Search result: Catalogue data in Spring Semester 2023

Computer Science Master Information
Majors
Major in Data Management Systems
Core Courses
NumberTitleTypeECTSHoursLecturers
263-3855-00LCloud Computing Architecture Information W9 credits3V + 2U + 3AG. Alonso, A. Klimovic
AbstractCloud computing hosts a wide variety of online services that we use on a daily basis, including web search, social networks, and video streaming. This course will cover how datacenter hardware, systems software, and application frameworks are designed for the cloud.
Learning objectiveAfter successful completion of this course, students will be able to: 1) reason about performance, energy efficiency, and availability tradeoffs in the design of cloud system software, 2) describe how datacenter hardware is organized and explain why it is organized as such, 3) implement cloud applications as well as analyze and optimize their performance.
ContentIn this course, we study how datacenter hardware, systems software, and applications are designed at large scale for the cloud. The course covers topics including server design, cluster management, large-scale storage systems, serverless computing, data analytics frameworks, and performance analysis.
Lecture notesLecture slides will be available on the course website.
Prerequisites / NoticeUndergraduate courses in 1) computer architecture and 2) operating systems, distributed systems, and/or database systems are strongly recommended.
Elective Courses
NumberTitleTypeECTSHoursLecturers
263-3800-00LAdvanced Operating Systems Information Restricted registration - show details W7 credits2V + 2U + 2AD. Cock, T. Roscoe
AbstractThis course is intended to give students a thorough understanding of design and implementation issues for modern operating systems, with a particular emphasis on the challenges of modern hardware features. We will cover key design issues in implementing an operating system, such as memory management, scheduling, protection, inter-process communication, device drivers, and file systems.
Learning objectiveThe goals of the course are, firstly, to give students:

1. A broader perspective on OS design than that provided by knowledge of Unix or Windows, building on the material in a standard undergraduate operating systems class

2. Practical experience in dealing directly with the concurrency, resource management, and abstraction problems confronting OS designers and implementers

3. A glimpse into future directions for the evolution of OS and computer hardware design
ContentThe course is based on practical implementation work, in C and assembly language, and requires solid knowledge of both. The work is mostly carried out in teams of 3-4, using real hardware, and is a mixture of team milestones and individual projects which fit together into a complete system at the end. Emphasis is also placed on a final report which details the complete finished artifact, evaluates its performance, and discusses the choices the team made while building it.
Prerequisites / NoticeThe course is based around a milestone-oriented project, where students work in small groups to implement major components of a microkernel-based operating system. The final assessment will be a combination grades awarded for milestones during the course of the project, a final written report on the work, and a set of test cases run on the final code.
227-0558-00LPrinciples of Distributed Computing Information W7 credits2V + 2U + 2AR. Wattenhofer
AbstractWe study the fundamental issues underlying the design of distributed systems: communication, coordination, fault-tolerance, locality, parallelism, self-organization, symmetry breaking, synchronization, uncertainty. We explore essential algorithmic ideas and lower bound techniques.
Learning objectiveDistributed computing is essential in modern computing and communications systems. Examples are on the one hand large-scale networks such as the Internet, and on the other hand multiprocessors such as your new multi-core laptop. This course introduces the principles of distributed computing, emphasizing the fundamental issues underlying the design of distributed systems and networks: communication, coordination, fault-tolerance, locality, parallelism, self-organization, symmetry breaking, synchronization, uncertainty. We explore essential algorithmic ideas and lower bound techniques, basically the "pearls" of distributed computing. We will cover a fresh topic every week.
ContentDistributed computing models and paradigms, e.g. message passing, shared memory, synchronous vs. asynchronous systems, time and message complexity, peer-to-peer systems, small-world networks, social networks, sorting networks, wireless communication, and self-organizing systems.

Distributed algorithms, e.g. leader election, coloring, covering, packing, decomposition, spanning trees, mutual exclusion, store and collect, arrow, ivy, synchronizers, diameter, all-pairs-shortest-path, wake-up, and lower bounds
Lecture notesAvailable.
LiteratureLecture Notes By Roger Wattenhofer. These lecture notes are taught at about a dozen different universities through the world.

