PG Diploma in Computer Vision

Module Description

Mathematics have a significant role in the foundation for programming and this module is designed to help students master the mathematical foundation required for writing programs and algorithms for Artificial Intelligence and Machine Learning. The module covers three main mathematical theories: Linear Algebra, Statistics and Probability Theory.

Learning Outcomes

LO1: Master the mathematical foundation required for writing programs

LO2: Learn mathematical and statistical foundations required for AI & ML

LO3: Acquire mathematical knowledge to build algorithms for data analysing

LO4: Apply statistical analysis techniques using essential softwares on data sets

Content Covered

• Linear Algebra

• Statistics

• Probability Theory

• Statistical Tools (CSV, Excel)

Module description

This module offers a guide to the parts of the Python programming language and its data oriented library ecosystem and tools that will equip students to become effective data analysts. The module focuses specifically on Python programming, libraries, and tools needed for data analysis. Essential Python libraries covered in this module are NumPy, pandas & matplotlib. NumPy provides the data structures, algorithms, and library glue needed for most scientific numerical data applications in Python. Pandas provide high-level data structures and functions that make working with structured or tabular data fast, easy, and expressive. Matplotlib libraries are used for producing plots and other two-dimensional data visualizations.

Learning Outcomes

LO1: Acquire practical skills in data analyzing, handling & visualization using Python tools

LO2: Perform mathematical operations on a wide range of data using NumPy

LO3: Operate Pandas to sort through and rearrange data, run analyses, and build data frames

LO4: Ability to analyze by visualizing data with Matplotlib

Contents Covered

Python Programming for AI & ML

• Essential Python libraries for data analysis

• Data storage and manipulation by NumPy

• Data Visualization using Matplotlib

• Data Analysis with Pandas

• Basic introduction to Sci-kit-learn

Module Description

This module provides an in-depth understanding of established methods of artificial intelligence and machine learning techniques that enable computers to learn without being explicitly programmed. The module discusses various parts of artificial intelligence, which include ML (Machine Learning), DL (Deep Learning), NLP (Natural language Processing), RL (Reinforcement learning), and DRL (Deep reinforcement learning), and aims to explain the real-world application of improved algorithms such as linear regression, k-NN, decision trees, random forest, etc. for machine learning by supervised, unsupervised and reinforcement learning.

Learning Outcomes

LO1: Understand Artificial Intelligence and Machine Learning fundamentals

LO2: Demonstrate a comprehensive knowledge of the nature of the data and techniques

used for pre- processing the data for machine learning

LO3: Introduction to major machine learning algorithms like Classifiers (for image, spam, fraud), Regression (stock price, housing price, etc.), Clustering (unsupervised classifiers)

LO4: Demonstrate a deep critical understanding of algorithms and mathematics

behind established ML approaches

Content Covered

• Introduction to Machine Learning & AI

• Supervised Learning

• Unsupervised Learning

• Reinforcement Learning

• Machine Learning Algorithms (Regression, Classifiers, Clustering)

• Machine Learning Task (dataset, data cleaning, algorithm selection, training & testing model)

Course Description

This module begins by learning about numerical processing using the NumPy library, reading and changing photographs using the OpenCV library to open and deal with picture essentials, and gaining insight into using current deep learning network models like CNN & RNN. Comprehend image processing and apply various effects, including color mappings, mixing, thresholds, gradients, etc. Learners master video basics using OpenCV, including dealing with streaming video from a webcam. The module will overview Image Processing & Computer Vision using Python. It will cover how TensorFlow and deep learning can be used for computer vision applications. Learners will learn to develop techniques to help computers see and understand the content of digital images, such as photographs and videos, using CNN (Convolution Neural Network).

Learning Outcomes

L01. Understand the Basic python tools used for Computer Vision

L02. Understand image processing python packages to enable them to write scripts for text pre-processing

L03. Learn popular machine learning algorithms, Feature Selection, and Mathematical intuition behind it

L04. Understand basic concepts and standard tools used in computer vision

Content Covered

Core Python for computer vision

• Strings

• Regex

Machine Learning algorithms

• Regression

• KNN

• SVM

Computer vision tools

• Keras

• TensorFlow

Course Description

This module will provide learners with knowledge and understanding of the application of machine learning methodologies to handle industrial difficulties, to a more extensive array of data mining and classification type activities. Learners will discover the machine learning algorithms by utilizing neural networks, k-means clustering, and support vector machines in computer vision to analyze data based on supervised, unsupervised, and partially supervised. Additionally covered in this module are, Tensor flow, Faster- RCNN-Inception-V2 model, and Anaconda software development environment utilized to recognize autos and individuals in pictures that provides insight into the usage of current deep learning network models like CNN

Learning Outcomes

L01.Concepts of deep learning to build artificial neural networks and traverse layers of data abstraction and get a solid understanding of deep learning

L02. Develop and build fully automated CV algorithms USING YOLO

L03. Develop the usage of Deep learning models like CNN and RNN

L04. Gain insights about advancements in CV, AI, and Machine Learning techniques

Content Covered

• Introduction to Computer Vision (CV)

• Deep Learning Network Models

• Convolutional Neural Networks (CNNs)

• Recurrent Neural Networks (RNNs)

• Introduction to Keras Model Life-Cycle

• Image Data Manipulation using Pillow Python library.

• Convert Images to NumPy Arrays and Back  

 Module Description

The purpose of this module is to discuss and explain the role of Artificial Intelligence and Machine Learning in an organization and their influence on its overall performance and competence. Learners will be encouraged to pick a research/development project that displays their past learning in the AI & ML domain. It is meant to understand various aspects of AI, such as Machine Learning, Deep Learning, Natural Language Processing, and Computer Vision, to name a few. It also endeavors to highlight the role and significance of AI & ML during the planning, decision-making, and implementation of change in the organization. 

Upon completing the module, the participants will have comprehensive knowledge and the ability to demonstrate their expertise in Artificial Intelligence and Machine Learning to potential employers or educational programs.

Learning Outcomes:

LO1: Conduct independent research and development within the context of an AL & ML project

LO2: Produce detailed documentation to a standard expected of a professional in the field of AI & ML

LO3: Communicate technical information clearly and succinctly to a broad, non-specialist audience

LO4: Apply knowledge of research principles and methods to plan and execute a research based industry project with a high level of personal autonomy and accountability

Content Covered

• Clarifying the terms of the research
• Suggesting areas of reading
• Apply the knowledge base and abilities taught throughout the course to a real-world scenario
• The Problem, Understanding It, and Getting Data
• Frame a business issue in a manner that can be solved with AI & ML
• Apply Exploratory Data Analysis and Modeling
• Identify the methodology or algorithm that will handle the proposed challenge
• Reviewing the proposed methodology
• Establishing a research timetable, including initial dates for further meetings between the student and supervisor
• Advising students about appropriate standards & conventions concerning the assessment.
• Providing means of contact in addition to tutorials
• Educate learners to research and write their results and thoughts correctly, clearly, logically, and to a high-professional degree