New answers tagged

0

There is sadly very little theory that is useful for predicting the behavior of neural networks. Also, their experiment tends to be dependent on the particular workload/task you are trying to solve it. While I know it's not what you were hoping to hear, I suggest that you try it in empirical experiments.


0

A general rule of thumb would be: look at the most successful architectures for your given task, take it as a prior and try to vary (by retraining) the number of layers if you need a specific point in the accuracy-speed tradeoff curve. Previously people believed that one can get more accuracy just by stacking more layers. Even though this is true in most ...


0

You can use anything you like. Right now neural networks are the state of the art: they produce the best predictions. But you could also use HMMs, or n-grams, or other methods; they just will be lower quality than a state-of-the-art neural network.


0

Try changing your input in this case if you wanted to take only the difference of two states into consideration. Think of each rounds in a discrete manner, they will be of their own distinctive state if not encountered the exactly same configuration of the board beforehand. What do you get? You get another set of states that takes differentiated states into ...


Top 50 recent answers are included