Mastering Distributed Algorithms
Roger Wattenhofer
Inverted Forest Publishing, 2020. ISBN 979-8628688267

Distributed Computing: Fundamentals, Simulations and Advanced Topics
Hagit Attiya, Jennifer Welch.
McGraw-Hill Publishing, 1998, ISBN 0-07-709352 6

Introduction to Algorithms
Thomas Cormen, Charles Leiserson, Ronald Rivest.
The MIT Press, 1998, ISBN 0-262-53091-0 oder 0-262-03141-8

Disseminatin of Information in Communication Networks
Juraj Hromkovic, Ralf Klasing, Andrzej Pelc, Peter Ruzicka, Walter Unger.
Springer-Verlag, Berlin Heidelberg, 2005, ISBN 3-540-00846-2

Introduction to Parallel Algorithms and Architectures: Arrays, Trees, Hypercubes
Frank Thomson Leighton.
Morgan Kaufmann Publishers Inc., San Francisco, CA, 1991, ISBN 1-55860-117-1

Distributed Computing: A Locality-Sensitive Approach
David Peleg.
Society for Industrial and Applied Mathematics (SIAM), 2000, ISBN 0-89871-464-8
Prerequisites / NoticeCourse pre-requisites: Interest in algorithmic problems. (No particular course needed.)
CompetenciesCompetencies
Subject-specific CompetenciesConcepts and Theoriesassessed
Techniques and Technologiesassessed
Method-specific CompetenciesAnalytical Competenciesassessed
Decision-makingassessed
Problem-solvingassessed
Major in Machine Intelligence
Core Courses
NumberTitleTypeECTSHoursLecturers
261-5110-00LOptimization for Data Science Information W10 credits3V + 2U + 4AB. Gärtner, N. He
AbstractThis course provides an in-depth theoretical treatment of optimization methods that are relevant in data science.
Learning objectiveUnderstanding the guarantees and limits of relevant optimization methods used in data science. Learning theoretical paradigms and techniques to deal with optimization problems arising in data science.
ContentThis course provides an in-depth theoretical treatment of classical and modern optimization methods that are relevant in data science.

After a general discussion about the role that optimization has in the process of learning from data, we give an introduction to the theory of (convex) optimization. Based on this, we present and analyze algorithms in the following four categories: first-order methods (gradient and coordinate descent, Frank-Wolfe, subgradient and mirror descent, stochastic and incremental gradient methods); second-order methods (Newton and quasi Newton methods); non-convexity (local convergence, provable global convergence, cone programming, convex relaxations); min-max optimization (extragradient methods).

The emphasis is on the motivations and design principles behind the algorithms, on provable performance bounds, and on the mathematical tools and techniques to prove them. The goal is to equip students with a fundamental understanding about why optimization algorithms work, and what their limits are. This understanding will be of help in selecting suitable algorithms in a given application, but providing concrete practical guidance is not our focus.
Prerequisites / NoticeA solid background in analysis and linear algebra; some background in theoretical computer science (computational complexity, analysis of algorithms); the ability to understand and write mathematical proofs.
263-3710-00LMachine Perception Information Restricted registration - show details W8 credits3V + 2U + 2AO. Hilliges, J. Song
AbstractRecent developments in neural networks have drastically advanced the performance of machine perception systems in a variety of areas including computer vision, robotics, and human shape modeling This course is a deep dive into deep learning algorithms and architectures with applications to a variety of perceptual and generative tasks.
Learning objectiveStudents will learn about fundamental aspects of modern deep learning approaches for perception and generation. Students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in learning-based computer vision, robotics, and shape modeling. The optional final project assignment will involve training a complex neural network architecture and applying it to a real-world dataset.

The core competency acquired through this course is a solid foundation in deep-learning algorithms to process and interpret human-centric signals. In particular, students should be able to develop systems that deal with the problem of recognizing people in images, detecting and describing body parts, inferring their spatial configuration, performing action/gesture recognition from still images or image sequences, also considering multi-modal data, among others.
ContentWe will focus on teaching: how to set up the problem of machine perception, the learning algorithms, network architectures, and advanced deep learning concepts in particular probabilistic deep learning models.

