Machine Learning Tutorials | Learn NLP with Python Online

technology

Machine Learning

Watch Demo

Rs. 1999 Rs. 599

Machine Learning and Natural Language Processing Tutorial

Created by Stanford and IIT alumni with work experience in Google and Microsoft, this Machine Learning tutorial teaches Sentiment Analysis, Recommendation Systems, Deep Learning Networks, and Computer Vision.

Loonycorn

13h:22m

Lifetime access

422 learners

4.7/5 (62)

Course Introduction:

Wondering ‘What is Machine Learning’?

“Machine Learning is a field of study that gives computers the ability to learn without being explicitly programmed” as defined by Arthur Samuel. Machine Learning probes around studying and constructing algorithms that can learn from and make predictions on data.

Wondering ‘What is Machine Learning’?

A team of experienced instructors from IIT Madras, IIM Ahmedabad, Stanford University have designed this course on Machine Learning. If Machine Learning is a car then this tutorial will teach you how to drive. This Machine Learning tutorial covers all the topics from the grassroots level. With the prime focus on establishing a strong foundation, this course has been divided into 5 modules:

Module 1 focuses on Machine Learning Basics and various aspects associated with it. In this module, you will learn about Association Detection, Anomaly Detection, Naive Bayes, K-nearest Neighbors, Linear and Logistics Regression, and Artificial Neural Networks.
Module 2 deals with Natural Language Processing with Python. The topics covered under this section are TF-IDF, Text Auto-summarization, Text classification with Naive Bayes and K-Nearest Neighbors, and Clustering with K-Means.
Module 3 focuses on Sentiment Analysis. This module deals with the usefulness of Sentiment Analysis, various approaches to solving – Rule-Based, ML-Based, Training, Feature Extraction, Sentiment Lexicons and Sentiment Analysis of Tweets with Python.
Module 4 gives you a detailed insight into Recommendation Engine. You will learn all about Content-based filtering, Collaborative Filtering, Neighborhood models, also known as Memory-based approaches, and Latent Factor Methods which are used to identify hidden factors that influence users from user history.
Module 5 covers a quick introduction to Computer Vision and Deep Learning Networks. Deep Learning Networks are the cutting edge solution for the handwritten digit recognition problems in computer vision. You will know how to identifying handwritten digits using the MNIST database and to feature extraction from images. You will learn about the concept of Perceptron.

Less

Course Objectives

The following are the few advantages in taking up this Machine Learning Tutorial:

Students will be able to spot situations where Machine Learning can be used, and deploy the appropriate solutions.
Discover various real life Machine Learning Applications.
Hundreds of lines of source code with comments are provided in the course, which can be directly used to implement Natural Language Processing and Machine Learning for text summarization, text classification in Python.
Product managers and executives will learn to intelligently converse with their data science counterparts, without being constrained by it.
NOTE: The coding language used in this tutorial is Python 2.7.

Pre-requisites:

If you are wondering whether you can enroll in this course without any pre-requisite, then the answer is definitely a YES! This course has no pre-requisites but knowledge of undergraduate level mathematics will help you understand the course better. Moreover, having a basic knowledge of Python would be an added advantage to run the source code used in the course.

