Here’s something that might surprise you: neural networks aren’t that complicated! We are going to prove that in this material. This Introduction to Neural Networks is intended for complete beginners and assumes zero prior knowledge of machine learning.
First, we have to talk about neurons, the basic unit of a neural network. A neuron takes inputs, does some math with them, and produces one output.
- A neural network is nothing more than a bunch of neurons connected together.
- Before we train our network, we first need a way to quantify how “good” it’s doing so that it can try to do “better”. That’s what the loss is.
- Introduce neurons, the building blocks of neural networks.
- Use the sigmoid activation function in our neurons.
- See that neural networks are just neurons connected together.
- Create a dataset with Weight and Height as inputs (or features) and Gender as the output (or label).
- Learn about loss functions and the mean squared error (MSE) loss.
- Realize that training a network is just minimizing its loss.
- Use backpropagation to calculate partial derivatives.
- Use stochastic gradient descent (SGD) to train our network.
Find here more examples of code and interesting figures.
It will be worthwhile to select top 10 automation testing tools to take make a whole picture more complete. Enjoy!
Well, to be sure, that you’re going to get maximum information on AI and ML, visit AI & Big Data Day in Lviv! At the same time you’ll get a chance to see one of the most beautiful cities in Ukraine!
p.s. Yes, we’re making a shameless promo!