Multi-layer neural networks
A multi-layer neural network is the structure that we are using for word2vec. This function takes input as a one-hot encoded word vector and this vector, as well as a weighted sum is passed to a hidden layer. By using the activation function, which is the sigmoid function in this case, output is generated from the hidden layer and this output is passed to the next layer, which is the output layer. We have already seen an example in this chapter, in the section entitled Neural network with two layers. In that section, we did not look at the mathematical aspect, so here I will walk you through the mathematical aspect of neural networks.
So, let's represent what I told you in the preceding paragraph through a mathematical ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access