Merge MLP And CNN in Keras

In the post (, it was shown how to build a merge-layer DNN by using the Keras Sequential model. In the example below, I tried to scratch a merge-layer DNN with the Keras functional API in both R and Python. In particular, the merge-layer DNN is the average of a multilayer perceptron network and a 1D convolutional network, just for fun and curiosity. Since the purpose of this exercise is to explore the network structure and the use case of Keras API, I didn’t bother to mess around with parameters.