Skip to content

Latest commit

 

History

History
144 lines (94 loc) · 6.26 KB

Readme.md

File metadata and controls

144 lines (94 loc) · 6.26 KB

Machine Learning Roadmap

1: Pick a programming language

There are different programming languages in the tech-sphere, but most preferred programming language for ML are Python and R.

Python is more recommended. Why? Because its popular, easy to learn and future-ready.

With Python, you can switch domains easily too. Python offers popular frameworks like Django and Flask for backend development, Tkinter for GUI development, Pygames for Game development, etc.

If you go with Python, you must learn sklearn for Machine Learning. Sklearn is a modern machine learning library written in Python.

The best thing about sklearn is that most of the Machine learning algorithms are written for you already. It has a lot of useful classes for preprocessing your data for further analysis

You should also look into the Tensorflow module, which can help you build a neural network without many efforts.

Resource

You can follow any of the resources below according to which you are comfortable with:

2: Learn Linear Algebra

Yes, there's maths here too. You should learn Linear Algebra if you want to master Machine Learning.

This is essential because if you want to tune your models with maximum flexibility, you need to know how they work, and knowing linear algebra is a must for that!

You can start learning linear algebra paralley with Programming Language.

Resource

3: Learn Statistics and Probability

You should have the good knowledge of Statistics and Probability. It is required for Machine Learning because with a decent understanding of statistical methods you can convert raw observations into information that is easy to understand, digest, and share. This will allow you to create machine learning models that will consistently deliver results.

Resource

4: Learn Python Libraries

After haviing the good knowledge of Programming Fundamentals; you should explore libraries:

  • Numpy
  • Pandas
  • All this will be helpful to debug the python/sklearn code.

Resource

5: Learn Core ML Algorithms

In order to get an idea of how these Machine learning algorithms work from within, look into:

  • Supervised vs Unsupervised learning
  • KNN (K Nearest Neighbours)
  • SVM (Support Vector Machine)
  • Decision Tree
  • Random Forest
  • Overfitting, Underfitting
  • Regularization
  • Gradient Descent
  • Slope
  • Reinforcement Learning
  • Basic Linear Regression
  • Logistic Regression
  • Clustering
  • Confusion Matrix
  • Working of all such similar models

Resource

6: Learn Data Preprocessing

Machine Learning is not only about the Algorithms. It also depends upon the data. So, for higher accuracy of Machine you should also learn:

  • Handling Null Accuracy
  • Standardization
  • Handling Categorial Values
  • One-Hot Encoding
  • Feature Scaling

Resource

7: Learn ML Libraries

Now, after having the clear concepts of Programming Language, its libraries, and ML Algorithms you can move forward to learn ML libraries:

  • Scikit Learn
  • Matplotlib
  • Tensorflow

Resource

8: Learn Deployment

To host your machine learning models with a powerful backend, you will need to learn frameworks like Django and Flask.

Docker and Kubernetes can be of great help if you want to ship and deploy your models quickly.

Streamlit is worthy of looking into if you wish to build custom web apps for machine learning and data science.

Resource

9: Practice

After Learning theories and learning from different resources start doing practice and enhance your skills.

Resource