Machine Learning ROADMAP
In this "Machine Learning series", i will document my ML & data science projects and notes for reference.
Table of contents
I searched through many videos on the roadmap for ML and found the following common topics.
Having a rough roadmap will help establish foundational topics that are essential to learn and provide some structure.
Machine learning is one of important skill in the domain of Data science.
I will update this with more topics, and resources as I progress.
Version control (Git and GitHub) https://hashnode.com/post/cm6nymept000s09l1blk1aivb
Python
Install Jupyter notebooks
Basic syntax (indentation rules, comments)
Variables , math , if/else, loops, printing
Data types (strings, int, float, boolean, lists, tuple, dictionary)
Functions and classes/objects
Modules, packages and importing
Foundational Math
Statistics & Probability(Khan academy course) - conditional probability, Bayes rule, Statistical distributions
Linear algebra (Matrices, vectors , eigen vectors/values) (khan academy course)
Calculus (Differentiation, Integration) - optimization (gradient descent—>derivatives)
Data Manipulation (preprocessing, cleaning ; visualization)
Python Libraries - Pandas, Numpy; matplotib, seaborn
Handling Null Values
Standardization
Handling Categorical Values
One-Hot Encoding
Feature Scaling
- ML core
Supervised vs Unsupervised vs Reinforcement
Linear Regression, Logistic Regression, Clustering
KNN (K Nearest Neighbours)
SVM (Support Vector Machine)
Decision Trees
Random Forests
Overfitting, Underfitting
Regularization, Gradient Descent, Slope
Confusion Matrix
- Deep learning
- Neural networks
- Projects
Resources
UCI machine learning repository(for datasets) https://archive.ics.uci.edu/datasets
Kaggle https://www.kaggle.com/datasets?search=Machine+learning+datasets
Roadmap videos