Machine Learning, AI, and Deep Learning

Course Code: 0114

Overview
Schedule classes
What you'll learn
Outline
Prerequisites
Who should attend
Certification

Overview

Cognixia’s Machine Learning, Artificial Intelligence and Deep Learning training course covers the latest machine learning algorithms while also talking about the common threads that can be used in the future for learning a wide range of algorithms. The course is a complete package that will help learners build their skillsets and meet the demand of the ML-AI industry, going beyond the theoretical concepts of the technology like regression, clustering and classification, and discussing their applications as well.

Schedule Classes

Looking for more sessions of this class?

Course Delivery

This course is available in the following formats:

Live Classroom
Duration: 16 days

Live Virtual Classroom
Duration: 16 days

What You'll learn

Overview of Machine Learning, Artificial Intelligence and Deep learning
Supervised and unsupervised learning concepts and modelling
Solving business problems using Artificial Intelligence and Machine Learning
Various theoretical concepts and how they relate to the practical aspects of machine learning and AI
Application of concepts such as regression, clustering, classification, dimensional reduction and engine recommendation

Outline

Module 1: Introduction to Machine Learning

What is Machine Learning?
Machine Learning use-cases
Machine Learning process flow
Machine Learning categories

Module 2: Overview of Artificial Intelligence

What is AI?
Applications of AI
History of AI
Inductive Reasoning and Deductive Reasoning
What is included in AI? (Robotics, Agents and more)

Module 3: Introduction to R Programming

Installing and setting up – R and R Studio
Fundamentals: Vector, function, packages
Matrices: Building, naming dimensions, operations, visualizing, sub-setting
Data Frames: Building, merging, visualizing (ggplot2)
Hands-on/Lab exercises

Module 4: Data Extraction, Wrangling, and Exploration

Data analysis pipeline
What is Data Extraction?
Types of Data
Raw and processed data
Data wrangling
Exploratory data analysis
Visualization of data
Loading different types of datasets in R
Arranging the data
Plotting the graphs
Hands-on/Lab exercises

Module 5: Supervised and Unsupervised Learning

Supervised and unsupervised learning

Module 6: Regression

Simple linear regression
Multiple linear regression
Support vector machine
Hands-on/ Lab exercises

Module 7: Classification

Classification
What is a decision tree?
Algorithm for decision tree induction
Creating a perfect decision tree
Confusion matrix
What is a Random Forest?
What is a Navies Bayes?
Support vector machine: Classification
Hands-on/ Lab exercises

Module 8: Clustering

What is Clustering? (Including use-cases)
What is K-means Clustering?
What is C-means Clustering?
What is hierarchical Clustering?
Hands-on/ Lab exercises

Module 9: Overview of Dimensional Reduction

Feature extraction with PCA
Feature selection techniques

Module 10: Recommendation Engine

What are association rules and their use cases?
What are recommendation engines and how do they work?
Types of recommendation types
User-based recommendation
Item-based recommendation
Difference: User-based and item-based recommendation
Recommendation use-case
Hands-on/ Lab exercises

Module 11: Time Series

What is time series data?
Time series variables
Different components of time series data
Visualizing the data to identify time series components
Implementing ARIMA model for forecasting
Exponential smoothing models
Identifying different time series scenario based on which different Exponential Smoothing model can be applied
Implementing respective ETS model for forecasting
Hands-on/ Lab exercises

Module 12: Overview of Deep Learning

What is Deep Learning?
Biological Neural Networks
Understanding Artificial Neural Networks
Building an Artificial Neural Network
How does ANN work?
Important terminologies of ANN

Prerequisites

A sound understanding of programming languages such as R and Python will be beneficial, however, not mandatory.

Who Should Attend

Cognixia’s Machine Learning, AI, and Deep Learning course is highly recommended for:

Data scientists or a Machine Learning experts
Software and Application Developers
Business Analysts/Analytics professionals
Recent graduates looking to build a career in Artificial Intelligence
Technology enthusiasts with a sound understanding of Machine Learning
Software Architects or Software Engineers who wish to gain expertise in Machine Learning algorithms

Interested in this course? Let’s connect!

Certification

Participants will be awarded with an exclusive certificate upon successful completion of the program. Every learner is evaluated based on their attendance in the sessions, their scores in the course assessments, projects, etc. The certificate is recognized by organizations all over the world and lends huge credibility to your resume.