Course Plan

Certificate of completion

1. Introduction

3mins

1 video

Introduction to the course 03:16

2. Jump right in : Machine learning for Spam detection

1hr 8mins

Watch Demo

4 videos

Machine Learning: Why should you jump on the bandwagon? 16:31

Plunging In – Machine Learning Approaches to Spam Detection 17:01

Spam Detection with Machine Learning Continued 17:04

Get the Lay of the Land : Types of Machine Learning Problems 17:27

3. Naive Bayes Classifier

1hr 1min

4 videos

Random Variables 20:11

Bayes Theorem 18:36

Naive Bayes Classifier 08:50

Naive Bayes Classifier : An example 14:04

4. K-Nearest Neighbors

27mins

2 videos

K-Nearest Neighbors 13:09

K-Nearest Neighbors : A few wrinkles 14:47

5. Support Vector Machines

24mins

Watch Demo

2 videos

Support Vector Machines: Introduction 08:16

Support Vector Machines : Maximum Margin Hyperplane and Kernel Trick 16:23

6. Clustering as a form Unsupervised learning

32mins

2 videos

Clustering : Introduction 19:08

Clustering : K-Means and DBSCAN 13:43

7. Association Detection

9mins

1 video

Association Rules Learning 09:13

8. Association Detection

29mins

Watch Demo

2 videos

Dimensionality Reduction 10:22

Principal Component Analysis 18:54

9. Artificial Neural Networks

11mins

1 video

Artificial Neural Networks I: Perceptron introduced 11:18

10. Regression as a form of supervised learning

24mins

2 videos

Regression Introduced : Linear and Logistic Regression 13:54

Bias Variance Trade-off 10:14

11. Natural Language Processing and Python

3hrs 28mins

Watch Demo

16 videos

Natural Language Processing with NLTK 07:26

Natural Language Processing with NLTK – See it in action 14:14

Web Scraping with BeautifulSoup 18:09

A Serious NLP Application : Text Auto Summarization using Python 11:34

Python Drill : Autosummarize News Articles I 18:34

Python Drill : Autosummarize News Articles II 11:28

Python Drill : Autosummarize News Articles III 10:24

Put it to work : News Article Classification using K-Nearest Neighbors 19:29

Put it to work : News Article Classification using Naive Bayes Classifier 19:25

Python Drill : Scraping News Websites 15:46

Python Drill : Feature Extraction with NLTK 17:43

Python Drill : Classification with KNN 03:44

Python Drill : Classification with Naive Bayes 07:43

Document Distance using TF-IDF 11:04

Put it to work : News Article Clustering with K-Means and TF-IDF 14:32

Python Drill : Clustering with K Means 06:54

12. Sentiment Analysis

2hrs 32mins

10 videos

A Sneak Peek at what’s coming up 02:36

Sentiment Analysis – What’s all the fuss about? 17:17

ML Solutions for Sentiment Analysis – the devil is in the details 19:57

Sentiment Lexicons ( with an introduction to WordNet and SentiWordNet) 18:49

Regular Expressions 17:54

Regular Expressions in Python 05:41

Put it to work : Twitter Sentiment Analysis 17:48

Twitter Sentiment Analysis – Work the API 20:00

Twitter Sentiment Analysis – Regular Expressions for Preprocessing 12:24

Twitter Sentiment Analysis – Naive Bayes, SVM and Sentiwordnet 19:41

13. Decision Trees

1hr 48mins

Watch Demo

7 videos

Planting the seed – What are Decision Trees? 17:01

Growing the Tree – Decision Tree Learning 18:03

Branching out – Information Gain 18:51

Decision Tree Algorithms 07:50

Titanic : Decision Trees predict Survival (Kaggle) – I 19:22

Titanic : Decision Trees predict Survival (Kaggle) – II 14:16

Titanic : Decision Trees predict Survival (Kaggle) – III 13:00

14. A Few Useful Things to Know About Overfitting

1hr 31mins

6 videos

Overfitting – the bane of Machine Learning 19:04

Overfitting Continued 11:20

Cross Validation 18:55

Simplicity is a virtue – Regularization 07:18

The Wisdom of Crowds – Ensemble Learning 16:39

Ensemble Learning continued – Bagging, Boosting and Stacking 18:03

15. Random Forests

32mins

2 videos

Random Forests – Much more than trees 12:28

Back on the Titanic – Cross Validation and Random Forests 20:03

16. Recommendation Systems

2hrs 18mins

Watch Demo