The course covers the following main areas:
I) Foundations of deep learning.
II) Advanced topics like probabilistic generative modeling of data (latent variable models, generative adversarial networks, auto-regressive models, invertible neural networks, diffusion models).
III) Deep learning in computer vision, human-computer interaction, and robotics.

Specific topics include:
I) Introduction to Deep Learning:
a) Neural Networks and training (i.e., backpropagation)
b) Feedforward Networks
c) Timeseries modelling (RNN, GRU, LSTM)
d) Convolutional Neural Networks
II) Advanced topics:
a) Latent variable models (VAEs)
b) Generative adversarial networks (GANs)
c) Autoregressive models (PixelCNN, PixelRNN, TCN, Transformer)
d) Invertible Neural Networks / Normalizing Flows
e) Coordinate-based networks (neural implicit surfaces, NeRF)
f) Diffusion models
III) Applications in machine perception and computer vision:
a) Fully Convolutional architectures for dense per-pixel tasks (i.e., instance segmentation)
b) Pose estimation and other tasks involving human activity
c) Neural shape modeling (implicit surfaces, neural radiance fields)
d) Deep Reinforcement Learning and Applications in Physics-Based Behavior Modeling
LiteratureDeep Learning
Book by Ian Goodfellow and Yoshua Bengio
Prerequisites / NoticeThis is an advanced grad-level course that requires a background in machine learning. Students are expected to have a solid mathematical foundation, in particular in linear algebra, multivariate calculus, and probability. The course will focus on state-of-the-art research in deep learning and will not repeat the basics of machine learning

Please take note of the following conditions:
1) Students must have taken the exam in Machine Learning (252-0535-00) or have acquired equivalent knowledge
2) All practical exercises will require basic knowledge of Python and will use libraries such as Pytorch, scikit-learn, and scikit-image. We will provide introductions to Pytorch and other libraries that are needed but will not provide introductions to basic programming or Python.

The following courses are strongly recommended as prerequisites:
* "Visual Computing" or "Computer Vision"

The course will be assessed by a final written examination in English. No course materials or electronic devices can be used during the examination. Note that the examination will be based on the contents of the lectures, the associated reading materials, and the exercises.

The exam will be a 3-hour end-of-term exam and take place at the end of the teaching period.
CompetenciesCompetencies
Subject-specific CompetenciesConcepts and Theoriesassessed
Techniques and Technologiesassessed
Method-specific CompetenciesAnalytical Competenciesassessed
Problem-solvingassessed
Project Managementassessed
Social CompetenciesCommunicationfostered
Cooperation and Teamworkfostered
Leadership and Responsibilityfostered
Self-presentation and Social Influence fostered
Personal CompetenciesAdaptability and Flexibilityfostered
Creative Thinkingfostered
Critical Thinkingfostered
Integrity and Work Ethicsfostered
Self-direction and Self-management fostered
Elective Courses
NumberTitleTypeECTSHoursLecturers
252-0526-00LStatistical Learning Theory Information W8 credits3V + 2U + 2AJ. M. Buhmann
AbstractThe course covers advanced methods of statistical learning:

- Variational methods and optimization.
- Deterministic annealing.
- Clustering for diverse types of data.
- Model validation by information theory.
Learning objectiveThe course surveys recent methods of statistical learning. The fundamentals of machine learning, as presented in the courses "Introduction to Machine Learning" and "Advanced Machine Learning", are expanded from the perspective of statistical learning.
Content- Variational methods and optimization. We consider optimization approaches for problems where the optimizer is a probability distribution. We will discuss concepts like maximum entropy, information bottleneck, and deterministic annealing.

- Clustering. This is the problem of sorting data into groups without using training samples. We discuss alternative notions of "similarity" between data points and adequate optimization procedures.

- Model selection and validation. This refers to the question of how complex the chosen model should be. In particular, we present an information theoretic approach for model validation.

