DeepMaker : A multi-objective optimization framework for deep neural networks in embedded systems

• Deep Neural Networks (DNNs) are compute-intensive learning models with growing applicability in a wide range of domains. Due to their computational complexity, DNNs benefit from implementations that utilize custom hardware accelerators to meet performance and response time as well as classification accuracy constraints. In this paper, we propose DeepMaker framework that aims to automatically design a set of highly robust DNN architectures for embedded devices as the closest processing unit to the sensors. DeepMaker explores and prunes the design space to find improved neural architectures. Our proposed framework takes advantage of a multi-objective evolutionary approach that exploits a pruned design space inspired by a dense architecture. DeepMaker considers the accuracy along with the network size factor as two objectives to build a highly optimized network fitting with limited computational resource budgets while delivers an acceptable accuracy level. In comparison with the best result on the CIFAR-10 dataset, a generated network by DeepMaker presents up to a 26.4x compression rate while loses only 4% accuracy. Besides, DeepMaker maps the generated CNN on the programmable commodity devices, including ARM Processor, High-Performance CPU, GPU, and FPGA.

Ämnesord

NATURVETENSKAP  -- Data- och informationsvetenskap (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences (hsv//eng)

TEKNIK OCH TEKNOLOGIER  -- Elektroteknik och elektronik -- Datorsystem (hsv//swe)

ENGINEERING AND TECHNOLOGY  -- Electrical Engineering, Electronic Engineering, Information Engineering -- Computer Systems (hsv//eng)

Nyckelord

Budget control; Embedded systems; Evolutionary algorithms; Integrated circuit design; Multiobjective optimization; Network architecture; Neural networks

Classification accuracy; Compression rates; Computational resources; Convolutional neural network; Custom hardwares; Design space exploration; Multi-objective evolutionary; Neural architectures

Deep neural networks

Publikations- och innehållstyp

ref (ämneskategori)

art (ämneskategori)