Artificial neuron network is the building block for deep learning algorithms. However, understanding how the artificial neuron network functions can be challenging, especially for self-taught students like myself. In this notebook, I share a multi-layer artificial neuron network that I developed from scratch with the feature of customizing the number of layers and the number of neurons in each layer. I also include the full math derivations using two simple examples to illustrate the principle of the algorithm. At the end, I also walk through the most important function in my classifier - the "fit" function - and explain step by step what the code does. I hope this little document can be helpful for people to better understand some basic logics behind the multi-layer articificial neuron network algorithms.
KuanWeiBeCool/Implementing-A-Multi-Layer-Artificial-Neuron-Network-From-Scratch
In this notebook, I share a multi-layer artificial neural network that I developed from scratch with the feature of customizing the number of layers and the number of neurons in each layer. I also include the full math derivations using two simple examples to illustrate the principle of the algorithm. At the end, I also walk through the most important function in my classifier - the "fit" function - and explain step by step what the code does.
Jupyter Notebook