement in recent years with the onset of deep neural networks (DNNs) that are able to carry out cognitive tasks with excellent performance.  However, the algorithmic performance of DNNs comes with massive computational and memory costs that pose serious challenges to the hardware platforms on which they are executed. Therefore the exploration of new devices, architectures, and algorithms, especially as the complexity of DNNs increase, is necessary to improve processing efficiency. The topics of interest of the track include, but are not limited to:

  • Sparse learning, personalization, and feature extraction,
  • Deep learning with real-time and low-power efficiency,
  • Applications of deep learning on a smart mobile platform, and IoT devices,
  • Hardware acceleration for machine learning,
  • Synaptic plasticity and neuron motifs of learning dynamics,
  • Hardware emulation of the brain