I tried a few and found a better way to learn Machine Learning

Learning Theories in Machine Learning (It’s not me btw xD)

I started to learn AI and ML way back in 2020. But, I didn’t find it easy to learn back then. So, I started to learn Web Development stuff. After around 2 years, I tried again to learn ML by following some tutorials. This time, I spent several days and months trying to find a better way to learn ML from scratch. Finally, I found a course by Andrew Ng. It’s not the same course I found apathetic to follow back in 2021. Now, it has been updated, and it’s a Machine Learning Specialization at Coursera.

Machine Learning Specailization

It has three courses:

1. Supervised Machine Learning: Regression and Classification
2. Advanced Learning Algorithms
3. Unsupervised Learning, Recommenders, Reinforcement Learning

Course 1: Supervised Machine Learning: Regression and Classification

Course 1

In the first course of the Machine Learning Specialization, I learned:

1. Build machine learning models in Python using popular machine learning libraries NumPy and scikit-learn.
2. Build and train supervised machine learning models for prediction and binary classification tasks, including linear regression and logistic regression

Course 2: Advanced Learning Algorithms

Course 2

In the second course of the Machine Learning Specialization, I learned:

1. Build and train a neural network with TensorFlow to perform multi-class classification
2. Apply best practices for machine learning development so that your models generalize to data and tasks in the real world
3. Build and use decision trees and tree ensemble methods, including random forests and boosted trees

Course 3: Unsupervised Learning, Recommenders, Reinforcement Learning

Course 3

In the third course of the Machine Learning Specialization, I learned:

1. Use unsupervised learning techniques for unsupervised learning: including clustering and anomaly detection
2. Build recommender systems with a collaborative filtering approach and a content-based deep learning method
3. Build a deep reinforcement learning model

It’s actually a beginner-friendly program; I learned the fundamentals of machine learning and how to use these techniques to build real-world AI applications.

It provides a broad introduction to modern machine learning, including

1. Supervised learning (multiple linear regression, logistic regression, neural networks, and decision trees)
2. Unsupervised learning (clustering, dimensionality reduction, recommender systems)
3. Some of the best practices used in Silicon Valley for artificial intelligence and machine learning innovation (evaluating and tuning models, taking a data-centric approach to improving performance, and more)

By the end of the Specialization, I had mastered key concepts and gained the practical know-how to quickly and powerfully apply machine learning to challenging real-world problems. If you’re looking to break into AI or build a career in machine learning, the new Machine Learning Specialization is the best place to start.

What’s next???

Wait until next article

Interested in my stories? Then head over to,

www.santhushajanana.medium.com -> where I share general tech stuff