Neural Network Architecture

Ok, so we're ready to put these building blocks together, and build great Neural Networks! (Or Multi-Layer Perceptrons, however you prefer to call them.)

This first two videos will show us how to combine two perceptrons into a third, more complicated one.

Combinando modelos

29 Neural Network Architecture 2

Based on the above video, let's define the combination of two new perceptrons as w ₁ *0.4 + w ₂ *0.6 + b. Which of the following values for the weights and the bias would result in the final probability of the point to be 0.88?

w ₁ : 2, w ₂ : 6, b: -2

w ₁ : 3, w ₂ : 5, b: -2.2

w ₁ : 5, w ₂ : 4, b: -3

SOLUTION:

w ₁ : 3, w ₂ : 5, b: -2.2

Multiple layers

Now, not all neural networks look like the one above. They can be way more complicated! In particular, we can do the following things:

Add more nodes to the input, hidden, and output layers.
Add more layers.

We'll see the effects of these changes in the next video.

Layers

Multi-Class Classification

And here we elaborate a bit more into what can be done if our neural network needs to model data with more than one output.

Multiclass Classification

QUESTION:

How many nodes in the output layer would you require if you were trying to classify all the letters in the English alphabet?

ANSWER:

SOLUTION:

NOTE: The solutions are expressed in RegEx pattern. Udacity uses these patterns to check the given answer