- Statistical physics models. We discuss approaches for approximately optimizing large systems, which originate in statistical physics (free energy minimization applied to spin glasses and other models). We also study sampling methods based on these models.
Lecture notesA draft of a script will be provided. Lecture slides will be made available.
LiteratureHastie, Tibshirani, Friedman: The Elements of Statistical Learning, Springer, 2001.

L. Devroye, L. Gyorfi, and G. Lugosi: A probabilistic theory of pattern recognition. Springer, New York, 1996
Prerequisites / NoticeKnowledge of machine learning (introduction to machine learning and/or advanced machine learning)
Basic knowledge of statistics.
252-0579-00L3D Vision Information W5 credits3G + 1AM. Pollefeys, D. B. Baráth
AbstractThe course covers camera models and calibration, feature tracking and matching, camera motion estimation via simultaneous localization and mapping (SLAM) and visual odometry (VO), epipolar and mult-view geometry, structure-from-motion, (multi-view) stereo, augmented reality, and image-based (re-)localization.
Learning objectiveAfter attending this course, students will:
1. understand the core concepts for recovering 3D shape of objects and scenes from images and video.
2. be able to implement basic systems for vision-based robotics and simple virtual/augmented reality applications.
3. have a good overview over the current state-of-the art in 3D vision.
4. be able to critically analyze and asses current research in this area.
ContentThe goal of this course is to teach the core techniques required for robotic and augmented reality applications: How to determine the motion of a camera and how to estimate the absolute position and orientation of a camera in the real world. This course will introduce the basic concepts of 3D Vision in the form of short lectures, followed by student presentations discussing the current state-of-the-art. The main focus of this course are student projects on 3D Vision topics, with an emphasis on robotic vision and virtual and augmented reality applications.
261-5120-00LMachine Learning for Health Care Information Restricted registration - show details W5 credits2V + 2AV. Boeva, J. Vogt, M. Kuznetsova
AbstractThe course will review the most relevant methods and applications of Machine Learning in Biomedicine, discuss the main challenges they present and their current technical problems.
Learning objectiveDuring the last years, we have observed a rapid growth in the field of Machine Learning (ML), mainly due to improvements in ML algorithms, the increase of data availability and a reduction in computing costs. This growth is having a profound impact in biomedical applications, where the great variety of tasks and data types enables us to get benefit of ML algorithms in many different ways. In this course we will review the most relevant methods and applications of ML in biomedicine, discuss the main challenges they present and their current technical solutions.
ContentThe course will consist of four topic clusters that will cover the most relevant applications of ML in Biomedicine:
1) Structured time series: Temporal time series of structured data often appear in biomedical datasets, presenting challenges as containing variables with different periodicities, being conditioned by static data, etc.
2) Medical notes: Vast amount of medical observations are stored in the form of free text, we will analyze stategies for extracting knowledge from them.
3) Medical images: Images are a fundamental piece of information in many medical disciplines. We will study how to train ML algorithms with them.
4) Genomics data: ML in genomics is still an emerging subfield, but given that genomics data are arguably the most extensive and complex datasets that can be found in biomedicine, it is expected that many relevant ML applications will arise in the near future. We will review and discuss current applications and challenges.
Prerequisites / NoticeData Structures & Algorithms, Introduction to Machine Learning, Statistics/Probability, Programming in Python, Unix Command Line

