On-device AI: Quantization-aware Training of Transformers in Time-Series
This work addresses the problem of efficient on-device AI deployment for pervasive computing applications, though it appears incremental as it builds on existing quantization techniques.
The research tackles the challenge of deploying large Transformer models for time-series forecasting on resource-constrained sensor devices by applying Quantization-aware Training to reduce model size and memory usage, aiming to optimize performance for FPGA hardware accelerators.
Artificial Intelligence (AI) models for time-series in pervasive computing keep getting larger and more complicated. The Transformer model is by far the most compelling of these AI models. However, it is difficult to obtain the desired performance when deploying such a massive model on a sensor device with limited resources. My research focuses on optimizing the Transformer model for time-series forecasting tasks. The optimized model will be deployed as hardware accelerators on embedded Field Programmable Gate Arrays (FPGAs). I will investigate the impact of applying Quantization-aware Training to the Transformer model to reduce its size and runtime memory footprint while maximizing the advantages of FPGAs.