Computer Science

This course is an introduction to digital image processing and analysis. Students benefit from an overview of image processing methods (histogram restauration, convolution filters, mathematical morphology, segmentation) and image analysis methods (pattern recognition, identification, etc.). During the course students: learn how to manage 2D, 3D, and animated images; understand human perception and image acquisition; discover image segmentation, registration, and analysis; concrete implementation through existing tools or simple script development; study algorithms to obtain features from images (histogram, filters, descriptors).

Students learn about the foundations, building blocks, and applications of Natural Language Processing (NLP), with an emphasis on approaches based on deep learning. They study the models used to represent words and word meanings. They then use these representations to study classification tasks (e.g. sentiment analysis) and tagging tasks (e.g. part of speech tagging). In addition students view languages as sequences of variable length, from pure language models to machine translation models. Finally students explore approaches that are based on modern neural machine learning algorithms, where linguistic information is provided by instances of uses of language.

This course introduces the subject of artificial intelligence covering the basic principles and technologies of intelligent computer systems and the algorithms to achieve AI and how to develop some AI programs. Topics include: intelligent agents; search techniques for problem solving (uninformed, informed, local, adversarial); knowledge representation; logical inference; propositional logic; reasoning under uncertainty; statistical models and machine learning; probability; Bayes’ nets; and decision theory.

This is a graduate level course that is part of the Laurea Magistrale program. The course is intended for advanced level students only. Enrollment is by consent of the instructor. The course focuses on the relevant themes related to blockchain technologies, cryptocurrencies, smart contracts, and novel applications that can be built over the blockchain. Students in the course develop simple smart contracts that can be deployed on a blockchain. Bitcoin and novel cryptocurrencies gathered momentum in the last months. More and more investors look with interest at these technologies, while others label them as a dangerous speculative bubble. The truth is that the blockchain, and the alternative implementations of a distributed ledger, represent very interesting technologies, that can be exploited to build novel distributed applications. The underlying building blocks are related to many concepts and research areas of computer science in general. This course illustrates the main principles and conceptual foundations of the blockchain and the Bitcoin network. The course discusses topics including introduction to peer-to-peer systems, overlay topologies and decentralization, introduction to Crypto and Cryptocurrencies, the blockchain: how to achieve decentralization, transactions and transaction scripting languages, mining, attacks to the blockchain, anonymity, and smart contracts.

This is a cross domain course which students are divided to two groups. One group focuses on Big Data processing needs, analytics, machine-learning and recommendation systems. The other emphasizes compilers and their contexts, be it Android compilation or Big Data languages. This is crucial especially today; Benefitting from Moore's Law, the main abstraction level in Computer Science has shifted higher rapidly. In comparison, Taiwan's industry has been buried in the hardware, drivers, and benchmarking game. Both groups are taught by an author of Big Explorer, Android Virtual Machine and RenderScript Engine (Google). The course also includes a mini-hackathon.

The course covers the basic principles, methods, and application of database technology. It examines existing database management systems and software development tools, and the core implementation technology of database management systems, database model design, and database application system development principles. Topics include basic concepts of database system, operation theory of relational model, SQL language, standardized design theory, database design, database storage structure, database query processing process, database management system implementation technology, database security, graph/sequence data management technology, NoSQL database, and cutting-edge paper reading.

This is an introductory course on modern Artificial Intelligence designed for Keio University. It focuses predominantly on theory and fundamental concepts, with implementation of basic techniques in Python. Depending on the level of the students and time constraints, it may also cover more practical engineering topics using modern practices, as well as some of the most influential recent advancements based on a selection of research papers. Additionally, the course also covers some topics in more depth based on the interests of the instructor. One of those topics is Natural Language Processing (NLP) in the era of Deep Learning, as well as advanced methods in representation learning.

This course focuses on Deep Neural Information Processing Systems. As a rapidly developing field, the course centers on most important trends and core ideas, as it is impossible to cover all recent developments in a single course. It follows historical trends in AI with a focus on neural networks, seeing how the current ideas emerged out of decades of research in the field.  Then, the course discusses current neural architectures and algorithms, while introducing modern perspectives. After completing this course, students are expected to have an appreciation and understanding of neural AI systems and anticipate future developments in research and applications of AI (especially Deep Learning).