Scribd
Upload
12 views

AIYA Pre-Requisites General Guidelines

Uploaded by

chess player aarav
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
12 views

AIYA Pre-Requisites General Guidelines

Uploaded by

chess player aarav
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

AIYA (For High School Students)

Pre-Requisites
General guidelines

Importance of Pre-Requisite Training for AIYA

To ensure your success in the AIYA programme at NUS, it is imperative that you possess a
solid foundation in key areas. Therefore, we are pleased to introduce prerequisite training
sessions designed to fortify your fundamental skills. These courses are tailored to sharpen
your proficiency in Python, statistics, and probability—essential pillars for excelling in the
AIYA programme. Mastery of these skills is pivotal in comprehending the intricacies of
Artificial Intelligence concepts. By investing time in these pre-requisite training, you are not
only laying a robust groundwork for your academic journey but also positioning yourself for a
more profound understanding of the cutting-edge technologies that await you in the AIYA
programme. Embrace these preparatory sessions as a valuable opportunity to enhance your
capabilities and embark on a rewarding exploration of the world of Artificial Intelligence.

Modules Overview
1. Python Programming Basics
 Variables, data types, and operators
 Control structures (if statements, loops)
 Functions and modules
 Lists, dictionaries, and other data structures

2. Python Libraries
 Familiarity with essential Python libraries such as NumPy and Pandas for
data manipulation
 Understanding of Scikit-Learn for machine learning tasks

3. Basic Mathematics and Statistics


 Arithmetic operations
 Mean, median, mode
 Standard deviation, variance
 Probability and probability distributions
 Linear algebra basics (vectors, matrices)
Topics where Pre-Requisites will be used

Colour code:
We are representing the NUS and AWS curriculum and the individual sections where
the pre-requisites are required have been colour-coded as below.
1. Python Programming Basics . .
2. Python Libraries . .
3. Basic Mathematics and Statistics . .

Sessions with NUS

Session Session Duration


Session Agenda
No. By (hours)

Lecture1: Introduction to AI

 Introduction to AI
 A brief review on AI history
1 NUS 3
 AI Applications: State of the art
 AI, Machine Learning, and Deep Learning
 Restrictions and constraints
 Future of AI

Leture 2: AI principles

 AI approaches
 Search and heuristics
2 NUS  Optimization of the solution 3
 Logic of building models
 Machine learning
 Deep learning
 Mini Project Definition
 Teams Configuration (by TA)

Lecture 3: Overview of Fuzzy Logic

 Introduction - Example
3 NUS  Learning Objectives for this course revisited 3
 Fuzzy Logic and its applications
 Designing a Fuzzy Logic System
 Real World Examples
 Q&A
Lecture 4: Machine Learning

 Introduction to ML and Orange – with


4 NUS Examples 3
 How to install and use Orange
 ML Approaches
 Datasets Intoduction and Importance
 Q&A
Lecture 5: Machine Learning Case Studies and
Application
 Clustering introduction and basic concepts
5 (AM) NUS  Function Estimation, improves models 3
 Classification, KNN and Logistic Regression
 Examples in Orange
 Q&A

 Course Summarization
5 (PM) NUS  Mini Projects Presentations 3
 Wrap up and Team feedback session
Sessions with AWS

Ses Session Duration


sion Theory Handson
No. By (hours)

● Introduction to data ● Creating a


science and its SageMaker Notebook
applications ● Basic data exploration
● Setting up essential
1 AWS tools: Amazon 3
SageMaker and
Jupyter Notebook
● Data preprocessing
techniques
● Introduction to ● Implementing a basic
supervised learning classification problem
2 AWS 3
● Model evaluation using SageMaker
methods
● Introduction to ● Text preprocessing
Natural Language exercises
Processing (NLP) ● Building and
and its applications evaluating an NLP
3 AWS ● Understanding text 3
preprocessing
techniques
● NLP libraries and
tools
● Introduction to ● Amazon Rekognition
Amazon Rekognition to perform image
● Introduction to classification
Amazon Textract ● Building an image
4 AWS classification model 3
using Amazon
SageMaker.
● Hands-on exercises
with Amazon Textract
Final Project ● Q&A question
Presentation ● Building a strong data
5 AWS science portfolio 3
● Career Roles post
programme.

You might also like