The State of Knowledge Distillation for Classification

1 code implementation • 20 Dec 2019 • Fabian Ruffy, Karanbir Chahal

We survey various knowledge distillation (KD) strategies for simple classification tasks and implement a set of techniques that claim state-of-the-art accuracy.

Classification Data Augmentation +2

Hydra: A Peer to Peer Distributed Training & Data Collection Framework

1 code implementation • 24 Nov 2018 • Vaibhav Mathur, Karanbir Chahal

Hydra couples a specialized distributed training framework on a network of these low powered devices with a reward scheme that incentivizes users to provide high quality data to unleash the compute capability on this training framework.

A Hitchhiker's Guide On Distributed Training of Deep Neural Networks

no code implementations • 28 Oct 2018 • Karanbir Chahal, Manraj Singh Grover, Kuntal Dey

Deep learning has led to tremendous advancements in the field of Artificial Intelligence.

Playing the Game of 2048