Programmable Bootstrapping Enables Efficient Homomorphic Inference of Deep Neural Networks.
Ilaria ChillottiMarc JoyePascal PaillierPublished in: IACR Cryptol. ePrint Arch. (2021)
Keyphrases
- neural network
- pattern recognition
- back propagation
- low cost
- artificial neural networks
- bayesian model
- neural nets
- bayesian networks
- belief nets
- inference process
- privacy preserving
- multilayer perceptron
- probabilistic inference
- multi layer
- associative memory
- dynamic bayesian networks
- activation function
- fuzzy systems
- data sets
- fuzzy logic
- random fields
- self organizing maps
- weakly supervised
- general purpose
- decision trees
- processor array