������

CS-E4330

This course is taught by malware experts from F-Secure, a Finnish cyber security company. You will learn about malware analysis and reverse-engineering tools and methods through hand-on exercises and lectures. The course will take place in January-April 2019.

Contact: cs-e4330@aalto.fi

CS-E5370

Artificial intelligence can now land an airplane: both civilian and military aircraft. Robot cars are being tested all over the world, including Finland. Should artificial intelligence and robotics have their own rules? They say that privacy is dead, yet it requires thousands of new specialists - why is the GDPR (General Data Protection Regulation) so important? Are cybersecurity rules robust enough for the hyperconnected society? These and many other questions will be addressed during the course.

Welcome to study Law in Digital Society that begins on 7 January 2019.

CS-E4070

Always-on microphones which share data with the cloud and other devices improve the performance of smart assistants and enable other voice-enabled technologies. At the same time, sharing speech and audio information is potentially very dangerous for our privacy. Who listens? What do they do with that information?

The objective of this seminar is to explore privacy issues in speech and audio interfaces, both for understanding better what privacy is, for the user-centric design of privacy-gentle user-interfaces as well as importantly, methods for enforcing privacy. 
The seminar is intended for master's and doctoral-level students, who have a background typically in (but not limited to) one of the following: speech or audio processing, acoustics, user-interface design, or privacy and security. Students can choose to do only home assignments and summary (3 ECTS) or presentation+experiments (5 ECTS).

More information: 

CS-E4070

Gaussian processes are a powerful tool for Bayesian nonparametric modelling. This course will give an introduction to the field of Gaussian processes and provide a theoretical background for Gaussian processes including both modelling and inference aspects. The course will include Gaussian process regression and classification as well as give examples of how Gaussian processes can be used as building blocks in more complex models. The participants will also be introduced to more recent advances in the field. 
  
The course will contain a mix of lectures, practical assignments and project work. The practical assignments will be based on pen & paper and the Python programming language. Other languages (such as Matlab and R) can be used, but it will require significantly more work from the participants.

CS-E4070

This 5 ETCS course will provide an introduction to some of the central topics in computational learning theory, a field that seeks to answer the question “can machines learn?” from the perspective of theoretical computer science. We will study mathematical and computational models of learning that give rigorous analysis on learning algorithms with focus on error bounds and computational efficiency.

Prerequisites: Basic discrete math and probability, Big-O notation and basic analysis of algorithms, familiarity with mathematical proof principles, and some basic knowledge of the theory of NP-completeness.

Teachers: Aristides Gionis and Cigdem Aslay

More information soon in MyCourses.

CS-E4070

The task of determining an optimal solution for a given problem (discrete optimization problem) is ubiquitous in computer science. A prominent example is the Travelling Salesman Problem where the goal is to find a shortest tour that visits a given set of locations. Unfortunately, for many optimization problems, no efficient algorithms are known (and under standard complexity theoretic assumptions, no such algorithms are expected to exist). However, feasible solutions are still required in practice. Thus, one approach is to determine efficient algorithms that provide provably good (but not necessarily optimal) solutions.

In this lecture, we discuss the design and analysis of techniques for such algorithms. Namely, we consider methods that provide a guaranteed approximation ratio (i.e., a bounded ratio between the objective value of a computed solution and the objective value of an optimal solution). For example, we will see an algorithm for the Travelling Salesman Problem where the ratio between the tour provided by the algorithm is at most two times the value of a shortest tour.

By the end of this course, participants should be able to analyze simple approximation algorithms with respect to their quality. They should also be able to apply basic design techniques (e.g., greedy, local search, scaling, and LP-based methods) to approximately solve discrete optimization problems.

Here is the  of the course.

CS-E4070

Alexander Ilin give a course "Advanced Topics in Deep Learning". Maximum 12 students can take the course, and students are chosen based on how well a student did in the course "Deep Learning": Either good grade in the previous years or a student has solved the exercises (with a good number of points) of the Deep Learning course that will start in period 4.

More information in .

CS-E5000

Data has huge potential, but unlocking the true value of data has many challenges. Global data play is dominated by a few isolated platform players that claim ownership of key data assets. It is difficult for businesses and governmental bodies to understand the characteristics and potential of data. Recent developments, such as privacy legislation GDPR, complicate the use of data further, but also open up possibilities for those who aim to redefine the rules to enable a more fair and trust-based data ecosystems. 

