Neural Network

2. It takes some inputs, some parameters, and produces a set of outputs
4. It is a multiplier that controls the degree to which increases or decreases of each weight during each iteration
8. The process that creates an improved weight value when repeated over and over
9. Refers to feed inputs to a model, collect its outputs, compare them with the expected outputs, and change the weights to make to correct the outputs.
11. With more data than that you can process or compute the gradient for all data, you can compute it for a small subset of the given data and apply it in sequence
12. Train the model with every data example one have

1. A function that measures the wrongness of the model
3. A function that enables neural networks to learn complex, nonlinear relationships between features and the label
5. Computational model of a neuron
6. It is an intercept or offset from an origin or reference
7. Rectified Linear Unit
10. By changing the values the network become able to make it do different things