An Efficient Reduce-and-Scale Architecture for DNN-based Inference on Resource-Constrained Systems

13.03.2019 11:15 – 12:15

While Deep Learning is becoming ubiquitous in computing, being deployed in systems ranging from data centers to mobile devices, its computational complexity is huge. Contrary, while resource-constrained systems steadily improve their processing power, there is a huge gap to the demands of deep neural networks. Furthermore, CMOS technology projections show that performance scaling will be increasingly difficult, due to reasons including power consumption and eventually limited component scaling.
In the DeepChip collaboration, we gear to design software architectures that improve the mapping of DNNs to resource-constrained systems. In this talk, we will shortly review basics and recent related work, before we introduce the main concept of DeepChip, which is based on a reduce-and-scale architecture and allows to remove redundancies found in typical DNNs, thereby allowing an improved deployment on mobile or embedded systems. We will conclude with a couple of anticipated research directions.

Lieu

Bâtiment: Ecole de Physique

Quai Ernest-Ansermet 24
1211 Genève 4
Grand Auditoire A

entrée libre