Artificial Intelligence Fundamentals

Course Description

Introduction:
In this basic course on Artificial Intelligence Fundamentals, participants will be provided an overview of AI, and explained on how it can be used for an effective and efficient decision making for an organization.

Initial Assessment: Participant’s Background

Assessment to understand the participant’s background to suit the course content. This assessment includes familiarity with AI concepts, programming language proficiency, and the frameworks of machine learnings.

Day 1 – AM

Topic	Content	Schedule
General Introduction	Introduction of Trainosys Courses Trainosys Offered Trainer’s Profile Course Expectancy Survey	08:00 AM – 08:30 AM
Artificial Intelligence	Introduction of Artificial Intelligence Weak Ai vs Strong AI Generative Models Artificial Intelligence Applications	08:31 AM – 09:30 AM
Break 10 mins
Artificial Intelligence Fundamentals	Introduction of Machine Learning How does ML work? Machine Learning vs Deep Learning vs Neural Network Machine Learning Platforms Machine Learning Use cases Machine Learning Fields (NLP, Geospatial, etc)	09:41 AM – 11:40 AM
Artificial Intelligence Fundamentals	AI Fundamentals Recap & Summary	11:41 AM – 12:00 PM
Lunch Break 1 hour (60 mins)

Day 1 – PM

Topic	Content	Schedule
Machine Learning	Validation of Required Libraries & Platforms to install Machine Learning vs Data Science Machine Learning Pipeline Data Science Pipeline	01:00 PM – 01:30 PM
Machine Learning Supervised Model Classification	Learning by Doing – Supervised Model – Classification Use Case 1 Data Preparation Data Cleaning Data Visualization Data Ingestion Data Transformation & Validation Feature Engineering Data Splitting	01:31 PM – 04:30 PM
Break 10 mins
Machine Learning Supervised Model Classification	Learning by Doing – Supervised Model – Classification Use Case 1 Model Building Choosing the Right Model Training Optimization Model Performance Evaluation Model Validation	04:41 PM – 05:00 PM
Machine Learning Supervised Model Classification	ML Supervised Model – Classification Part 1 Recap + Take Home Exercise + End-of-day Survey	05:01 PM – 05:30 PM

Day 2 – AM

Topic	Content	Schedule
Machine Learning Supervised Model Classification	Take Home Exercise Discussion	08:00 AM – 09:00 AM
Machine Learning Supervised Model Classification	Learning by Doing – Supervised Model – Classification Use Case 1 Exporting and Importing a model in .pkl or .sav	09:01 AM – 09:30 AM
Break 10 mins
Machine Learning Supervised Model Classification	ML Supervised Model – Classification Part 2 Recap	09:41 AM – 10:30 PM
Machine Learning Supervised Model Classification	Learning by Doing – Supervised Model – Regression Use Case 2 Data Preparation: Data Cleaning Data Visualization Data Integration	10:31 AM – 12:00 PM
Lunch Break 1 hour (60 mins)

Day 2 – PM

Topic	Content	Schedule
Machine Learning Supervised Model Regression	Learning by Doing – Supervised Model – Regression Use Case 2 Data Preparation: Data Transformation & Validation Feature Engineering Data Splitting	01:00 PM – 02:00 PM
Machine Learning Supervised Model Regression	Learning by Doing – Supervised Model – Regression Use Case 2 Model Building Choosing the Right Model Training Optimization Model Performance Evaluation Model Validation	02:00 PM – 04:00 PM
Break 10 mins
Machine Learning Supervised Model Regression	ML Supervised Model – Regression Use Case 2 Exporting and Importing a Model in .pkl or .sav	04:00 PM – 04:30 PM
Machine Learning Supervised Model Regression	ML Supervised Model – Regression Recap + Take Home Exercise + End-of-day Survey	04:31 AM – 05:15 PM

Day 3 – AM

Topic	Content	Schedule
Machine Learning Supervised Model Regression	Take Home Exercise Discussion	08:00 AM – 09:00 AM
Machine Learning Unsupervised Model Clustering	Learning by Doing – Unsupervised Model – Clustering Use Case 3 Data Preparation: Data Transformation & Validation Feature Engineering Data Splitting	09:01 AM – 10:00 AM
Break 10 mins
Machine Learning Unsupervised Model Clustering	Learning by Doing – Unsupervised Model – Clustering Use Case 3 Model Building: Choosing the Right Model/Algorithm of Clustering Training Optimization Model Performance Evaluation Model Validation	10:01 AM – 11:30 AM
Machine Learning Unsupervised Model Clustering	Learning by Doing – Unsupervised Model – Clustering Use Case 3 Exporting and Importing a Model in .pkl or .sav	11:31 AM – 12:00 PM
Lunch Break 1 hour (60 mins)

Day 3 – PM

Topic	Content	Schedule
Deep Learning	What is Deep Learning? Deep Learning vs Machine Learning Deep Learning vs Neural Network How does Deep Learning Work?	01:00 PM – 01:30 PM
Deep Learning	One Learning Applications Deep Learning Use Cases Pros & Cons of Deep Learning Deep Learning Platforms	01:31 PM – 02:00 PM
Break 10 mins
Deep Learning	Learning by Doing – Deep Learning Model: Use Case 4 Data Preparation: Data Transformation & Validation Feature Engineering Data Splitting	02:11 PM – 03:00 PM
Deep Learning	Learning by Doing – Deep Learning Model: Use Case 4 Model Building: Choosing the Right Algorithm Training Optimization Model Performance Evaluation Model Validation	03:01 AM – 05:00 PM
Closing	Short Quiz and End-of-course Survey	05:01 AM – 05:30 PM

Requirements

Please install the following tools and libraries before the training day.

Toolkit:

Anaconda (https://www.anaconda.com/download)
Jupyter (https://test-jupyter.readthedocs.io/en/latest/install.html)
Python (https://test-jupyter.readthedocs.io/en/latest/install.html) – from Anaconda
Visual Code Studio (https://code.visualstudio.com/download)
Postman (https://www.postman.com/downloads/)

Libraries (run in the terminal):