This thesis proposes "1D Convolution replacement layer ", a novel optimization for first convolution layer in CNN. This optimization enables edge friendly streaming acce[...]

Vision Transformers (ViTs) have revolutionized computer vision by shifting from convolutional architectures to attention-based models that process images as sequences of [...]

Development of accelerators for deep learning accelerators have been gaining a lot of popularity due to sheer amount computation performed by deep learning algorithms. Fr[...]