Deep Learning Notebooks

📕 This is a repo for my notes and code snippet from my Deep Learning Journey. Notebooks cover the foundation concepts of DeepLearning, Neural networks and AI project.

Neural Networks From Scratch

Authors: Harrison Kinsley & Daniel Kukieła, How to build a Neural Networks from scatch with Python and Numpy. Self notes taken on January 2022

Content	Topics.	Colab	Github
Chapter 2	Coding your first neural network
Chapter 3	Adding layers
Chapter 4	Activation function
Chapter 5	Calculation Network error loss
Chapter 6	Introducing optimization
Chapter 7	Derivatives
Chapter 8	Gradients, Partial derivative, and the chain rules
Chapter 9	Backpropagation
Chapter 10	Optimizers	WIP	WIP
Chapter 11	Testing data	WIP	WIP
Chapter 12	Validation data	WIP	WIP
Chapter 13	Training dataset	WIP	WIP
Chapter 14	L1 and L2 regularization	WIP	WIP
Chapter 15	Dropout	WIP	WIP
Chapter 16	Binary logistic regression	WIP	WIP
Chapter 17	Regression	WIP	WIP
Chapter 18	Model object	WIP	WIP
Chapter 19	Real dataset	WIP	WIP
Chapter 20	Model evaluation	WIP	WIP
Chapter 21	Saving and loading model information	WIP	WIP
Chapter 22	Model prediction_inference	WIP	WIP

Deep Learning with Python (Keras/Tensorflow)

Second Edition, Author: Francois Chollet, Publishers: Manning Publications. Self notes taken February 2022.

Content	Topics.	Colab	Github
Chapter 2	The Mathematical building blocks of Neural Network
Chapter 3	Introduction to Keras and Tensorflow
Chapter 4	Getting started with neural networks: Classification and regression
Chapter 5	Fundamentals of machine learning
Chapter 6	The universal workflow of machine learning	WIP	WIP
Chapter 7	Working with Keras a deep dive
Chapter 8	Introduction to deep learning for computer vision
Chapter 9	Advance deep learning for computer vision Keras
Chapter 10	Deep learning for Timeseries
Chapter 11	Deep learning for text	WIP	WIP
Chapter 12	Generative for deep learning	WIP	WIP
Chapter 13	Best practice for the real world	WIP	WIP