We propose extreme compression techniques like binarization, ternarization for Turbo code
based Neural Decoders such as TurboAE. These methods reduce memory and computation …

In the era of Deep Neural Network based solutions for a variety of real-life tasks, having a
compact and energy-efficient deployable model has become fairly important. Most of the …

Compact and energy-efficient models have become essential in this era when deep learning-
based solutions are widely used for various real-life tasks. In this paper, we propose rotating …