DeepLearningModule

Custom Deep Learning Module programmed in base Python as a learning exercise.

This project showcases a custom DeepLearning module programmed in base Python. This was part of a a Machine Learning course about Deep Learning. The Jupyter Notebook showcases the following:

Part A:

1. Activation functions
2. Derived Activation functions
3. Loss functions
4. Single-Layer Perceptron Classification
5. Binominal Logistic Regression Classification
6. Multi-Layer Perceptron Classification
7. Linear Regression
8. Regression using a full Neural Network

Part B:

Using the module to classify hand-written number from the MNIST dataset

1. Classification using a dummy network [step 1-7] with an accuracy of 54%
2. Classification using an actual network [step 1-7] with 8.2 minutes training time and 89.9% accuracy.