Relation to Course 261-5100-00 Computational Biomedicine: This course is a continuation of the previous course with new topics related to medical data and machine learning. The format of Computational Biomedicine II will also be different. It is helpful but not essential to attend Computational Biomedicine before attending Computational Biomedicine II.
263-5000-00LComputational Semantics for Natural Language Processing Information W6 credits2V + 1U + 2AM. Sachan
AbstractThis course presents an introduction to Natural language processing (NLP) with an emphasis on computational semantics i.e. the process of constructing and reasoning with meaning representations of natural language text.
Learning objectiveThe objective of the course is to learn about various topics in computational semantics and its importance in natural language processing methodology and research. Exercises and the project will be key parts of the course so the students will be able to gain hands-on experience with state-of-the-art techniques in the field.
ContentWe will take a modern view of the topic, and focus on various statistical and deep learning approaches for computation semantics. We will also overview various primary areas of research in language processing and discuss how the computational semantics view can help us make advances in NLP.
Lecture notesLecture slides will be made available at the course Web site.
LiteratureNo textbook is required, but there will be regularly assigned readings from research literature, linked to the course website.
Prerequisites / NoticeThe student should have successfully completed a graduate level class in machine learning (252-0220-00L), deep learning (263-3210-00L) or natural language processing (252-3005-00L) before. Similar courses from other universities are acceptable too.
263-5051-00LAI Center Projects in Machine Learning Research Information Restricted registration - show details
Last cancellation/deregistration date for this ungraded semester performance: Friday, 17 March 2023! Please note that after that date no deregistration will be accepted and the course will be considered as "fail".
W4 credits2V + 1AA. Ilic, N. Davoudi, M. El-Assady, F. Engelmann, S. Gashi, T. Kontogianni, A. Marx, B. Moseley, G. Ramponi, X. Shen, M. Sorbaro Sindaci
AbstractThe course will give students an overview of selected topics in advanced machine learning that are currently subjects of active research. The course concludes with a final project.
Learning objectiveThe overall objective is to give students a concrete idea of what working in contemporary machine learning research is like and inform them about current research performed at ETH.

In this course, students will be able to get an overview of current research topics in different specialized areas. In the final project, students will be able to build experience in practical aspects of machine learning research, including research literature, aspects of implementation, and reproducibility challenges.
ContentThe course will be structured as sections taught by different postdocs specialized in the relevant fields. Each section will showcase an advanced research topic in machine learning, first introducing it and motivating it in the context of current technological or scientific advancement, then providing practical applications that students can experiment with, ideally with the aim of reproducing a known result in the specific field.

A tentative list of topics for this year:
- fully supervised 3D scene understanding
- weakly supervised 3D scene understanding
- causal discovery
- biological and artificial neural networks
- reinforcement learning
- visual text analytics
- human-centered AI
- representation learning.

The last weeks of the course will be reserved for the implementation of the final project. The students will be assigned group projects in one of the presented areas, based on their preferences. The outcomes will be made into a scientific poster and students will be asked to present the projects to the other groups in a joint poster session.
Prerequisites / NoticeParticipants should have basic knowledge about machine learning and statistics (e.g. Introduction to Machine Learning course or equivalent) and programming.
263-5052-00LInteractive Machine Learning: Visualization & Explainability Information Restricted registration - show details W5 credits3G + 1AM. El-Assady
AbstractVisual Analytics supports the design of human-in-the-loop interfaces that enable human-machine collaboration. In this course, will go through the fundamentals of designing interactive visualizations, later applying them to explain and interact with machine leaning models.
Learning objectiveThe goal of the course is to introduce techniques for interactive information visualization and to apply these on understanding, diagnosing, and refining machine learning models.
ContentInteractive, mixed-initiative machine learning promises to combine the efficiency of automation with the effectiveness of humans for a collaborative decision-making and problem-solving process. This can be facilitated through co-adaptive visual interfaces.

This course will first introduce the foundations of information visualization design based on data charecteristics, e.g., high-dimensional, geo-spatial, relational, temporal, and textual data.

Second, we will discuss interaction techniques and explanation strategies to enable explainable machine learning with the tasks of understanding, diagnosing, and refining machine learning models.

Tentative list of topics:
1. Visualization and Perception
2. Interaction and Explanation
3. Systems Overview
Lecture notesCourse material will be provided in form of slides.
LiteratureWill be provided during the course.
Prerequisites / NoticeBasic understanding of machine learning as taught at the Bachelor's level.
263-5255-00LFoundations of Reinforcement Learning Information Restricted registration - show details W7 credits3V + 3AN. He
AbstractReinforcement learning (RL) has been in the limelight of many recent breakthroughs in artificial intelligence. This course focuses on theoretical and algorithmic foundations of reinforcement learning, through the lens of optimization, modern approximation, and learning theory. The course targets M.S. students with strong research interests in reinforcement learning, optimization, and control.
Learning objectiveThis course aims to provide students with an advanced introduction of RL theory and algorithms as well as bring them near the frontier of this active research field.

