Input Compression with Positional Consistency for Efficient Training and Inference of Transformer Neural Networks.
Amrit NagarajanAnand RaghunathanPublished in: CoRR (2023)
Keyphrases
- neural network
- training process
- fuzzy logic
- fault diagnosis
- training algorithm
- genetic algorithm
- inference process
- multi layer
- efficient learning
- feedforward neural networks
- feed forward neural networks
- image compression
- training set
- decision trees
- probabilistic inference
- compression ratio
- test set
- structured prediction
- backpropagation algorithm
- neural network training