XOR_p A maximally intertwined p-classes problem used as a benchmark with built-in truth for neural networks gradient descent optimization.
Danielle Thierry-MiegJean Thierry-MiegPublished in: CoRR (2018)
Keyphrases
- neural network
- optimization algorithm
- pattern recognition
- optimization problems
- optimization process
- global optimization
- genetic algorithm
- artificial neural networks
- cost function
- back propagation
- fuzzy systems
- highly non linear
- stochastic gradient descent
- optimization model
- optimization methods
- optimization method
- learning rules
- fault diagnosis
- faster convergence
- discrete optimization
- multi class
- objective function