Lectures
Lectures
Computer Science is the systematic study of algorithmic processes, computational systems, and the hardware and software designs used to process information. It encompasses a wide range of topics, from theoretical foundations like data structures and complexity to practical applications such as artificial intelligence and software engineering.
This course introduces practical data analysis programming using Python. Students learn essential libraries for data processing, visualization, and analysis, along with fundamental machine learning concepts and techniques. Through hands-on exercises using real-world datasets, students develop practical skills in data analysis and machine learning.
Capstone Design is a comprehensive course where students apply their cumulative knowledge of computer science to plan and design a solution for a real-world problem. His project-based curriculum focuses on the entire development lifecycle, including team collaboration, requirement analysis, system architecture design, and the initial implementation of a functional prototype.
Computer Science is the systematic study of algorithmic processes, computational systems, and the hardware and software designs used to process information. It encompasses a wide range of topics, from theoretical foundations like data structures and complexity to practical applications such as artificial intelligence and software engineering.
Description: Introduction to Artificial Neural Networks explores the mathematical models inspired by the biological structure of the human brain to enable computers to learn from data and recognize complex patterns. The course covers the fundamental principles of how information flows through layers of neurons and how optimization techniques like backpropagation are used to improve predictive accuracy.
Description: Capstone Design I is a comprehensive course where students apply their cumulative knowledge of computer science to plan and design a solution for a real-world problem. his project-based curriculum focuses on the entire development lifecycle, including team collaboration, requirement analysis, system architecture design, and the initial implementation of a functional prototype.
This course introduces the fundamental theories and algorithms of reinforcement learning, focusing on how intelligent agents learn optimal decision-making through interaction with their environments. Students explore key concepts such as Markov decision processes, value functions, policy optimization, and deep reinforcement learning. Through theoretical study and practical implementation, students develop the ability to design and apply reinforcement learning methods to real-world problems.
Description: Meta-Learning is an advanced graduate course focused on the concept of "learning to learn," where AI models are designed to rapidly adapt to new tasks with minimal data by leveraging previous learning experiences. The curriculum delves into sophisticated architectures and optimization strategies, such as few-shot learning and model-agnostic meta-learning (MAML), to improve the efficiency and generalization of neural networks.