Grande área: Engenharias
Tipo de oportunidade: Pós-graduação
Objetivo: Objectives are: (1) To study how much of the anomaly detection pipeline can run locally, and how many/much features/data should be communicated to the cloud for further processing there. (2) To co-design the local algorithms for various deep learning architectures, to make sure the algorithms match the chosen architectures optimally. A logical step is here for instance the use of quantized models. Beyond that, there also exist interesting approaches to achieve structured sparsity, and hence simpler models. (3) To divide the models into small parts that can be executed intermittently, while trading off memory access cost likelihood of losing intermediate results.
Inscrições: até 31 de maio de 2021
Mais informações no site.