# AI-ML Track

Artificial Intelligence and Machine Learning are among the most exciting fields in the industry right now. There is a very high demand for AI and ML professionals in the industry, but it is crucial to have the relevant skills, exposure and academic credentials to be able to capitalise on these opportunities. This program would enable candidates to make this transition to high growth careers in AI and ML field.

Includes:

• 36 hours of lecture Videos
• 532 hands-on practice exercises
• 468 Assessment exercises
• 158 code analysis exercises
• 4320 knowledge based questions
• 24 Live connect sessions
(Master classes)
+91 95669 33778

### Linear Algebra for Machine Learning – The Easy Way

This course helps you to understand the vectors in different dimensions and their linear transformation to some other domain, matrix theory and various properties of matrices and its transformations, Eigenvalues and Eigenvectors and their role in dimensionality reduction and the applications of linear algebra for AI and ML.

COURSE OBJECTIVES

Upon successful completion of the course, the learner will be able to :
• Master the various concepts in Linear Algebra.
• Learn how linear algebra plays an important role in reducing the complexity of the data processing in AI and ML algorithms.

## Course Content

### Vector spaces, Linear Transformations

In this topic, you will learn about the multidimensional vector space and its various representations. You will also understand the transformations between different domains.

• 1 Video
• 3 hours
• 65 Problems

### Subspaces, Span and Basis

In this topic, you will learn about Subspaces, span and Basis of a vector and how it reduces the complexity of representing the vectors.

• 1 Video
• 3 hours
• 65 Problems

### Matrix Theory

In this topic, you will learn about Grouping multiple vectors to form matrices and various types of matrices and its properties.

• 1 Video
• 3 hours
• 65 Problems

### Eigenvalues and Eigenvectors

In this topic, you will learn about how to derive Eigenvalues and Eigenvectors from the matrices and how they are used to reduce dimension.

• 1 Video
• 3 hours
• 65 Problems

### Inner-Product Spaces, Linear Algebra Applications for ML & AI

In this topic, you will learn about how to find the inner product of the matrix and its properties and short cuts to find it. You will also learn how Linear Algebra is used in the field of AI and ML.

• 1 Video
• 10 hours
• 92 Problems

### Probability for Machine Learning – The Easiest Way of Learning

In this course, you will learn about probability, different types of distribution and density functions, joint distributions and density functions and the different moments, parameter estimation and minimum risk estimation and the application of probability in the field of Data Science and ML.

COURSE OBJECTIVES

Upon successful completion of the course, the learner will be able to :
• Master the various concepts in Probability.
• Learn how Probability plays an important role in prediction and decision making in AI and ML algorithms.

## Course Content

### Probability of Events, Conditional Probabilities, Random variables and Random Processes

In this topic, you will learn about introduction to probability and the various terms associated with it. You will understand conditional probability by solving various problems in random variables and finding probabilities for random processes.

• 1 Video
• 3 hours
• 65 Problems

### Probability Distributions and Densities, Choosing and Applying Probability Densities

In this topic, you will learn about different probability distribution and density functions. You will learn about choosing and applying appropriate Probability Densities functions.

• 1 Video
• 3 hours
• 65 Problems

### Joint Distributions and Densities, Moments

In this topic, you will learn about joint distributions and Densities.You will also understand the various order of Moments.

• 1 Video
• 3 hours
• 65 Problems

### Parameter Estimations, Minimum Risk Estimations

In this topic, you will learn about choosing the correct parameter through parameter estimation and risk estimation for a given process.

• 1 Video
• 3 hours
• 65 Problems

### Applications in Data Science and ML

In this topic, you will learn about the application of Probability in the field of Data Science and ML.

• 1 Video
• 10 hours
• 92 Problems

### Statistics For Decision Making

In this course, you will learn about Bayes Theorem and decision making using Bayes Theorem, designing and customizing the Bayesian theorem to work with more than 2 features and cost estimation for errors.

COURSE OBJECTIVES

Upon successful completion of the course, the learner will be able to :
• Master the various concepts in Statistical Decision Making.
• Learn how Statistical Decision Making plays an important role in prediction and decision making in AI and ML algorithms.

## Course Content

### Bayes Theorem and Bayesian Decision Making

In this topic, you will learn about how conditional probability is used to derive Bayes Theorem and decision making using Bayes Theorem.

• 1 Video
• 7 hours
• 80 Problems

### Multiple Features and Multivariate Statistics

In this topic, you will learn about designing and customizing the Bayesian theorem to work with more than 2 features.

