In Part 1 of the assignment I learned to implement all the building blocks of a neural network from scratch using Numpy, and use these building blocks in Part 2 to build a neural network. This cat recognition algorithm gave an 80% accuracy.In this assignment I:
- Developed an intuition of the over all structure of a neural network.
- Wrote functions (e.g. forward propagation, backward propagation, logistic loss, etc...) that would help decompose the code and ease the process of building a neural network.
- Learned to Initialize/update parameters.
- Learned that it is always easier to build helper functions before attempting to build a neural network from scratch.
- Used ReLU activation function.