Following is a very simple learning path designed for students to start with Machine learning.
Analyze the following !
- What is Artificial Intelligence (AI) and Machine Learning (ML)?
- Impact and applications of AI/ML across various industries like Healthcare, Finance, Agriculture etc., and how it's improving human lives.
- Skills required for AI/ML
Note : Don't let the AI craze which is happening around us let you start with Machine Learning. If you are really convinced about it's impact and if you feel it's your cup of tea, then go for it. Spend good time in analyzing these. If Yes, move to the next step
- Why Python for Machine Learning?
- Recommended Learning Resources
- Set up a local environment
- Experiment in jupyter notebooks
- Build a simple project in python like atori games
- IDE : PyCharm or VisualStudio
Tip : Try Jupyter notebook extensions which is totally cool.
- Watch Python ecosystem for Data Science
- Read Python Libraries for Data Science
- Most commonly used libraries
- Data Handling libraries
- numpy
- pandas
- Data Visualization libraries
- matplotlib
- seaborn
- bokeh
- Machine Learning libraries
- scipy
- scikit-learn
- Model Deployment
- Flask
- Django
- Data Handling libraries
Note : These are just the most commonly used libraries, not the entire set
- Statistics
- Probability Theory
- Linear Algebra
- Calculus
Tip : Instead of going by the subjects, go by the topics which is more essential for machine learning
- Read Comprehensive Guide
- Watch Khan Academy
- Read Comprehensive Guide
- Read Basic Distributions
- Watch Khan Academy
- Comprehensive Guide
- Watch Khan Academy
- Watch 3blue1brown
- Comprehensive Guide
- Watch Khan Academy
- Watch 3blue1brown
Tip : It's okay to skip this step and learn the required math concepts where ever you encounter it. But I highly encourage you to go through the basics atleast (Comprehensive Guides and Khan Academy videos in this playlist) since it will make you feel comfortable when you go through the machine learning algorithms.
-
Learn the algorithms which are not covered in MOOC
- Naive Bayes
- KNN etc.,
Tip 1: Whenever you learn an algorithm, make sure you do the following things.
- 1. Understand the basic intuition of how it works (without math)
- 2. Understand the underlying mathematics (Intuition you have now will give enough confidence to crack the math)
- 3. Implement the algorithm from scratch in python (Atleast for very important concepts like Linear Regression, Logistic Regression, Gradient Descent, Neural Networks etc.,)
- 4. Solve a simple real world problem by downloading a relevant dataset. You can use Machine Learning libraries in this phase
Tip 2: Document and Maintain your code in a github
- Sample pipeline
- Evaluation metrics
- Hyper parameter tuning
Important Tip : Start learning EDA and Machine Learning pipeline parallely once you are done with Linear and Logistic regression algorithms in the MOOC
- Go through solved problems as reference from github or kaggle kernels
- kaggle kernels
- Example : Titanic
- Places to find datasets
- Competition Platforms
Note: Do any one of the above courses.
Assuming 8-10 hours a week,
Steps | Topics | Approx Time Period |
---|---|---|
Step 1 | Decide whether Machine Learning is your cup of tea | Not more than a week |
Step 2 | Learn and Practise Python | Approx 2 weeks |
Step 2a | Python for Data Science | Not more than a week |
Step 3 | Refresh Essential High School Mathematics | Not more than a week |
Step 4 | Structured online course MOOC + Other Algorithms | Approx 2 months |
Step 4b | Exploratory Data Analysis (EDA) | Approx 2 weeks |
Step 4c | Machine Learning Pipeline Concepts | Approx 1 weeks |
Step 5 | Start solving problems with datasets. | Approx 2 weeks |
Step 6 | Start with Deep learning | Approx 2/3 months |
Tip : Personalize the above plan as per your needs.
- data-sciencetutorial-for-beginners
- python-graph-gallery
- machine-learning-glossary
- machine-learning-for-humans
- machine-learning-101
Tip : Your first task here is to build a simple end to end pipeline for a given problem, submit the solution and seeing your name in the leaderboard. Then try to improve your solution iteratively which makes you move higher in the leader board and the actual learning happens here in the iteration.
Tip: Download Feedly app and subscribe to all these blogs, forums and newsletters
Note : Being active in these communities will help you to stay motivated and informed about the latest AI advancements.
Tip : Build a professional profile and follow the active community members and research leaders once you sign up
💥 Important Note : Topics and resources mentioned in this document is just a drop in the ocean. Please don't restrict yourself only to these resources 💥
Connect with me here !