1---What is deep learning
Deep learning is an approach to machine learning characterized by deep stacks of computations.
This in-depth computation enables deep learning models to unravel the complex and hierarchical patterns found in the most challenging real-world datasets.
The defining model of deep learning: neural network
2---The Linear Unit
To learn a neural network, we have to start with one of its components: the individual neuron.
As a diagram, a neuron (or unit) with one input looks like:
X-input
W-weight(Neural networks learn by adjusting weights)
B-bias(Enables a neuron to adjust its output independently of its input)
Y-output
This neuron's activation is y = w * x + b, or as a formula
𝑦=𝑤𝑥+𝑏