• 1 Video
• 7 hours
• 80 Problems

### Decision Regions and Decision Boundaries, Multi-Dimensional Decision Boundaries

In this topic, you will learn about how to create decision region classification by deriving Decision Boundaries and multidimensional Decision Boundaries.

• 1 Video
• 7 hours
• 80 Problems

### Cost of Errors and Estimation of Errors, Regression

In this topic, you will learn about how to calculate the cost of error and how to do an estimation of errors.

• 1 Video
• 7 hours
• 80 Problems

### Applications of Statistical Modelling in ML

In this topic, you will learn about the application of Statistical Decision Making in the field of AI and ML.

• 1 Video
• 7 hours
• 80 Problems

### The Mathematics of Machine Learning

In this course, you will learn about the basics of calculus, multivariable calculus and how to apply calculus on complex function using chain rule and optimization and regression using Calculus.

COURSE OBJECTIVES

Upon successful completion of the course, the learner will be able to :
• Master the various concepts in Calculus.
• Learn how Calculus plays an important role in AI and ML algorithms.

## Course Content

### Basics of Calculus

In this topic, you will learn about Introduction to calculus and Introduction to building framework for modeling systems in which there is a change.

• 1 Video
• 3 hours
• 65 Problems

### Multivariate calculus

In this topic, you will learn about performing integration and differentiation with respect to multiple variables.

• 1 Video
• 7 hours
• 80 Problems

### Multivariate chain rule

In this topic, you will learn about constructing complicated functions by substitution and differentiating such complicated functions using the chain rule.

• 1 Video
• 7 hours
• 80 Problems

### Calculus for Optimization

In this topic, you will learn about how to identify the quantity to optimize in an ML algorithm using Calculus.

• 1 Video
• 7 hours
• 80 Problems

### Calculus in Regression

In this topic, you will learn about how to build regression models using Calculus.

• 1 Video
• 7 hours
• 80 Problems

### Learn Features and Dimensions : The Complete Developer Guide

In this course, you will learn about different pattern recognition systems, data preprocessing, dimensionality reduction and component analysis and discriminants.

COURSE OBJECTIVES

Upon successful completion of the course, the learner will be able to :
• Master the various concepts in Features and Dimensions.
• Learn how Features and Dimensions plays an important role in AI and ML algorithms.

## Course Content

### Pattern Recognition Systems

In this topic, you will learn about Different Pattern Recognition Systems and Different steps to follow Pattern Recognition, like, Sensing, Segmentation, Grouping, Feature Extraction, Classification and Post Processing.

• 1 Video
• 7 hours
• 80 Problems

### Design Cycle

In this topic, you will learn about the design cycle in Pattern Recognition and the different states in the design cycle like, Data Collection, Feature Choice, Model Choice, Training, Evaluation and Complexity analysis.

• 1 Video
• 7 hours
• 80 Problems

### Data Preprocessing

In this topic, you will learn about the different data processing techniques, which involve, Descriptive Data Summarization, Data Cleaning, Data Integration and Transformation, and Data Reduction.

• 1 Video
• 10 hours
• 90 Problems

### Problems of Dimensionality

In this topic, you will learn about the various problems that arises due to high dimensional data, with respect to Accuracy and Complexity and how an increase in the number of features lead to Overfitting of the Component.

• 1 Video
• 7 hours
• 80 Problems

### Component Analysis and Discriminants

In this topic, you will learn about the various Component Analysis like, PCA and the various Discriminant Analysis line, LDA and MDA.

• 1 Video
• 7 hours
• 80 Problems

### Machine Learning Techniques – Learning Made Easy

In this course, you will learn about various branches in Machine learning, Artificial Neural Networks, classification and clustering and Deep Learning.

COURSE OBJECTIVES

Upon successful completion of the course, the learner will be able to :
• Master the various concepts in Machine Learning Techniques.
• Learn how Machine Learning Techniques plays an important role in AI and ML algorithms.

## Course Content

### Similarity and Metric Learning

In this topic, you will learn about finding the similarity between two features using distance metrics.

• 1 Video
• 7 hours
• 80 Problems

### Association rule learning

In this topic, you will learn about discovering interesting relations between variables in large databases using Association Rule Learning.

• 1 Video
• 7 hours
• 80 Problems

### Decision tree learning

In this topic, you will learn about decision making using a decision support tool that uses a tree-like model of decisions.

• 1 Video
• 7 hours
• 80 Problems

### Artificial Neural Networks

In this topic, you will learn about replicating the way that the humans learn using Artificial Neural Networks.

