Artificial Intelligence Training Program


According to the father of Artificial Intelligence, John McCarthy, it is The science and engineering of making intelligent machines, especially intelligent computer programs”.

Artificial Intelligence is a way of making a computer, a computer-controlled robot, or a software think intelligently, in a similar manner the intelligent humans think.

Course Outline:

Artificial Intelligence

  • Introduction to Artificial Intelligence (AI)
  • History of AI
  • Importance and other Philosophies about AI
  • General Approaches and Goals of AI
  • Components of AI
  • Working Domains/Companies/Products in the Current Market
  • Programming Languages Used for AI
  • Python Programming

Python programming

  • Basic of python and why python for machine learning
  • Installation of software on different OS.
  • Understanding basic syntax with data types
  • Number, String, List, Tuple, Dictionary
  • Extracting data from a file
  • Committing your code to GIT

More about python programming

  • Conditional statement and loops
  • Function and modules
  • File handling
  • Creating own modules/library
  • Web scraping with urllib2
  • Grabbing system information from Popen and os library
  • Scanning Network IP & MAC address with loop

Libraries Used

  • Introduction to Numpy & Matplotlib
  • Managing array with numpy
  • Multidimensional array with numpy
  • Unit matrix handling & creating
  • Deleting indexes from the matrix
  • Deep dive with Matplotlib
  • Drawing general purpose graphs
  • Graphs with mathematics

Machine learning techniques

  • Types of learning
  • Advice of applying machine learning
  • Machine learning System Design
  • Decision Tree Classifier
  • Training your machine with real-time datasets
  • Deep dive with UCI
  • Lab session for loading data from different APIs
  • Detecting data from numpy and converting for training and
  • testing data
  • Exercise with ML and others framework
  • Introduction to iris datasets
  • Understanding iris datasets
  • Modifying and loading with scikit-learn
  • Separating data with numpy
  • Training classifier
  • Algo data process view
  • Decision Tree understanding

Linear Regression

  • Using House Price Prediction
  • Simple Linear Regression
  • Polynomial Linear Regression
  • Cost Function of Linear Regression
  • Understanding linear regression using matrix

Logistic Regression

  • Using Iris dataset to understand logistic regression
  • The concept of linearly separable data
  • Cost Function & Mathematical Foundation
  • Using Iris dataset to understand logistic regression
  • The concept of linearly separable data
  • Cost Function & Mathematical Foundation

Neural Networks analysis

  • Introduction to Neural Network
  • Understanding neural networks
  • Data learning and machine predictions
  • Neural networks real understanding
  • Neural network implementation with real datasets
  • Natural Language Processing
  • Tokenizing text data
  • Converting words to their base forms using stemming
  • Converting words to their base forms using lemmatization
  • Dividing text data into chunks
  • Extracting the frequency of terms using a Bag of Words model
  • Building a category predictor
  • Constructing a gender identifier
  • Building a sentiment analyzer
  • Topic modelling using Latent Dirichlet Allocation

More About ANN

  • Perception
  • Back Propagation/Training Algo’s
  • Convolutional & Recurrent and Artificial Neural Networks
  • Deep Neural Network

Natural Language Processing (NLP)

  • Introduction to NLP
  • Word Representation Model
  • Sentence Classification
  • Language Modeling

Project:- Building AI based ChatBots

Feature Engineering

  • Categorical Features
  • Text Features
  • Image Features
  • Derived Features
  • Imputation of Missing Data
  • Feature Pipelines – Transformer & Estimator

Naive Bayes Classification

  • Bayesian Classification
  • Gaussian Naive Bayes
  • Multinomial Naive Bayes
  • When to Use Naive Bayes
  • Application: Identify category from text

K-Means Clustering

  • Introducing k-Means
  • The understanding cost function for unsupervised algorithms
  • Elbow rule to decide the number of clusters
  • Application: Image compression
  • Application: Detection of number of characters in Arabic

Decision Trees and Random Forests

  • Understanding Decision trees
  • Printing tree
  • Motivating Random Forests: Decision Trees
  • Ensembles of Estimators: Random Forests
  • Random Forest Regression
  • Application: Random Forest for Classifying Digits
  • Other Boosting techniques – AdaBoost, Gradient Tree Boosting

Genetic Algorithms

  • Fundamental concepts in genetic algorithms
  • Generating a bit pattern with predefined parameters
  • Visualising the evolution
  • Solving the symbol regression problem
  • Building an intelligent robot controller

Project: Handwriting recognition with Neural Networks

Building Recommender Systems

  • Extracting the nearest neighbors
  • Building a K-Nearest Neighbors classifier
  • Computing similarity scores
  • Finding similar users using collaborative filtering
  • Building a movie recommendation system


  • Understanding BeautifulSoup
  • Scraping for text, images
  • Searching for Links, Data
  • web data extraction: extracting data from websites.

Image Processing and ML

  • Introduction to Image Processing and
  • How image search is going to work
  • Taking pictures with python for image processing
  • Loading and registering images
  • Object detection
WhatsApp chat