• Classroom Training   • Online Training   • Corporate Training  • Live Projects & Guidance 

Machine Learning & Artificial Intelligence

Courses Information

Learn foundational machine learning algorithms, starting with data cleaning and supervised models. Then, move on to exploring deep and unsupervised learning. At each step, get practical experience by applying your skills to code exercises and projects.

You will learn about training data, and how to use a set of data to discover potentially predictive relationships.

Curriculum
Module 1 - Introduction To Machine Learning And AI Concepts
  • What is Machine Learning?
  • Applications of Machine Learning
  • Concept of Artificial Intelligence
  • AI v/s ML v/s DL v/s DS
Module 2 - Foundation of ML / AI (Python)
  • Flow Controllers
  • List, Tuples and Dictionaries
  • Modules and Packages
  • Exception Handling
  • File Handling
  • Multi Threading
  • Python Database Connectivity
  • OOPs Concepts
  • Working with CSV, TSV and JSON files
  • Working with NumPy, Pandas and Matplotlib
Module 3 - Foundation of ML / AI (R Programming)
  • Commands and Syntax
  • Data Types
  • Vectors Arrays and Factors
  • Importing / Exporting Data
  • Packages and Libraries
  • working with Data Structure
  • Matrices
  • List and Data Frames
  • Control Structure
  • Functions in R
Module 4 - Descriptive Statistics
  • Data exploration (histograms, bar chart, box plot, line graph, scatter plot)
  • Other Measures: Quartile and Percentile
  • Measure of Central Tendency (Mean, Median and Mode)
Module 5 - Data Acquisition
  • Gather information from different sources
  • Open Data Sources
  • Using Available Data Sets
  • DDL and DML Statements
  • Relational Database access (queries) to process/access data
  • Joins and Set Operations
  • Working with Constraints
  • Implementation of Data integrity
Module 6 - Data Pre-processing and Preparation
  • Data Munging, Wrangling
  • Filtering data
  • Reshaping data
Module 7 - Supervised Learning
  • Students apply supervised learning input-output pairing techniques to a data set
  • Linear Regression
  • Multi Linear Regression
  • Decision Tree
  • Naive Bayes Classifier (NBC)
  • KNN - K Nearest Neighbors
  • Logistic Regression
Module 8 - Unsupervised Learning
  • Students utilize an unlabeled data set as well as algorithmic patterns to organize a data set into clusters.
  • Students assess the various clustering techniques on data sets.
  • Distance measures
  • Measures of quality of clustering
  • K-means clustering
Module 9 - Support Vector Machines
  • SVM for classification and regression problems.
Module 10 - Ensemble Techniques
  • Decision Trees
  • Bagging
  • Random Forests
Module 11 - Reinforcement Learning
  • Markov Decision
  • Random Forests
Module 12 - ARTIFICIAL INTELLIGENCE
  • Introduction to AI
  • AI: Application areas
  • NN basics
Module 13 - Convolution Neural Networks
  • Text classification
  • Image classification
Module 14 - Recurrent Neural Network
  • Building recurrent NN
  • Long Short-Term Memory
Module 15 - Natural Language Processing
  • Introduction to Natural Language Processing
  • Text Mining
  • Generations
  • Case Studies
Module 16 - Predictive Analysis
  • Logistics
  • Time Series (ARIMA)
  • Time Series Case Study
Module 17 - Deep Learning
  • Stacked auto-encoders and semi-supervised learning
  • Auto-encoders and unsupervised learning
Module 18 - TensorFlow
  • Getting started with TensorFlow
  • Deep learning and TF
  • Neural Structured Learning
  • Multilayer Perception Learning
  • TF Graphics
  • RNN
  • TF Visualization
  • Tf Optimizers
Module 19 – Computer Vision
  • Image Processing
  • Feature Detection
  • Video Analysis
  • Image Filtering
  • Drawing Shapes

Trending Courses