• 1 Video
• 7 hours
• 80 Problems

### Support vector machines

In this topic, you will learn about performing classification by finding the hyperplane that differentiate the two classes using Support Vector Machines.

• 1 Video
• 7 hours
• 80 Problems

### Bayesian networks

In this topic, you will learn about building probabilistic directed acyclic graphical model(network) to compute probability and classify.

• 1 Video
• 7 hours
• 80 Problems

### Clustering Algorithms

In this topic, you will learn about various clustering algorithms that group set of objects in such a way that objects in the same group are more similar to each other.

• 1 Video
• 7 hours
• 80 Problems

### Representation learning, Reinforcement learning, Sparse dictionary learning

In this topic, you will learn about systems that automatically discover the representations needed for feature detection or classification from raw data through Representation Learning and automatically performing some actions and seeing the results to learn how to behave in a environment using Reinforcement Learning.

• 1 Video
• 7 hours
• 80 Problems

### Deep Learning - Back Propagation

In this topic, you will learn about constructing a network of neurons, training them by adjusting their weights using Back Propagation.

• 1 Video
• 7 hours
• 80 Problems

### Deep Learning - Convolution Network

In this topic, you will learn about classifying images and perform object recognition using Deep Convolution Network.

• 1 Video
• 7 hours
• 80 Problems

### Deep Learning - Reinforcement Model

In this topic, you will learn about combining feedforward neural networks with temporal-difference learning to train a program to learn to play certain board games like backgammon

• 1 Video
• 7 hours
• 80 Problems

### Knowledge Discovery Process Models: From Traditional to Agile Modeling

In this course, you will learn about classification and clustering, analyzing data for patterns, or co-occurrence using Association Rules, trend analysis using Time series analysis and sequence discovery and deriving information through summarization techniques.

COURSE OBJECTIVES

Upon successful completion of the course, the learner will be able to :
• Master the various concepts in Knowledge Discovery Models.
• Learn how Knowledge Discovery Models plays an important role in AI and ML algorithms.

## Course Content

### Classification

In this topic, you will learn about various classification algorithms and their implementations.

• 1 Video
• 7 hours
• 80 Problems

### Clustering

In this topic, you will learn about various clustering algorithms that group set of objects in such a way that objects in the same group are more similar to each other.

• 1 Video
• 7 hours
• 80 Problems

### Association Rules

In this topic, you will learn about analyzing data for patterns, or co-occurrence, in a database using Association Rule.

• 1 Video
• 7 hours
• 80 Problems

### Regression, Prediction

In this topic, you will learn about forming regression line for the given data and Predicting the outcome for a given input using the previously formed regression relation.

• 1 Video
• 7 hours
• 80 Problems

### Time Series Analysis

In this topic, you will learn about how to perform trend analysis using a statistical technique called Time Series Analysis.

• 1 Video
• 7 hours
• 80 Problems

### Sequence Discovery

In this topic, you will learn about finding statistically relevant patterns between data examples using Sequence Discovery.

• 1 Video
• 7 hours
• 80 Problems

### Summarization

In this topic, you will learn about deriving information from the data using various summarization techniques.

• 1 Video
• 7 hours
• 80 Problems

In this course, you will learn about Knowledge discovery theories-review, Data analysis on different domains and Spatial, Temporal, and Multimedia Databases and their analytics.

COURSE OBJECTIVES

Upon successful completion of the course, the learner will be able to :
• Learn various concepts in Advancement in Knowledge Discovery.
• Learn how Advancement in Knowledge Discovery plays an important role in AI and ML algorithms.

## Course Content

### Review of Knowledge discovery theories

In this topic, you will have a review on Knowledge discovery theories, models and systems, Deep learning and deep analytics, Scalable analysis and learning Knowledge discovery theories, models and systems.

• 1 Video
• 7 hours
• 80 Problems

### Data analysis on different domains

In this topic, you will learn about Cloud computing and service data analysis, High performance computing for data analytics, VLDB Administration and Manageability, Tuning, Benchmarking and Performance Measurement.

• 1 Video
• 7 hours
• 80 Problems

### Spatial, Temporal, and Multimedia Databases, Multimedia/stream/text/visual analytics

In this topic, you will learn about Spatial, Temporal, and Multimedia Databases and Multimedia/stream/text/visual analytics.

• 1 Video
• 10 hours
• 90 Problems

### Artificial Intelligence – Learn How To Build an AI

In this course, you will learn about simulating human intelligence processes in machines, properly representing knowledge for reasoning and NLP, Social Intelligence, motion and manipulation according to situations.

