Below are notes on various topics as I learn all things AI. These notes are updated as I learn more on the topic. My raw notes are a mixture of markdown and LaTeX so will need an editor such as Typora. Below are the same notes in PDF format.
- Logistic Regression
- Binary Logistic Regression
- Multiclass Logistic Regression
- Logistic Regression Vectorization
- Introduction
- Types of Neural Networks
- Forward Propagation
- Classification and Cost
- Activation Functions
- Logic Gates
- Back Propagation
- Gradient Checking
- Parameter Initialization
- Unrolling Parameters
- Architecting a Basic Neural Network
- Training a Neural Network
As I study a topic I will create a notebook to apply concepts. Below are various notebooks on some of the topics above.
- Univariate Linear Regression
- Multivariate Linear Regression
- Binary Logistic Regression
- Multiclass Logistic Regression
- Neural Network
- K-Means Clustering
- K-Means Cluster Distance
- Data Visualization
My notes from the MIT Introduction to Computational Thinking and Data Science course are here.
This was part of the MIT course and the full source can be found here.