The seminar is aimed at students who want to understand better the opportunities and challenges related to using and sharing data internally at businesses and within a data ecosystem. The data ecosystem topic will be approached from multiple angles, including e.g. governance, trust and privacy, business, technology, and legal aspects. The course will be conducted as a combination of guest lectures and a student project on selected topics. The class instructors will include Aalto University researchers and affiliates with various academic backgrounds, as well as guest lecturers who are domain experts from the industry.

In the project, the students apply what they have learned from topics covered and propose a solution to a problem or a way to move the ball forward in this field. This may take many forms (case study, project proposal, technical recommendation, code, etc.) as long as the idea is adequately explained and/or demonstrated. In addition to final project presentation, students will create a poster that summarize the results of about their project.

Course lectures will be held on Tuesdays between 14-16 o’clock starting 22.1.2019. As shown in Weboodi, room is T4 in Konemiehentie 2 (T-talo). More information in MyCourses.

MS-E1000

Through the art projects students deepen their understanding of various geometric and topological phenomena, and find new interpretations on them.  The contents of the course set up an ideal foundation for digital technologies such as CAD, 3D printing, game design and VR. 

DL 15.12.2018. More information. 

MS-E1687

Description: In teaching period III, we are going to see the new TLS 1.3 Key Exchange protocol and a game-based security analysis.  In teaching period IV, we are going to study connections/separations between complexity theory/worst-case hardness, average-case hardness, hard learning problems and cryptography. Moreover, we are going to see the implications of the advent of indistinguishability obfuscation which was at the center of the last scientific revolution in cryptography. Lecture: Monday 10:15 - 11:45 Y124,   Exercise: Monday 14:15 - 15:45 Y122.

More information: 

ELEC-E9910

Design teacher Salu Ylirisku and Prof Pekka Nikander have developed an ambitious combination of three interlinked courses, where the students design and implement simple IoT systems from the ground up, including electronics, mechanics, embedded software, communications, cloud, and user interfaces.  In January the implementation phase, ELEC-E9910 Neppi Tech, will start.  For that, they call master students with skills in various aspects software, etc. 

More information: 

CS-E4001

As machine learning (ML) applications become increasingly prevalent, the security and privacy of ML algorithms become a major concern. A lot of research has been done lately to identify the security threats to ML algorithms and some protection have been proposed. In this course we explore contemporary research topics in the domain of security and privacy of machine learning. It consists in several group discussion sessions. Two scientific papers related to security and privacy of machine learning are discussed during each session. Students will learn about ML security and privacy, but also methods for scientific paper reading, analyzing and synthesizing information, and reporting the findings. 

More information in .

CS-E5000

This seminar will pursue a cross-disciplinary investigation of the socio-ethical implications of digital technologies. We will combine theoretical viewpoints with concrete issues facing people who are implementing digital systems. We will cover a variety of themes, including data ownership and control, digital economics and surveillance capitalism, power and governance of algorithmic decision making, humanization of digital technology, and ethics of robotics and autonomous systems. 

The course will entail an intense array of learning and teaching methods. We will take up issues that have recently come into focus and are being approached by a variety of disciplines at different paces. We will discuss examples from various domains, such as health, media, games, retail, manufacturing. The class instructors will include Aalto University researchers and affiliates with various academic backgrounds, as well as experts from the industry.

In the final project, the students apply what they have learned from topics covered and propose a solution to a problem or a way to move the ball forward in this field. This may take many forms (case study, project proposal, policy recommendation, code, etc.) as long as the idea is adequately explained and/or demonstrated. In addition, students will create a poster about their project.

Course lectures will be held on 25.9, 9.10, 16.10, 6.11, 13.11, 20.11, 27.11 and 4.12 between 14-16 o’clock. In addition, there will be a poster session for completed projects on 12.12 (to be confirmed).

More information in .

CS-E5460

If you want to know what technology is needed for things like IIoT (Industrial Internet of Things) and Mobile CPS (Cyber Physical Systems), you should take this course. The course addresses the concrete building blocks of such systems; starting from user interfaces and spanning from the sensor/actuator devices to the related cloud services. The course is an advanced course in a project format, where you learning by doing. The topic is varying and is assigned per group, the interested students should attend the opening event (Monday 2018-09-10, 14-16 T6/T-building). 

More information in  .

NBE-4150

10.9.2018-3.12.2018, periods I-II, 5 cr

This is a new interdisciplinary course on the rapidly emerging field of DNA nanotechnology (), which applies computational techniques to the design of nucleic acid nanostructures for bioengineering uses, and theoretically also for biologically based computation.

