Correct me if I'm wrong but I get the impression is that Convolutional Neural Networks (cnn) are the constructs that have demonstrated a unique effectiveness for deep neural networks and have done this primarily through pattern recognition.
Recurrent NNs are a different beast, predicting sequential processes and so operating in an area closer to hidden Markov chain that have some successes but their operations and direction don't seem as convnets.
Note that since the game of go is a sequence of moves, one might training a RNN to play go. However, AlphaGo (very roughly) used a Convnet to tell a Monte Carlo Tree structure which final positions looked good.
Recurrent NNs are a different beast, predicting sequential processes and so operating in an area closer to hidden Markov chain that have some successes but their operations and direction don't seem as convnets.
Note that since the game of go is a sequence of moves, one might training a RNN to play go. However, AlphaGo (very roughly) used a Convnet to tell a Monte Carlo Tree structure which final positions looked good.
I'm going partly from: http://neuralnetworksanddeeplearning.com/chap6.html#other_ap...