10 videos

What do Amazon and Netflix have in common? 16:44

Recommendation Engines – A look inside 10:45

What are you made of? – Content-Based Filtering 13:36

With a little help from friends – Collaborative Filtering 10:27

A Neighbourhood Model for Collaborative Filtering 17:51

Top Picks for You! – Recommendations with Neighbourhood Models 09:42

Discover the Underlying Truth – Latent Factor Collaborative Filtering 20:13

Latent Factor Collaborative Filtering contd. 12:09

Gray Sheep and Shillings – Challenges with Collaborative Filtering 08:12

The Apriori Algorithm for Association Rules 18:32

17. Recommendation Systems in Python

1hr 47mins

8 videos

Back to Basics : Numpy in Python 18:06

Back to Basics : Numpy and Scipy in Python 14:19

Movielens and Pandas 16:45

Code Along – What’s my favorite movie? – Data Analysis with Pandas 06:19

Code Along – Movie Recommendation with Nearest Neighbour CF 18:10

Code Along – Top Movie Picks (Nearest Neighbour CF) 06:16

Code Along – Movie Recommendations with Matrix Factorization 17:56

Code Along – Association Rules with the Apriori Algorithm 09:51

18. A Taste of Deep Learning and Computer Vision

1hr 29mins

6 videos

Computer Vision: An Introduction 18:08

Perceptron Revisited 16:00

Deep Learning Networks Introduced 17:01

Code Along – Handwritten Digit Recognition -I 14:30

Code Along – Handwritten Digit Recognition – II 17:36

Code Along – Handwritten Digit Recognition – III 06:01

Meet the Author

Loonycorn

4 Alumni of Stanford, IIM-A, IITs and Google, Microsoft, Flipkart

Loonycorn is a team of 4 people who graduated from reputed top universities. Janani Ravi, Vitthal Srinivasan, Swetha Kolalapudi and Navdeep Singh have spent years (decades, actually) working in the Tech sector across the world.

Janani: Graduated from Stanford and has worked for 7 years at Google (New York, Singapore). She also worked at Flipkart and Microsoft.

Vitthal: Studied at Stanford; worked at Google (Singapore), Flipkart, Credit Suisse, and INSEAD.

Swetha: An IIM Ahmedabad and IIT Madras alumnus having experience of working in Flipkart.

Navdeep: An IIT Guwahati alumnus and Longtime Flipkart employee.

More from Loonycorn

Job Seeker’s Guide To Cracking the Technical Interview

Rs. 1499

Complete guide for Quants Trading using Machine Learning

Rs. 1999 Rs. 599 70% off

A Complete tutorial on Python Programming

Rs. 1999 Rs. 599 70% off

Understanding Decision Trees and Random Forests

Rs. 799 Rs. 499 38% off

Ratings and Reviews

4.7/5

ABENAV

Superb Course

This course is designed for Beginners but as the course progresses ur doing some serious stuff with Python! Kudos to the team for bringing in such a wonderful course! i will definitely reccomend this course to newbies who are keen to learn ML and NLP 🙂

MANUKUMAR

content is good, but streaming!

Content of the course really good, I am enjoying. But I can’t see vedio steaming properly, it is taking too much of time to buffer. The problem is with only this website, I can watch all YouTube videos without problem.

RHEA SHARMA

The Best Online Course for Machine Learning!

This is one of the best online tutorial i have come across. Janani is amazing. I have never learnt NLP and ML in such a simplified Manner. Plus the certification! Great Package! Do not think twice, just buy!

PANKAJ RANJAN

Great Visuals and Examples

I loved the way the instructor simplifies everything. The course has good visuals to make it easy to understand. This is one of the best content I have come across online. Totally worth it!

Machine Learning Tutorials | Learn NLP with Python Online

Rs. 1999 Rs. 599

Machine Learning and Natural Language Processing Tutorial

Created by Stanford and IIT alumni with work experience in Google and Microsoft, this Machine Learning tutorial teaches Sentiment Analysis, Recommendation Systems, Deep Learning Networks, and Computer Vision.

Meet the Author

Loonycorn

4 Alumni of Stanford, IIM-A, IITs and Google, Microsoft, Flipkart

More from Loonycorn

You may also like