Depth Separations in Neural Networks: Separating the Dimension from the Accuracy.
Itay SafranDaniel ReichmanPaul ValiantPublished in: CoRR (2024)
Keyphrases
- neural network
- computational cost
- error rate
- prediction accuracy
- database
- reinforcement learning
- high accuracy
- back propagation
- accuracy rate
- error analysis
- multi layer
- highly accurate
- associative memory
- multilayer perceptron
- feed forward
- depth map
- classification accuracy
- computational complexity
- pattern recognition
- training data
- decision trees
- decision making
- learning algorithm
- real time