Compressing deep neural networks on FPGAs to binary and ternary precision with hls4ml.
Jennifer NgadiubaVladimir LoncarMaurizio PieriniSioni SummersGiuseppe Di GuglielmoJavier M. DuartePhilip C. HarrisDylan S. RankinSergo JindarianiMia LiuKevin PedroNhan TranEdward KreinarSheila SagearZhenbin WuDuc HoangPublished in: Mach. Learn. Sci. Technol. (2021)
Keyphrases
- neural network
- maximum likelihood
- pattern recognition
- artificial neural networks
- high precision
- feed forward
- non binary
- multilayer perceptron
- back propagation
- fuzzy logic
- data compression
- recurrent neural networks
- field programmable gate array
- genetic algorithm
- network architecture
- deep architectures
- cellular neural networks
- hamming distance
- hidden layer
- fuzzy systems
- neural nets
- precision and recall
- information retrieval