I have several sentences that I transformed into vectors. With these vectors I would like to predict another vector (which represents a vector of a sentence (the answer)).
Can you tell me if this kind of neural network fits this problem? (In term of loss function, activation function (I didn't use an activation function for the output), and metrics.
model = Sequential() model.add(Dense(1024, input_shape=(1200,))) model.add(Activation('relu')) model.add(Dense(100)) model.compile(loss='mse', optimizer='rmsprop', metrics=['mae'])
Input: Several sentences, converted into 100 dimensions array (so, 12 sentences)
Output: 100 dimensions array, that should correspond to the kind of answer we would have from the 12 sentences.