By the end of the course, students will be able to
- Identify the strengths and limitations of various reinforcement learning algorithms;
- Formulate and solve sequential decision-making problems by applying relevant reinforcement learning tools;
- Generalize or discover “new” applications, algorithms, or theories of reinforcement learning towards conducting independent research on the topic.
ContentBasic topics include fundamentals of Markov decision processes, approximate dynamic programming, linear programming and primal-dual perspectives of RL, model-based and model-free RL, policy gradient and actor-critic algorithms, Markov games and multi-agent RL. If time allows, we will also discuss advanced topics such as batch RL, inverse RL, causal RL, etc. The course keeps strong emphasis on in-depth understanding of the mathematical modeling and theoretical properties of RL algorithms.
Lecture notesLecture notes will be posted on Moodle.
LiteratureDynamic Programming and Optimal Control, Vol I & II, Dimitris Bertsekas
Reinforcement Learning: An Introduction, Second Edition, Richard Sutton and Andrew Barto.
Algorithms for Reinforcement Learning, Csaba Czepesvári.
Reinforcement Learning: Theory and Algorithms, Alekh Agarwal, Nan Jiang, Sham M. Kakade.
Prerequisites / NoticeStudents are expected to have strong mathematical background in linear algebra, probability theory, optimization, and machine learning.
263-5351-00LMachine Learning for Genomics Information Restricted registration - show details
The deadline for deregistering expires at the end of the third week of the semester. Students who are still registered after that date, but do not provide project work, do not participate in paper presentation sessions and/or do not show up for the exam, will officially fail the course.
W5 credits2V + 1U + 1AV. Boeva
AbstractThe course reviews solutions that machine learning provides to the most challenging questions in human genomics.
Learning objectiveOver the last few years, the parallel development of machine learning methods and molecular profiling technologies for human cells, such as sequencing, created an extremely powerful tool to get insights into the cellular mechanisms in healthy and diseased contexts. In this course, we will discuss the state-of-the-art machine learning methodology solving or attempting to solve common problems in human genomics. At the end of the course, you will be familiar with (1) classical and advanced machine learning architectures used in genomics, (2) bioinformatics analysis of human genomic and transcriptomic data, and (3) data types used in this field.
Content- Short introduction to major concepts of molecular biology: DNA, genes, genome, central dogma, transcription factors, epigenetic code, DNA methylation, signaling pathways
- Prediction of transcription factor binding sites, open chromatin, histone marks, promoters, nucleosome positioning (convolutional neural networks, position weight matrices)
- Prediction of variant effects and gene expression (hidden Markov models, topic models)
- Deconvolution of mixed signal
- DNA, RNA and protein folding (RNN, LSTM, transformers)
- Data imputation for single cell RNA-seq data, clustering and annotation (diffusion and methods on graphs)
- Batch correction (autoencoders, optimal transport)
- Survival analysis (Cox proportional hazard model, regularization penalties, multi-omics, multi-tasking)
Prerequisites / NoticeIntroduction to Machine Learning, Statistics/Probability, Programming in Python, Unix Command Line
263-5352-00LAdvanced Formal Language Theory Information W6 credits4G + 1AR. Cotterell
AbstractThis course serves as an introduction to various advanced topics in formal language theory.
Learning objectiveThe objective of the course is to learn and understand a variety of topics in advanced formal language theory.
ContentThis course serves as an introduction to various advanced topics in formal language theory. The primary focus of the course is on weighted formalisms, which can easily be applied in machine learning. Topics include finite-state machines as well as the algorithms that are commonly used for their manipulation. We will also cover weighted context-free grammars, weighted tree automata, and weighted mildly context-sensitive formalisms.
263-5353-10LPhilosophy of Language and Computation II (with Case Study) Information W5 credits2V + 1U + 1AR. Cotterell, J. L. Gastaldi
AbstractUnderstand the philosophical underpinnings of language-based artificial intelligence.
Learning objectiveThis graduate class, taught like a seminar, is designed to help you understand the philosophical underpinnings of modern work in natural language processing (NLP), most of which is centered around statistical machine learning applied to natural language data.
ContentThis graduate class, taught like a seminar, is designed to help you understand the philosophical underpinnings of modern work in natural language processing (NLP), most of which is centered around statistical machine learning applied to natural language data. The course is a year-long journey, but the second half (Spring 2023) does not depend on the first (Fall 2022) and thus either half may be taken independently. In each semester, we divide the class time into three modules. Each module is centered around a philosophical topic. After discussing logical, structuralist, and generative approaches to language in the first semester, in the second semester we will focus on information, language games, and pragmatics. The modules will be four weeks long. During the first two weeks of a module, we will read and discuss original texts and supplementary criticism. During the second two weeks, we will read recent NLP papers and discuss how the authors of those works are building on philosophical insights into our conception of language—perhaps implicitly or unwittingly.
LiteratureThe literature will be provided by the instructors on the class website
263-5354-00LLarge Language Models Information W8 credits3V + 2U + 2AR. Cotterell, M. Sachan, F. Tramèr, C. Zhang
AbstractLarge language models have become one of the most commonly deployed NLP inventions. In the past half-decade, their integration into core natural language processing tools has dramatically increased the performance of such tools, and they have entered the public discourse surrounding artificial intelligence.
Learning objectiveTo understand the mathematical foundations of large language models as well as how to implement them.
ContentWe start with the probabilistic foundations of language models, i.e., covering what constitutes a language model from a formal, theoretical perspective. We then discuss how to construct and curate training corpora, and introduce many of the neural-network architectures often used to instantiate language models at scale. The course covers aspects of systems programming, discussion of privacy and harms, as well as applications of language models in NLP and beyond.
LiteratureThe lecture notes will be supplemented with various readings from the literature.
227-0434-10LMathematics of Information Information W8 credits3V + 2U + 2AH. Bölcskei
AbstractThe class focuses on mathematical aspects of

