Reg-TuneV2: A Hardware-Aware and Multiobjective Regression-Based Fine-Tuning Approach for Deep Neural Networks on Embedded Platforms.
Arnab Neelim MazumderTinoosh MohseninPublished in: IEEE Micro (2023)
Keyphrases
- fine tuning
- multi objective
- neural network
- embedded systems
- genetic algorithm
- evolutionary algorithm
- control software
- multiobjective optimization
- computing platform
- optimization algorithm
- fine tune
- viable alternative
- low cost
- multi objective optimization
- particle swarm optimization
- embedded processors
- fine tuned
- hardware and software
- nsga ii
- pattern recognition
- hardware software
- real time
- micro controller
- multiobjective evolutionary algorithm
- artificial neural networks
- multiple objectives
- fuzzy systems
- image processing
- objective function
- hardware platforms
- field programmable gate array
- computer systems
- smart camera
- recurrent neural networks
- cloud computing
- evolutionary computation
- neural network model
- hw sw
- feed forward
- associative memory
- general purpose
- neural nets
- min max
- multi layer