COURSE OBJECTIVES

Upon successful completion of the course, the learner will be able to :
• Master the various concepts in Artificial Intelligence.
• Learn how Artificial Intelligence plays an important role in AI and ML algorithms.

## Course Content

### Introduction to Artificial Intelligence

In this topic, you will learn about introduction to how to simulate human intelligence processes in machines.

• 1 Video
• 3 hours
• 65 Problems

### Problem Solving in AI

In this topic, you will learn about Problem solving in AI that encompasses a number of techniques known as algorithms, heuristics, root cause analysis, etc.

• 1 Video
• 7 hours
• 80 Problems

### Knowledge and Reasoning

In this topic, you will learn about incorporating the findings from logic to automate various kinds of reasoning, such as the application of rules or the relations of sets and subsets.

• 1 Video
• 7 hours
• 80 Problems

### Knowledge Representation

In this topic, you will learn about representing knowledge in order to design formalisms that will make complex systems easier to design and build.

• 1 Video
• 7 hours
• 80 Problems

### Planning

In this topic, you will learn about performing decision making tasks to achieve a specific goal by planning.

• 1 Video
• 7 hours
• 80 Problems

### Uncertain Knowledge and Reasoning

In this topic, you will learn about modelling and processing uncertain knowledge about an environment and correspondingly acting on it.

• 1 Video
• 7 hours
• 80 Problems

### Learning

In this topic, you will learn about learning agents that learn something and try something different and learning from the previous experiences.

• 1 Video
• 7 hours
• 80 Problems

### Communicating, Perceiving, and Acting

In this topic, you will learn about how to model neurons that communicate with each other, perceive knowledge and act as per the previous experience.

• 1 Video
• 7 hours
• 80 Problems

### Natural language processing

In this topic, you will learn about programming computers to process and analyze human (natural) languages through Natural Language Processing.

• 1 Video
• 7 hours
• 80 Problems

### Social intelligence, Motion and manipulation

In this topic, you will learn about programming machines(robots) that can move and manipulate(eg., car assembling) and programming social intelligence to machine to coordinate with the society.

• 1 Video
• 7 hours
• 80 Problems

### Case Studies

Artificial Intelligence is the development of computer systems to be able to perform tasks normally requiring human intelligence and Machine learning is an application that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. In this course you will learn how to apply these topic in real time, by applying it in various case studies.

COURSE OBJECTIVES

Upon successful completion of the course, the learner will be able to :
• Master the concepts in Artificial Intelligence and Machine Learning by applying it the realtime data through lot of case studies.

## Course Content

### Image Analytics

In this topic, you will learn about Image analysis, which is the ability of computers to recognize attributes within an image and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems

### Video Analytics

In this topic, you will learn about Video content analysis, which is the capability of automatically analyzing video to detect and determine temporal and spatial events and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems

### Text Analytics

In this topic, you will learn about Text analytics, which is the process of deriving high-quality information from text and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems

### AI and Big Data

In this topic, you will learn about Artificial Intelligence and Big Data and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems

### Forecasting

In this topic, you will learn about Forecasting, which is the process of making predictions of the future based on past and present data and most commonly by analysis of trends and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems

### Customer Experience

In this topic, you will learn about enhancing the Customer Experience using Machine Learning and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems

### Supply Chain

In this topic, you will learn about applying Artificial Intelligence in Supply Chain and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems

### Behavioral Analytics

In this topic, you will learn about Behavioral analytics, which is an area of data analytics that focuses on providing insight into the actions of people and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems

### AI in Health Care

In this topic, you will learn about applying Artificial Intelligence in Health Care and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems

### Personality Analytics

In this topic, you will learn about applying Artificial Intelligence in Personality Analytics and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems

### Consumer Packaged Goods

In this topic, you will learn about applying Artificial Intelligence in Consumer Packeged goods like food, beverages, cosmetics and cleaning products and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems

### Financial Services

In this topic, you will learn about applying Artificial Intelligence in Consumer Packeged goods like food, beverages, cosmetics and cleaning products and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems

### Healthcare & Life Sciences

In this topic, you will learn about developing predictive models in Healthcare & Life Sciences and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems

### Insurance

In this topic, you will learn about applying Machine Learning in Insurance Market analysis and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems

### Technology, Media, Telecom

"In this topic, you will learn about applying Machine Learning in Technology, Media, Telecom implement the given case study step by step."

• 1 Video
• 4 hours
• 69 Problems

### Retail

In this topic, you will learn about applying Machine Learning in Retail analysis to forecast and make simple assumptions about customers and implement the given case study step by step.

• 1 Video
• 4 hours
• 69 Problems