1. Information science: Sampling theorems, frame theory, compressed sensing, sparsity, super-resolution, spectrum-blind sampling, subspace algorithms, dimensionality reduction

2. Learning theory: Approximation theory, greedy algorithms, uniform laws of large numbers, Rademacher complexity, Vapnik-Chervonenkis dimension
Learning objectiveThe aim of the class is to familiarize the students with the most commonly used mathematical theories in data science, high-dimensional data analysis, and learning theory. The class consists of the lecture and exercise sessions with homework problems.
ContentMathematics of Information

1. Signal representations: Frame theory, wavelets, Gabor expansions, sampling theorems, density theorems

2. Sparsity and compressed sensing: Sparse linear models, uncertainty relations in sparse signal recovery, super-resolution, spectrum-blind sampling, subspace algorithms (ESPRIT), estimation in the high-dimensional noisy case, Lasso

3. Dimensionality reduction: Random projections, the Johnson-Lindenstrauss Lemma

Mathematics of Learning

4. Approximation theory: Nonlinear approximation theory, best M-term approximation, greedy algorithms, fundamental limits on compressibility of signal classes, Kolmogorov-Tikhomirov epsilon-entropy of signal classes, optimal compression of signal classes

5. Uniform laws of large numbers: Rademacher complexity, Vapnik-Chervonenkis dimension, classes with polynomial discrimination
Lecture notesDetailed lecture notes will be provided at the beginning of the semester.
Prerequisites / NoticeThis course is aimed at students with a background in basic linear algebra, analysis, statistics, and probability.

We encourage students who are interested in mathematical data science to take both this course and "401-4944-20L Mathematics of Data Science" by Prof. A. Bandeira. The two courses are designed to be complementary.

