Tree DNN: A Deep Container Network

no code implementations • 7 Dec 2022 • Brijraj Singh, Swati Gupta, Mayukh Das, Praveen Doreswamy Naidu, Sharan Kumar Allur

TreeDNN helps in training the model with multiple datasets simultaneously, where each branch of the tree may need a different training dataset.

Multi-Task Learning

AutoCoMet: Smart Neural Architecture Search via Co-Regulated Shaping Reinforcement

no code implementations • 29 Mar 2022 • Mayukh Das, Brijraj Singh, Harsh Kanti Chheda, Pawan Sharma, Pradeep NS

Designing suitable deep model architectures, for AI-driven on-device apps and features, at par with rapidly evolving mobile hardware and increasingly complex target scenarios is a difficult task.

Neural Architecture Search

Reinforcement Learning Based Asymmetrical DNN Modularization for Optimal Loading

no code implementations • 1 Jan 2021 • Brijraj Singh, Yash Jain, Mayukh Das, Praveen Doreswamy Naidu

Latency of DNN (Deep Neural Network) based prediction is the summation of model loading latency and inference latency.

reinforcement-learning Reinforcement Learning (RL)