Building Neural Networks

• Below we see a basic input-output type of neural network: It has one input layer with 4 neurons and one output layer with 1 neuron. - We can add another layer called a “hidden” layer with 6 neurosn in-between the input and output layers and this process can be keep repeating itself.
• These different ways that neural networks can be constructed are called architectures.

• Every purpose, every application, every challenge will have a different architecture that serves it best.
• Finding the right neural network architecture is actually a very creative process.
• And that’s why expert ML engineers and data scientists who build DL algorithms are in such high demand.