H. Bölcskei and A. Bandeira
401-3632-00LComputational StatisticsW8 credits3V + 1UM. Mächler
AbstractWe discuss modern statistical methods for data analysis, including methods for data exploration, prediction and inference. We pay attention to algorithmic aspects, theoretical properties and practical considerations. The class is hands-on and methods are applied using the statistical programming language R.
Learning objectiveThe student obtains an overview of modern statistical methods for data analysis, including their algorithmic aspects and theoretical properties. The methods are applied using the statistical programming language R.
ContentSee the class website
Prerequisites / NoticeAt least one semester of (basic) probability and statistics.

Programming experience is helpful but not required.
CompetenciesCompetencies
Subject-specific CompetenciesConcepts and Theoriesassessed
Techniques and Technologiesassessed
Method-specific CompetenciesAnalytical Competenciesassessed
Media and Digital Technologiesassessed
Problem-solvingassessed
Personal CompetenciesCreative Thinkingassessed
Critical Thinkingassessed
Major in Secure and Reliable Systems
Core Courses
NumberTitleTypeECTSHoursLecturers
263-2815-00LAutomated Software Testing Information Restricted registration - show details
Last cancellation/deregistration date for this graded semester performance: 17 March 2023! Please note that after that date no deregistration will be accepted and the course will be considered as "fail".
W7 credits2V + 1U + 3AZ. Su
AbstractThis course introduces students to classic and modern techniques for the automated testing and analysis of software systems for reliability, security, and performance. It covers both techniques and their applications in various domains (e.g., compilers, databases, theorem provers, operating systems, machine/deep learning, and mobile applications), focusing on the latest, important results.
Learning objective* Learn fundamental and practical techniques for software testing and analysis

* Understand the challenges, open issues and opportunities across a variety of domains (security/systems/compilers/databases/mobile/AI/education)

* Understand how latest automated testing and analysis techniques work

* Gain conceptual and practical experience in techniques/tools for reliability, security, and performance

* Learn how to perform original and impactful research in this area
ContentThe course will be organized into the following components: (1) classic and modern testing and analysis techniques (coverage metrics, mutation testing, metamorphic testing, combinatorial testing, symbolic execution, fuzzing, static analysis, etc.), (2) latest results on techniques and applications from diverse domains, and (3) open challenges and opportunities.

A major component of this course is a class project. All students (individually or two-person teams) are expected to select and complete a course project. Ideally, the project is original research related in a broad sense to automated software testing and analysis. Potential project topics will also be suggested by the teaching staff.

Students must select a project and write a one or two pages proposal describing why what the proposed project is interesting and giving a work schedule. Students will also write a final report describing the project and prepare a 20-30 minute presentation at the end of the course.

The due dates for the project proposal, final report, and project presentation will be announced.

The course will cover results from the Advanced Software Technologies (AST) Lab at ETH as well as notable results elsewhere, providing good opportunities for potential course project topics as well as MSc project/thesis topics.
Lecture notesLecture notes/slides and other lecture materials/handouts will be available online.
LiteratureReading material and links to tools will be published on the course website.
Prerequisites / NoticeThe prerequisites for this course are some programming and algorithmic experience. Background and experience in software engineering, programming languages/compilers, and security (as well as operating systems and databases) can be beneficial.
263-2925-00LProgram Analysis for System Security and Reliability Information
Does not take place this semester.
W7 credits2V + 1U + 3AM. Vechev
AbstractSecurity issues in modern systems (blockchains, datacenters, deep learning, etc.) result in billions of losses due to hacks and system downtime. This course introduces fundamental techniques (ranging over automated analysis, machine learning, synthesis, zero-knowledge, differential privacy, and their combinations) that can be applied in practice so to build more secure and reliable modern systems.
Learning objective* Understand the fundamental techniques used to create modern security and reliability analysis engines that are used worldwide.

* Understand how symbolic techniques are combined with machine learning (e.g., deep learning, reinforcement learning) so to create new kinds of learning-based analyzers.

* Understand how to quantify and fix security and reliability issues in modern deep learning models.

* Understand open research questions from both theoretical and practical perspectives.
ContentPlease see: https://www.sri.inf.ethz.ch/teaching/pass2022 for detailed course content.
  •  Page  1  of  7 Next page Last page     All