Scribd
Upload
44 views3 pages

AI-Internship Syllabus

The document outlines a course on Artificial Intelligence, focusing on fundamental concepts, machine learning methods, and deep learning techniques, alongside programming skills in Python. It includes practical experience through hands-on sessions, a capstone project, and aims to build a strong portfolio for students. Key topics covered include data analysis, machine learning algorithms, image processing, and natural language processing.

Uploaded by

jaikumar84980
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
44 views3 pages

AI-Internship Syllabus

The document outlines a course on Artificial Intelligence, focusing on fundamental concepts, machine learning methods, and deep learning techniques, alongside programming skills in Python. It includes practical experience through hands-on sessions, a capstone project, and aims to build a strong portfolio for students. Key topics covered include data analysis, machine learning algorithms, image processing, and natural language processing.

Uploaded by

jaikumar84980
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Artificial Intelligence – Fundamentals

Course Objectives:
1. Build a strong understanding of fundamentals of AI concepts, machine learning
methods, and deep learning techniques.
2. Learn the basics of programming and become skilled in Python for AI development.
3. Gain key data analysis skills using Python, including importing, transforming data,
creating visualizations, and storytelling with data.
4. Study and understand the structures and algorithms of various machine learning and
AI techniques.
5. Be able to design and apply different machine learning methods to solve real-world
problems.

Program Benefits:
1. Practical Experience: Get hands-on practice with exercises and real-world case studies
to apply what you learn.
2. Portfolio Building: Create a strong portfolio that highlights your problem-solving skills
and showcases your ability to handle case studies, helping you stand out to potential
employers.

Program Outline:

Program Component
Technical Course Content - Theory
Hands-On sessions
Capstone Project
Self-Paced Content
Total Duration
Day Description of the content to be covered

AI Concepts, Python Basics


Understanding AI Concepts
• Understanding AI terminologies, real-world applications, and market trends.
• Exploring open-source tools, platforms, and the latest AI models.
Hands-on:
• AI System Scavenger Hunt
Fundamentals of Python Programming
• Fundamentals of open-source Python programming tools.
• Installation of Anaconda and Set up the Python Environment.
• Use Command Line and IDE to create and execute a Python program.
• Basics of Python: Data types, variables, basic operators, and input/output
• Control Structures: Conditional statements, loops.
• Functions: Writing functions
Hands-on:
• Python Control statements and Functions
• Data Structures: Lists, Dictionaries, Sets, Tuples.
• File Handling: Reading from and writing to files.
Applied Data Analytics with Python Programming
Data Processing and Analysis with Python
• Introduction of Exploratory Data Analysis and Types of EDA.
• Data preprocessing techniques: Data cleaning, normalisation, and
transformation.
Python Packages for EDA applications:
• Python packages for EDA applications: Practicing with NumPy.
• Python packages for EDA applications: Practicing with Pandas.
• Practicing with Data Visualization Python packages (matplotlib and Seaborn)
• Story telling with data on real-world dataset
Hands-on:
• Create a mini project to guide students through conducting Exploratory Data
Analysis (EDA) on a dataset containing information about university students.
The objective is to uncover insights and patterns related to academic
performance, study habits, and extracurricular activities.
Implementation of ML and DL Algorithms
Introduction to Machine Learning.
Classification and Regression Algorithm
• Supervised, Unsupervised, Semi-supervised and Reinforcement learning.
Supervised ML Algorithms
• Understanding Linear Regression, Decision Tree and Support Vector Machine.
• Model Evaluation and Validation.
• Train-test split, cross-validation.
• Performance metrics (accuracy, precision, recall, F1-score).
Hands-on:
• Use linear regression to predict housing prices based on features such as
square footage, number of bedrooms, bathrooms, etc.
• Use decision trees to predict whether customers are likely to churn (cancel
their subscription or leave the service).
Unsupervised ML Algorithm
• Understanding the K-Means Clustering algorithm.
• Evaluation metrics for model performance.
Hands-on:
• K-Means Clustering for Customer Segmentation: Use k-means clustering to
segment customers based on their purchasing behaviors, demographics, and
other relevant features.
Image Processing with OpenCV, Python
• Image Processing Vs Computer Vision
• Image handling with OpenCV
• Edge Detection with OpenCV
Hands-On:
• Image Processing by OpenCV- Resize, Rotation, Annotation etc.,
• Edge Detection by OpenCV – Canny Edge Detection
OpenCV project to identify faces in the image
Neural Networks and Deep Learning
• Introduction to deep learning and neural networks.
• Building neural networks using TensorFlow.
• Advanced techniques in deep learning (CNNs, RNNs, etc.).
• Training deep learning models and transfer learning.
• Overfitting, Underfitting, Dropouts, Regularization, Early Stopping.
Hands-on:
• Building a simple feedforward neural network using TensorFlow.
• Image classification with CNNs using the MNIST dataset.
Hands-on:
Building an image classification application using a pre-trained model.
Exploring NLP and use cases
NLP Introduction
• Introduction workflow of NLP
• NLP techniques and challenges
• NLP Applications
• NLP python packages
• Understand RNN models for sentiment analysis
Hands-on:
• Text pre-processing with NPL
• NLP Concepts based project: Spam Email Classification using NLP and
Machine Learning
• Implement sentiment analysis by RNN model

You might also like