Globally Optimal Training of Neural Networks with Threshold Activation Functions.
Tolga ErgenHalil Ibrahim GullukJonathan LacotteMert PilanciPublished in: ICLR (2023)
Keyphrases
- globally optimal
- activation function
- neural network
- feed forward neural networks
- backpropagation algorithm
- feedforward neural networks
- back propagation
- artificial neural networks
- hidden layer
- feed forward
- training phase
- multi layer perceptron
- training algorithm
- graph cuts
- multilayer perceptron
- locally optimal
- neural architecture
- neural nets
- network architecture
- radial basis function
- connection weights
- hidden nodes
- basis functions
- learning rate
- training process
- support vector
- multi layer
- global optimality
- recurrent neural networks
- neural network model
- pattern recognition
- fuzzy neural network
- fault diagnosis
- higher order
- supervised learning
- image processing
- genetic algorithm
- machine learning