Why is pretraining a deep MLP network appropriate?
A) increases the chances of a global optimum being reached
B) is necessary always necessary for this type of network
C) increases duration before global optimum is reached
D) none of these

Question

Quizplus · Accepted Answer

Pretraining a deep MLP (Multi-Layer Perceptron) network can help in initializing the weights in a manner that brings the network closer to the global optimum before fine-tuning with backpropagation. This can make it easier for the network to learn and converge to a better solution, hence increasing the chances of reaching a global optimum.

Why Is Pretraining a Deep MLP Network Appropriate