Efficient Accuracy Recovery in Approximate Neural Networks by Systematic Error Modelling.
Cecilia De la ParraAndre GuntoroAkash KumarPublished in: ASP-DAC (2021)
Keyphrases
- neural network
- error rate
- high accuracy
- data sets
- computational cost
- prediction accuracy
- feed forward
- maximum error
- average error
- relative error
- multilayer perceptron
- classification accuracy
- artificial neural networks
- pattern recognition
- error bounds
- neural network model
- cost effective
- recurrent neural networks
- highly accurate
- error analysis
- computational complexity