This module is composed of five units. Each unit will cover a wide range of thought-provoking subject matter in addressing both theoretical and practical issues related machine learning and artificial intelligent
UNIT 1. Introduction to Machine Learning and Artificial Intelligence:
Definition of machine learning (ML) and artificial intelligence (AI)
Historical background and key milestones
Importance and applications of ML and AI in various fields
UNIT 2. Fundamentals of Machine Learning:
Supervised, unsupervised, and reinforcement learning
Training data, validation data, and test data
Feature engineering and feature selection
Evaluation metrics for ML models
UNIT 3. Regression and Classification:
Linear regression
Logistic regression
Decision trees
Random forests
Nearest neighbourhood
Unit 4. Clustering and Dimensionality Reduction:
Hierarchical clustering
Principal Component Analysis (PCA)
UNIT5. Neural Networks and Deep Learning:
Introduction to artificial neural networks (ANN)
Feedforward neural networks
Backpropagation algorithm
Convolutional Neural Networks (CNN)
Recurrent Neural Networks (RNN)
Generative Adversarial Networks (GAN)
This module is composed of five units. Each unit will cover a wide range of thought-provoking subject matter in addressing both theoretical and practical issues related machine learning and artificial intelligent
UNIT 1. Introduction to Machine Learning and Artificial Intelligence:
Definition of machine learning (ML) and artificial intelligence (AI)
Historical background and key milestones
Importance and applications of ML and AI in various fields
UNIT 2. Fundamentals of Machine Learning:
Supervised, unsupervised, and reinforcement learning
Training data, validation data, and test data
Feature engineering and feature selection
Evaluation metrics for ML models
UNIT 3. Regression and Classification:
Linear regression
Logistic regression
Decision trees
Random forests
Nearest neighbourhood
Unit 4. Clustering and Dimensionality Reduction:
Hierarchical clustering
Principal Component Analysis (PCA)
UNIT5. Neural Networks and Deep Learning:
Introduction to artificial neural networks (ANN)
Feedforward neural networks
Backpropagation algorithm
Convolutional Neural Networks (CNN)
Recurrent Neural Networks (RNN)
Generative Adversarial Networks (GAN)
Welcome to Physical Geography I module. This module aims at providing to the students’ basic knowledge of universe and galaxies, notions of mineralogy, petrography, and stratigraphy. It deals also with internal geodynamics (structure and composition of the earth, continental drift and plate tectonics theories as well as orogenesis), and external geodynamics (factors of slope development, topographic units, fluvial erosion, anthropogenic erosion, mass wasting and runoff). Additionally, this module provides theoretical and practical knowledge and skills in the field works.
This module aims at providing students with deep understanding of concepts and practices of research, different research approaches and designs, research methods and techniques, writing research proposal, data collection tools and methods, data management and analysis, academic writing, research reporting, and dissemination.
The Game Theory and Information Economics module provides students with core theories, mathematical models, and analytical tools for decision-making and strategic interaction among rational agents. It covers key concepts in Decision Theory, including payoff analysis and decision-making under certainty, risk, and uncertainty, alongside decision tree techniques. The module also introduces the fundamental structures and assumptions of game theory, addressing both perfect and imperfect information settings. Grounded in real-world applications, it develops students’ critical thinking, problem-solving, and innovative capacities.
This module aims at providing students with deep understanding of concepts and practices of research, different research approaches and designs, research methods and techniques, writing research proposal, data collection tools and methods, data management and analysis, academic writing, research reporting, and dissemination.
This module ED80442 introduces to different key concepts used in Early Childhood Inclusion (ECI), Inclusive education framework with golden rules for effective implementation of ECI. It also gives insignhts into methodology for children with various spcial needs and disabilities. The module culminates in a field visit to an inclusive preschool model for observation of real classroom environment and interaction with caregivers and children.
This module aims at providing students with deep understanding of concepts and practices of research, different research approaches and designs, research methods and techniques, writing research proposal, data collection tools and methods, data management and analysis, academic writing, research reporting, and dissemination.
Services and resources required in Special Needs Education for early childhood, Policies and legislation related to the needs of children with disabilities; working with parents and the local community to respond to the needs of children with Special Educational Needs, responding appropriately to children with special educational needs, assessment of SNE in early childhood. Areas of assessment: social interaction, self-esteem and emotional state, motor skills, basic academic skills (pre-reading/reading, pre-writing/writing, pre-numbers/numbers), perception skills, language development and communication skills, adaptive behaviour, the child's interest.