The course comprises 12 lectures on the foundational principles in this field, and 6 demo sessions on the most widely used computational tools and laboratory techniques. Coursework consists of reading assignments and four small projects on designing and analysing nanostructures using the given software tools. There is no exam.

Responsible teachers: Prof. Anton Kuzyk (NBE), Prof. Pekka Orponen (CS)

Prerequisites: Interest in bionanotechnology and molecular self-assembly. Familiarity with basic programming concepts. Basic knowledge of nanomicroscopy techniques on the one hand and discrete mathematics and automata on the other are additional assets.

Course homepage in .

CS-E4070

As data grow increasingly diverse and heterogeneous, it is ever more important to be able to exploit different points of views on the same phenomena in order to extract more coherent and relevant information. Multi-view and multi-modal data analysis techniques are therefore becoming more important in data analysis. 

The aim of this course is to introduce students to redescription mining, a relatively recent multi-view data analysis technique. Redescription mining is related to standard data analysis tasks of association rule mining and classification. 
The course will cover the formal problem definition, various algorithms, as well as some of the applications and variants of the method. 

The course is most suitable for students who know the basics of data analysis and are interested in learning about further methods. 
Students will be asked to attend weekly meetings, report on a paper selected from a reading list and participate actively in discussions. Students may also work on a implementation or hands-on analysis task related to redescription mining in order to earn additional credits.

The course is held in period II, more information will be published later in MyCourses

CS-E4000

This course is a reading seminar in algorithms and theory of computation. Everyone is welcome to attend. For further information, see: . For students, you will get 5 credits if you do the following:  

• Participate in the seminar through the semester.  
• Pick a paper and (1) write a summary (up to 5 pages) about it and (2) present the paper in one of the meetings. 

CS-E4000

8.1.2018 - 15.1.2018 and 20.4.2018, periods III-V, 5 cr

For further information on a topic and an implementation follow the MyCourses pages.

CS-E4002

02.01.2018-27.03.2018, periods III-IV, 5 cr

For further information on a content and an implementation follow the MyCourses pages.

CS-E4070

08.01.2018-05.03.2018, periods III-IV, 3 cr

Vision and cognition is a course targeting the overlap of cognitive vision and computer vision. The main goal of the course is looking behind the biological inspirations that have been leading the computer vision community for decades. Together, we will go through several biological inspired architectures for vision systems, including deep neural models of vision.

For further information, see:

CS-E4070

9.1.2018 - 27.3.2018, periods III-IV, 5 cr

 (a.k.a. ABC, likelihood-free inference) is a new class of computational inference methods that can be used when the likelihood function is difficult to evaluate or unknown, and one has a simulator for generating data that (hopefully) resemble observations when generated with correct parameters. The underlying intuition is that similar model parameters are likely to generate similar data, but the practice is of course a bit more complex... 

ABC has applications from medicine to particle physics, and is expected to revolutionize computional sciences that cannot apply traditional statistical methods.

CS-E4330 

10.01.2018-04.04.2018, periods III-IV, 5 cr

For further information on a content and an implementation follow the MyCourses pages.

CS-E5000

20.02.2018-15.05.2018, periods IV-V, 5 cr

For further information on a topic and an implementation follow the MyCourses pages.

CS-E5390

12.03.2018-04.05.2018, periods IV-V, 3 cr

For further information on a topic and an implementation follow the MyCourses pages.

CS-E4070

21.2.-28.3.2018, Period IV, 5 cr

Gaussian processes are a powerful tool for Bayesian nonparametric modelling. This seminar course will give an introduction to the field of Gaussian processes and provide a theoretical background for Gaussian processes including both modelling and inference aspects. The seminar will include Gaussian process regression and classification as well as give examples of how Gaussian processes can be used as building blocks in more complex models. The participants will also be introduced Bayesian optimization as well as more recent advances in the field.

The seminar will contain a mix of lectures, video lectures, practical assignments and project work. The practical assignments will be based on pen & paper and the Python programming language. Other languages (such as Matlab and R) can be used, but it will require significantly more work from the participants.

The exact content of the course will be adjusted based on the participants. Feel free to contact Michael (michael.andersen@aalto.fi) for more information. More information in .

