MACHINE LEARNING WITH APPLICATION TO OBJECT RECOGNITION
From Naanmudhalvan Wiki
Contents |
Course Details
| Course Code | L | T | P | C |
|---|---|---|---|---|
| SB8007 | 1 | 0 | 2 | 2 |
COURSE OBJECTIVE
The objective of this course is to provide a view of data science, recognize why data science is gaining importance in today’s business world to comprehend where data science can be applied across industry domains to understand major components of data science stack to learn how a data science project is implemented step-by-step in each business use-case
Pre-requisite courses
| Pre-requisite Knowledge | Courses Available on Springboard |
|---|---|
| Probability and Statistics | Probability and Statistics Probabilty distribution using Python Statistical Interence using Python |
| Python Programming Language | Programming Fundamentals using Python - Part 1 |
| Linear Algebra | Basics of Linear Algebra |
| Regression Analysis | Regression Analysis |
| Deep Learning | Deep Learning for Developers |
| Exploratory Data Analysis | Exploratory data analysis |
SYLLABUS
UNIT I - INTRODUCTION TO AI AND DATA SCIENCE
Why AI? - What is AI? - AI in Practice - AI in Business - AI Platforms. Data Science: The Data Revolution - Components of Data Science - Data Science in Action – Conclusion.
UNIT II - PYTHON FOR DATA SCIENCE
Why Python Libraries – NumPy - Introduction to NumPy - Operations on NumPy – Pandas – Introduction to Pandas – Introduction to Pandas Object – Working with datasets – Pandas Plots - Matplotlib – Introduction to Matplotlib – Types of Plots – Scikit-learn – Machine Learning using sklearn. [Practical hands-on exercises using NumPy, Pandas, Matplotlib]
UNIT III - DATA VISUALIZATION USING PYTHON
Data visualization using Python: Data Visualization: Developing insights from data using Basic Plots using Matplotlib (Box, Scatter, Line, Bar, Pie, Histogram), Statistical analysis using Heatmap, Kernel Density plot using Seaborn, Network Graphs, Choropleth Map Using Ploty, Word Cloud. [Practical hands-on exercises for creating charts]
=== UNIT IV - EXPLORE MACHINE LEARNING USING PYTHON
Introduction to Machine Learning - Regression – Classification – Clustering – Introduction to Artificial Neural Network. [Hands-on Exercises for Practicing Machine Learning Models Using Capstone Project]
UNIT V - OBJECT DETECTION AND RECOGNITION USING DEEP LEARNING IN OPENCV
Basic Operations and Algorithms in OpenCV - Object Detection and Recognition Using Features - Deep Learning in OpenCV - Object Classification Using Deep Learning, Recognizing Text in an Image.
TOTAL : 45 PERIODS
SUGGESTED ACTIVITIES
- Continuous / Self-Assessment (MCQ)
- Capstone Project - Build a ML model using a sample image dataset, to detect or identify specific features in sample image such as mask on human face etc.,
SUGGESTED EVALUATION METHODS
- Video Proctored Exam
- Self-Assessment
COURSE OUTCOMES
On completion of the course, students will be able to:
CO1 :Demonstrate fundamental understanding of the history of artificial intelligence (AI) and its foundations.
CO2 :Apply basic principles of AI in solutions that require problem solving, inference, perception, knowledge representation, and learning.
CO3 :Assess and select appropriate data analysis models for solving real-world problem.
CO4 :Demonstrate the importance of data visualization, design, and use of visual components.
CO5 :Demonstrate fundamental understanding of applications of machine learning for object recognition
REFERENCE(Course Material)
- Introduction to AI
- Introduction to Data Science
- Python for Data Science
- Data visualization using Python
- Explore Machine Learning
- Object Detection and Recognition Using Deep Learning in OpenCV
Mode of Training: Online (Self-Learning)
Course Evaluation: Online Assessment
Multiple Hybrid Branch of Students: Applicable for IT/CSE
Internship/Placement Opportunities: Click Here
NOS Alignment: Yes, Infosys Industry Standard
Train-the-Trainer: Faculty Enablement Program
Commercials: Free of Cost
