The ability to process large quantities of data and to efficiently conclude from it is critical for coping with the “big” data generated by the information revolution. Machines that learns patterns and predict from data, proved useful in NLP, Computerized vision (e.g. autonomous cars), Speech recognition, Image, video and text generation, Fraud Detection and Cyber security. Deep learning using such networks is probably one of the most successful machine learning technologies in recent years with applications that span across. many domains. In this course students will learn the principles of using such brain inspired networks for machine learning and will practice programming small projects.
Machine learning (or Computational learning) is a sub-field in computer science and in Artificial Intelligence and intersects Statistics and Optimization theory. The field deals with algorithms, which allow computer to learn from examples, and to operate in a variety of computational tasks, where classical programming is impossible or not economical. Machine learning is relatively new area and is responsible to recent breakthroughs in Artificial intelligence, Data mining and automatic knowledge discovery in big data. In its core lies the ability to the specific tasks. This is done by analyzing large quantities of data, pattern recognition and forecasting future behavior.
The computer science seminar on seminal papers in AI will explore the foundational research that has shaped the field of artificial intelligence. Participants will engage with groundbreaking works that introduced key concepts, algorithms, and methodologies, such as neural networks, machine learning, natural language processing, and reinforcement learning. Through presentations and discussions, attendees will gain a deeper understanding of the historical context, innovative ideas, and enduring impact of these pivotal papers on modern AI developments and applications. The seminar aims to foster critical thinking and inspire new perspectives on the future direction of AI research.
As part of the course, the student will be exposed to all the development stages of an application or software package including: application design and development, interface design, algorithm implementation, architecture selection and database integration, methodology implementation, critical thinking, end-to-end development and testing, documentation and presentation, teamwork and project management.
This is a continuation course in which the student will be exposed to all the development stages of an application or software package, including: application design and development, interface design, algorithm implementation, architecture selection and database integration, methodology implementation, critical thinking, end-to-end development and testing, documentation and presentation, teamwork and management projects.
This course aims to give the students a basic foundation in Artificial Intelligence (AI) techniques. The first part of the course will focus on fundamental AI concepts of Search & Planning. The second part will include Probabilistic reasoning. The theoretical material will be supported by examples and practical applications.