2 papers
cs.LG2022
AutoCoMet: Smart Neural Architecture Search via Co-Regulated Shaping Reinforcement
Mayukh Das, Brijraj Singh, Harsh Kanti Chheda +2
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…
cs.CV2020
Hybrid and Non-Uniform quantization methods using retro synthesis data for efficient inference
Tej pratap GVSL, Raja Kumar
Existing quantization aware training methods attempt to compensate for the quantization loss by leveraging on training data, like most of the post-training quantization methods, an…