CS-E4070

Period IV-V, 5 cr

Humans are the drivers and benefactors of the progress in artificial intelligence and machine learning. On the other hand, artificial intelligence and machine learning are breaking ground for new kinds of user interfaces and user experiences. Closing this loop, that is, optimally combining the strengths of humans and machines, is one of the most interesting scientific questions at the moment. This course provides a look into state-of-the-art research at this intersection of probabilistic machine learning, cognitive models, and human-machine interaction.

The course will be useful for students how are interested in:
* machine learning: A bottleneck for AI systems is that they don't understand humans.
* cognitive science: Understanding human behaviour is of interest as such.
* human-computer interaction: A bottleneck for intelligent interfaces is modeling human cognition and behavior and getting humans to understand the system.

All of these fields share a common underlying challenge, for which modelling of humans, machines, and their environment can provide the solution.
The course will include (1) high-level introductory lectures on the main topics, including computational rationality, reinforcement learning, probabilistic programming, and user modelling, (2) a project work for hands-on experience and a deeper look into a topic, and (3) select readings of research papers for a wider scope overview.

Prerequisites: Either (1) good understanding of probabilistic modelling/machine learning and programming experience (implementing machine learning algorithms) with interest in HCI/cognitive science/reinforcement learning, or (2) good understanding of HCI and some background in probabilistic modelling/machine learning with interest to learn more. The course is intended for advanced Master’s level or PhD level students.

More information will be in MyCourses.

CS-E4070

4 cr

Lecturer: Professor Panagiotis Papapetrou, University of Stockholm

Content:
- Semantics in electronic health records (EHRs): ICD10 codes, ATC codes, healthcare registry systems
- Temporal abstractions for complex, time-evolving data sources
- Predictive modeling for EHRs: random forests, survival analysis
- Descriptive modeling for EHRs: clustering, disproportionality analysis, subgroup discovery
- Two applications areas: detecting adverse drug events, predicting heart failure
Lectures: Five lectures, on March 6, 8, 12, 14, and 16, at 10am-noon. 
Location: CS building, lecture room T5 (except from March 16, which will be in T6)
Assignments: 1 in-class paper presentation and 1 project
Exam: a take-home exam
More information will be in MyCourses.

CS-E5370

Artificial intelligence can now land an airplane, that is both civilian and military aircraft. Robot cars are being tested all over the world, including Finland. Should AI and robotics have their own rules? And how has cybersecurity come to embrace protecting, in addition to computers, entire societies? They say that privacy is dead, yet it requires thousands of new specialists - why? These and many other questions will be answered during the course. Welcome to study Law in Digital Society that begins on 19 February 2018.

of the course.

CS-E4070

09.04.2018 - 25.05.2018, Period V, 3 or 5 cr

Latent variable models (LVMs) are powerful and flexible tools for learning hidden structure underlying data objects in an unsupervised fashion. They provide a compact, meaningful representation of the inputs. Bayesian matrix factorization is a general class of LVMs which factorizes a data matrix into a product of two low-rank matrices. LVMs (and BMF) can be used for many purposes in machine learning, such as clustering, pattern recognition, dimensionality reduction, feature extraction, and predicting missing values.

Latent variable modeling is a very broad research topic. This seminar course will provide a gateway to this interesting topic through introductory lectures for several widely used LVMs (e.g. factor analysis and multi-view learning) and basic principles of the methods as well as discussion of more recent advances in the field.

Content summary:The course will include (1) introductory lectures about the main topics and related probabilistic programming in STAN, (2) student presentation of selected readings of research papers for an overview of the topics, and optionally (3) a project work for hands-on experience and a deeper understanding of the topics. The project work will be based on pen & papers and R/Python & STAN programming language. The presentation should explain the background / motivation, major concept of the selected papers, and possibly the connection with the other / previous presentation, etc. Everyone (at least students who do presentations in pair) is expected to be familiar with the discussed papers prior to the seminar. Following each presentation there will be a discussion with all course participants about the contributions of the papers and the questions remaining open. Active participation is strongly encouraged.

Target students: The course is mainly aimed at doctoral students and advanced master's students. Note that due to the format of the course, the number of students is limited to maximum 15.

Prerequisites: Basic Mathematics, familiarity with Machine Learning basic principles is a plus.

Time and place: Period V, Lectures: Mondays, 10:15-12:00.

3 ECTS for presenting papers and active participation; 5 ECTS, requirement for 3 ECTS + doing one of the proposed projects; Grades: Pass or Fail.

Course instructors:  Xiangju Qin, Paul Blomst, Advisor: Prof. Samuel Kaski

More detailed schedule, course work, and materials will be added later. Contact the instructors (firstname.lastname@)