Disadvantage of ANN model Other than ANN inconsistent prediction performance, What is other ANN disadvantage and weakness?
 A: Here are several disadvantages that I can think of off the top of my head:


*

*Long training times for deep networks, which are the most accurate architecture for most problems. This is especially true if you're training on a CPU instead of a specialized GPU instance.

*Need lots of data, especially for architectures with many layers. This is a problem for most ML algorithms, of course, but is especially relevant for ANNs because of the vast number of weights and connections in ANNs.

*Architectures have to be fine-tuned to achieve the best performance. There are many design decisions that have to be made, from the number of layers to the number of nodes in each layer to the activation functions, and an architecture that works well to some one problem very often does not generalize well.

A: Neutral networks does give predictable performance. Other than the things @liangly already written:


*

*It's far complicated than many other models, such as decision tree and regression. It's hard to interpret and understand the weights, and why it has to be like that. Weights in regression have simple statistical meaning.

*Harder to visualize and present your ANN model, in particular, non-technical audience. Decision tree is simple for them. Regression may also be visualized.

*Easier to overfit your model with ANN.

*It's harder to get confidence and prediction interval in ANN. They are useful in regression.
