Exploring the Training and Execution Acceleration of a Neural Network in a Reconfigurable General-purpose Processor for Embedded Systems.
Grégory Calegari MarchesanEverton Alceu CararaMarcelo Serrano ZanettiLeonardo Londero de OliveiraPublished in: NEWCAS (2019)
Keyphrases
- embedded systems
- general purpose
- neural network
- low cost
- instruction set
- field programmable gate array
- training process
- embedded devices
- computing power
- real time systems
- smart camera
- resource limited
- embedded software
- processing power
- artificial neural networks
- back propagation
- software systems
- real time image processing
- hardware software
- application specific
- digital signal
- graphics processing units
- parallel processing
- relational databases
- flash memory
- computer architecture
- hardware and software
- data model
- consumer electronics