|Support type:||Scholarships abroad - Research|
|Effective date (Start):||October 01, 2019|
|Effective date (End):||September 30, 2020|
|Field of knowledge:||Physical Sciences and Mathematics - Computer Science - Computer Systems|
|Principal researcher:||Vanderlei Bonato|
|Home Institution:||Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil|
|Research place:||Imperial College London, England|
The adoption of Deep Neural Networks on real time systems requires a special attention to thelatency of the network inference stage. The signal propagation delay through layers stronglydepends on memory organisation, network connectivity balance, and on the level of computing parallelisation along with the operations complexity. Recent works demonstrated promising results from design space exploration techniques for multi-objective metrics, considering latency, accuracy, and computational resources. However, when ultra low latency is desired the challenge remains since it does a strong pressure on computational resources requiring not only architectural improvements, but also further problem-orientated optimisations provided by highly customised hardware components. This research project aims to explore the conditions to enable ultra low latency deployments of CNN and LSTM-based models on FPGAs, having as case study the High Frequency Trading problem.