Self Paced Learning

Lifetime access to self-paced learning

Instructor Led Online Classes

Half-day workshop to get you started + 90 day access to self-paced videos

Apr 25 Tue

Batch 1 (Tuesday)

Apr 25 to Apr 25

Apr
  • 25 Tue

    Session 1

    04:00 PM to 08:00 PM (EDT)


Need Custom Training for Your Team?

Get Quote

Call Us

Toll Free (844) 397-3739

Inquire About This Course

Instructor

Thumb fb3ddbc2 8896 4df9 a4a8 da35efd32065

Hadi Harb

Hadi has more than 15 years of experience in the development and management of Artificial Intelligence and Audio Signal Processing projects. Hadi holds an MEng in electrical-electronic engineering. He earned his MSc and PhD both in computer science from the Institut National des Sciences Appliquées INSA Lyon, and the Ecole Centrale de Lyon respectively.

Marketing Analytics: Text Analysis & Recommendation Systems

Instructor: Hadi Harb

AI from a practical perspective to help you solve your day-to-day problems

  • Enables students to conduct text analysis, clustering, classification and handle recommender systems while implementing learnings in professional settings.
  • Instructor: Researched and taught Artificial Intelligence for 15 years. He also founded and operated a successful Artificial Intelligence startup in France. 

Course Description

This course introduces the Artificial Intelligence subject from a practical point of view. The objectives are: 1- To give ideas on how to use AI techniques to solve day-to-day problems 2- To provide a basic description of some AI techniques 3- To introduce some open-source frameworks that can be used immediately to build AI applications

What am I going to get from this course?
Learn how to:
  • Use regular expressions to find and replace patterns in text.
  • Use Stanford NLP framework for part-of-speech tagging and named entity recognition.
  • Use GloVe tool to estimate semantic similarity between words.
  • Use TF-IDF weighting scheme in a search application.
  • Detect problems where clustering can be used.
  • Define supervised learning problems.
  • Use WEKA software to solve automatic classification problems.
  • Use WEKA software to generate rules for a recommender system.

Prerequisites and Target Audience

What will students need to know or do before starting this course?
  1. Bachelor's Degree in computer science
  2. Physics
  3. Maths
  4. Economy, or a related specialty is recommended.
Who should take this course? Who should not?
This course is adapted for:
  • A technical person willing to know how to use Artificial Intelligence techniques to solve his/her problems.
  • A management person willing to understand the practical applications of Artificial Intelligence in his/her business.
  • A technical or non-technical person wishing to start using existing frameworks for text analysis, clustering, automatic classification and recommender systems.
This course is not adapted for:
  • A technical person wishing to understand the algorithmic details so that he/she can implement Artificial Intelligence algorithms.
  • A technical person wishing to modify/improve existing Artificial Intelligence algorithms.

Curriculum

Module 1: Introduction
Lecture 1 Why This Course?
02:54
Module 2: Text Analysis
Lecture 2 Text Analysis
02:00

In this video you will learn about the reasons why text analysis is important. Typical applications of text analysis are listed: search applications, text classification, named entity recognition, and pattern search and replace applications.

Lecture 3 Regular Expressions - part 1
08:11

In this video you will be introduced to the regular expressions and how they can be used to find patterns in texts such as URLs, emails, dates, time ...

Lecture 4 Regular Expressions - part 2
11:00

In this video you will learn by example how to write regular expressions to: find email patterns, find date patterns and parse XML documents.

Lecture 5 Preprocessing Text
09:41

In this video you will learn about the typical pre-processing steps that are used in text analysis applications. You will learn about tokenization, tags stripping, stop-words elimination, part-of-speech tagging, and named entity recognition.

Lecture 6 Search: Information Retrieval - part 1
11:44

In this video you will be introduced to the information retrieval subject and you will learn about the vector space model.

Lecture 7 Search: Information Retrieval - part 2
16:04

In this video you will learn about TF-IDF (Term Frequency - Inverse Document Frequency) and its use in text information retrieval.

Lecture 8 Semantic Analysis - part 1
04:52

In this video you will learn about semantic analysis in text. You will be introduced to WordNet and learn about its use in enriching text analysis applications.

Lecture 9 Semantic Analysis - part 2
09:20

In this video you will learn about numerical vector representation of words (word embeddings). You will learn how this representation can be used to estimate semantic similarity or relatedness between words.

Lecture 10 Demo: Regular Expressions (RegExr)
10:45

In this video you will learn how www.regexr.com website can be used to find regular expressions that are shared by the community. It shows you also how to test your regular expressions live.

Lecture 11 Demo: Pre-processing (Stanford NLP)
04:13

In this video you will learn about the Standford NLP framework that can be used for text processing applications. The demo shows you how the framework can be used to extract part-of-speech tags and name entities from a text.

Lecture 12 Demo: Numerical Vector Representation of Words (GLOVE)
04:44

In this video you will learn about GloVe: a tool that lets you generate word embeddings. You will see how word embeddings can be used to estimate semantic similarity between words.

Module 3: Clustering
Lecture 13 Clustering
11:34

In this video you will learn about clustering and its applications such as: customer segmentation, fast search, and visualization.

Lecture 14 K-Means Clustering
07:40

In this video you will learn about the K-means clustering algorithm and its principle of operations.

Module 4: Classification
Lecture 15 Classification
13:34

In this video you will learn about automatic classification and its applications. You will learn how to define a supervised learning problem so that you can apply a machine learning algorithm to solve it.

Lecture 16 Decision Trees - part 1
11:19

In this video you will be introduced to the Decision Trees classifiers and learn about their principle of operations.

Lecture 17 Decision Trees - part 2
12:02

In this video you learn how a Decision Tree can be automatically generated to represent data and to classify data points.

Lecture 18 Naive Bayes & K-NN
12:35

In this video you will be introduced to the Naive Baye's and K-NN (K Nearest Neighbors) classifiers. You will learn when each classifier is more adapted to be used.

Lecture 19 Neural Networks
08:49

In this video you will be introduced to Neural Networks classifiers. You will learn about the principle of error back-propagation algorithm that is typically used to train Neural Networks.

Lecture 20 Demo: Classification (WEKA)
14:17

In this video you will be introduced to the WEKA software that can be used for classification, clustering and recommendation. You will learn how WEKA can be used in the case of two classification problems: cancer recurrence classification and text classification.

Module 5: Recommenders
Lecture 21 Recommenders
07:59

In this video you will be introduced to recommender systems. You will learn about association rules and their use in recommender systems.

Lecture 22 Demo: Association Rules (WEKA)
03:58

In this video you will learn how WEKA software can be used to generate association rules from transaction data. An example of how you would generate recommendation rules based on the analysis of super-market transactions data.

Reviews

4 Reviews

Empty user
Kamal K

December, 2016

Empty user
Martin R

May, 2017

A very informative course I ever came across. It can definitely help me solve many day-to-day problems, and enables to do text analysis, clustering, classification in professional settings and much more. It is a great experience to learn from a founder of a successful Artificial intelligence startup with fifteen years. It is easy to learn artificial intelligence from a practical perspective, AI techniques, and its basics, and open-source frameworks to build AI applications. The course provides value for the time and money invested in learning it. The video learning is a new experience for me and able to grasp.

Empty user
Bill S

May, 2017

With this excellent course I could learn using regular expressions, NLP framework estimate semantic similarities and use of weka software to solve automatic classification problem.

Empty user
Kevin H

May, 2017

A very beneficial excellent course as I could find.the instructor was precise in getting to very points in the course. Overall I satisfied in learning this course.

350