This Machine Learning Specialization course comprises of three sub courses as follows:
1. Supervised Machine Learning: Regression and Classification
2. Advanced Learning Algorithms
3. Unsupervised Learning, Recommenders, Reinforcement Learning
Though this specialization is a combination of three courses but each one of them can be accessed individually in both paid and free versions. The paid version includes a sharable certificate whereas the free version only provides the learning material in audit mode. One can also apply for financial aid to get full access including the certificate of completion. So now let’s look at the details of each course individually:
1. Supervised Machine Learning: Regression and Classification
About:
This is one out of three courses in the Machine Learning Specialization Course and is of beginner level. From this course, you will learn to build ML models in Python using popular ML libraries NumPy & scikit-learn. You will also learn to train supervised ML models for prediction & binary classification tasks, including linear regression & logistic regression.
Prerequisites:
As it’s a beginner-level course basic coding and advanced arithmetic & algebra concepts will also be taught in this course.
Duration:
Approximately takes 33 hours to complete with flexible deadlines.
Syllabus:
First Week: Introduction to Machine Learning.
The first module contains 20 videos for a total of 147 minutes and three practice exercises where you will be introduced to basic terminologies in machine learning.
Second Week: Regression with multiple input variables.
In the second week, you will extend linear regression to handle multiple input features and you will learn various methods for improving your model’s training and performance. Lastly, you will get to practice implementing linear regression in code. This contains 10 videos of 66 minutes and 2 practices.
Third Week: Classification.
Classification is another type of Supervised Learning where you will learn how to predict categories using the logistic regression model, how to handle Overfitting through Regularization, etc. along with a practice at the end. This lesson has 11 videos of 98 minutes, 1 reading, 5 quizzes, and four exercises.
2. Advanced Learning Algorithms
About:
This is the second course out of three courses in Machine Learning Specialization. The details about its sylllabus and prerequisites is hereunder.
Prerequisites:
Although it’s a begginner level course it is recommended that you must complete Supervised Learning: Regression and Classification Course before you start this course.
Duration:
Approximately 30 hours to complete with flexible deadlines.
Syllabus:
First Week: Neural Networks.
It has 17 videos of total 140 minutes which covers how to use Neural Networks for classification tasks, how to use TensorFlow framework to build Neural Network, how to code up your own Neural Network in Python from scratch and many more such stuffs.
Second Week: Neural Network Training.
You will learn to train your model in TensorFlow and to go beyond binary classification to multiclass classification in the second week. Moreover, you will learn about Adam Optimizer and other layer types besides the one you’ve seen so far. The lesson contains 12 videos of 88 minutes and 4 practice excercises.
Third Week: Advice for applying Machine Learning.
In the third week you’ll learn best practices for training and evaluating your learning algorithms. The 17 videos of total 177 minutes and 3 practice excercises covers a wide range of useful advice about the machine learning lifecycle, tuning your model and also improving your training data.
Fourth Week: Decision Trees.
Here you’ll learn about a practical and very commonly used learning algorithm – the decision tree and about it’s variations including random forests and boosted trees (XGBoost). This lesson has 13 videos of total 98 minutes, 1 reading, 4 quizzes, and 3 practices.
3. Unsupervised Learning, Recommenders, Reinforcement Learning
About:
The third and final course in the Machine Learning Specialization is Unsupervised Learning, Recommenders, Reinforcement Learning.
Prerequisites:
The course providers recommend you to complete Supervised Learning: Regression and Classification and Advanced Learning Algorithms of the series Machine Learning Specialization.
Syllabus:
Lastly, in the third course of the Machine Learning Specialization, you will use unsupervised learning techniques for unsupervised learning including clustering and anomaly detection, build recommender systems with a collaborative filtering approach and a content-based deep learning method and Build a deep reinforcement learning model.
For Machine Learning By Google Developers Click Here.
