Which one of the following is NOT related to feed-forward networks trained with the Backpropagation algorithm (in terms of the functions they can represent)?
Pick an option to check yourself, or open the answer below.
Show answer & explanation
Correct answer: D. Greedy function
Explanation
Multilayer feed-forward networks can represent every Boolean function, approximate any bounded continuous function, and (with two hidden layers) approximate arbitrary functions. 'Greedy function' is not such a class.More Artificial Intelligence (AI) questions
- Match List I with List IIList I List II (A) The activation (I) is called the delta function rule. (B) The learning method of perceptron (II…
- Arrange the following steps in proper sequence involved in a Genetic Algorithm: (A) Selection (B) Initialization (C) Crossover (D) Mutation…
- Arrange the following steps in proper sequence for the process of training a neural network. (A) Weight initialization (B) Feed forward (C)…
- Match List I with List IIList I List II (A) Natural language processing (I) A method of training an algorithm by rewarding desired behaviou…
- What is the role of the Back Propagation algorithm?
- What is the role of weights in an ANN?