WinTA: An Efficient Reconfigurable CNN Training Accelerator With Decomposition Winograd
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Circuits and Systems I: Regular Papers"
DOI: 10.1109/tcsi.2023.3338471
Abstract: Convolutional neural networks (CNNs) are expected to bridge the domain shift between the training data and real-world tasks. Moreover, the efficient training of CNNs on resource-constrained platforms has become more important because of communication latency… read more here.
Keywords: reconfigurable cnn; training; cnn training; decomposition winograd ... See more keywords