convolutional neural networks for embedded systems
One of the problems for deploying convolutional neural networks(CNNs) on embedded systems has been large memory, power consumption, and computational complexity. In these networks, hundreds of filters and channels should be processed in high-dimensional convolutions. These computations cause a significant amount of data movement. There have been several proposed CNNs in order to make them suitable for embedded systems. Furthermore, there have been efforts in order to find a dataflow that supports parallel processing with minimal data movement cost in order to achieve a fast and energy-efficient CNN with the same accuracy. In this seminar, we will discuss the efforts that have been done to deploy the CNNs on embedded systems.