The public defense of Mohammad Loni’s licentiate thesis in Computer Science and Engineering
The public defense of Mohammad Loni's licentiate thesis in Computer Science will take place at Mälardalen University, room U2-024 (Västerås Campus) and online via Zoom at 11.30 on December 4, 2020.
Title: “DeepMaker: Customizing the Architecture of Convolutional Neural Networks for Resource-Constrained Platforms”.
Serial number: 299.
The faculty examiner is Professor Franz Pernkopf, Graz University of Technology.
The examining committee consists of Professor Franz Pernkopf; Professor Vladimir Vlassov, KTH; Associate Professor Andreas Ermedahl, Ericsson.
Reserve; Professor Shahina Begum, Mälardalen University.
Convolutional Neural Networks (CNNs) suffer from energy-hungry implementation due to requiring huge amounts of computations and significant memory consumption. This problem will be more highlighted by the proliferation of CNNs on resource-constrained platforms in, e.g., embedded systems.
In this thesis, we focus on decreasing the computational cost of CNNs in order to be appropriate for resource-constrained platforms. The thesis work proposes two distinct methods to tackle the challenges: optimizing CNN architecture while considering network accuracy and network complexity, and proposing an optimized ternary neural network to compensate the accuracy loss of network quantization methods. We evaluated the impact of our solutions on Commercial-Off-The-Shelf (COTS) platforms where the results show considerable improvement in network accuracy and energy efficiency.