Suchergebnis: Katalogdaten im Herbstsemester 2019

Nummer	Titel	Typ	ECTS	Umfang	Dozierende
DAS in Data Science
Kernfächer
Einführungskurse
227-0427-00L	Signal Analysis, Models, and Machine Learning	W	6 KP	4G	H.‑A. Loeliger
Kurzbeschreibung	Mathematical methods in signal processing and machine learning. I. Linear signal representation and approximation: Hilbert spaces, LMMSE estimation, regularization and sparsity. II. Learning linear and nonlinear functions and filters: neural networks, kernel methods. III. Structured statistical models: hidden Markov models, factor graphs, Kalman filter, Gaussian models with sparse events.
Lernziel	The course is an introduction to some basic topics in signal processing and machine learning.
Inhalt	Part I - Linear Signal Representation and Approximation: Hilbert spaces, least squares and LMMSE estimation, projection and estimation by linear filtering, learning linear functions and filters, L2 regularization, L1 regularization and sparsity, singular-value decomposition and pseudo-inverse, principal-components analysis. Part II - Learning Nonlinear Functions: fundamentals of learning, neural networks, kernel methods. Part III - Structured Statistical Models and Message Passing Algorithms: hidden Markov models, factor graphs, Gaussian message passing, Kalman filter and recursive least squares, Monte Carlo methods, parameter estimation, expectation maximization, linear Gaussian models with sparse events.
Skript	Lecture notes.
Voraussetzungen / Besonderes	Prerequisites: - local bachelors: course "Discrete-Time and Statistical Signal Processing" (5. Sem.) - others: solid basics in linear algebra and probability theory

Capstone-Projekt
Nummer	Titel	Typ	ECTS	Umfang	Dozierende
266-0100-00L	Capstone Project Only for DAS in Data Science.	O	8 KP	17A	F. Perez Cruz, O. Verscheure, Professor/innen
Kurzbeschreibung	The capstone project is part of the DAS in Data Science and is an opportunity to apply the knowledge acquired in the program in an independent, real-world project. Deadline for a project the following semester conducted at the SDSC is mid June/mid December.
Lernziel	To apply the knowledge acquired in the program in an independent, real-world project.
Inhalt	The capstone project can be done under the supervision of the Swiss Data Science Center, or of any core or adjunct faculty of Data Science.

Vertiefungen
Hardware for Machine Learning Wird im Frühjahrssemester angeboten.
Nummer	Titel	Typ	ECTS	Umfang	Dozierende
227-0155-00L	Machine Learning on Microcontrollers Registration in this class requires the permission of the instructors. Class size will be limited to 25. Preference is given to students in the MSc EEIT.	W	3 KP	2G	M. Magno, L. Benini
Kurzbeschreibung	Machine Learning (ML) and artificial intelligence are pervading the digital society. Today, even low power embedded systems are incorporating ML, becoming increasingly “smart”. This lecture gives an overview of ML methods and algorithms to process and extract useful near-sensor information in end-nodes of the “internet-of-things”, using low-power microcontrollers/ processors (ARM-Cortex-M; RISC-V)
Lernziel	Learn how to Process data from sensors and how to extract useful information with low power microprocessors using ML techniques. We will analyze data coming from real low-power sensors (accelerometers, microphones, ExG bio-signals, cameras…). The main objective is to study in details how Machine Learning algorithms can be adapted to the performance constraints and limited resources of low-power microcontrollers.
Inhalt	The final goal of the course is a deep understanding of machine learning and its practical implementation on single- and multi-core microcontrollers, coupled with performance and energy efficiency analysis and optimization. The main topics of the course include: - Sensors and sensor data acquisition with low power embedded systems - Machine Learning: Overview of supervised and unsupervised learning and in particular supervised learning (Bayes Decision Theory, Decision Trees, Random Forests, kNN-Methods, Support Vector Machines, Convolutional Networks and Deep Learning) - Low-power embedded systems and their architecture. Low Power microcontrollers (ARM-Cortex M) and RISC-V-based Parallel Ultra Low Power (PULP) systems-on-chip. - Low power smart sensor system design: hardware-software tradeoffs, analysis, and optimization. Implementation and performance evaluation of ML in battery-operated embedded systems. The laboratory exercised will show how to address concrete design problems, like motion, gesture recognition, emotion detection, image and sound classification, using real sensors data and real MCU boards. Presentations from Ph.D. students and the visit to the Digital Circuits and Systems Group will introduce current research topics and international research projects.
Skript	Script and exercise sheets. Books will be suggested during the course.
Voraussetzungen / Besonderes	Prerequisites: C language programming. Basics of Digital Signal Processing. Basics of processor and computer architecture. Some exposure to machine learning concepts is also desirable

Image Analysis & Computer Vision
Nummer	Titel	Typ	ECTS	Umfang	Dozierende
263-5902-00L	Computer Vision	W	7 KP	3V + 1U + 2A	M. Pollefeys, V. Ferrari, L. Van Gool
Kurzbeschreibung	The goal of this course is to provide students with a good understanding of computer vision and image analysis techniques. The main concepts and techniques will be studied in depth and practical algorithms and approaches will be discussed and explored through the exercises.
Lernziel	The objectives of this course are: 1. To introduce the fundamental problems of computer vision. 2. To introduce the main concepts and techniques used to solve those. 3. To enable participants to implement solutions for reasonably complex problems. 4. To enable participants to make sense of the computer vision literature.
Inhalt	Camera models and calibration, invariant features, Multiple-view geometry, Model fitting, Stereo Matching, Segmentation, 2D Shape matching, Shape from Silhouettes, Optical flow, Structure from motion, Tracking, Object recognition, Object category recognition
Voraussetzungen / Besonderes	It is recommended that students have taken the Visual Computing lecture or a similar course introducing basic image processing concepts before taking this course.

Neural Information Processing
Nummer	Titel	Typ	ECTS	Umfang	Dozierende
227-0421-00L	Learning in Deep Artificial and Biological Neuronal Networks	W	4 KP	3G	B. Grewe
Kurzbeschreibung	Deep-Learning (DL) a brain-inspired weak for of AI allows training of large artificial neuronal networks (ANNs) that, like humans, can learn real-world tasks such as recognizing objects in images. However, DL is far from being understood and investigating learning in biological networks might serve again as a compelling inspiration to think differently about state-of-the-art ANN training methods.
Lernziel	The main goal of this lecture is to provide a comprehensive overview into the learning principles neuronal networks as well as to introduce a diverse skill set (e.g. simulating a spiking neuronal network) that is required to understand learning in large, hierarchical neuronal networks. To achieve this the lectures and exercises will merge ideas, concepts and methods from machine learning and neuroscience. These will include training basic ANNs, simulating spiking neuronal networks as well as being able to read and understand the main ideas presented in today’s neuroscience papers. After this course students will be able to: - read and understand the main ideas and methods that are presented in today’s neuroscience papers - explain the basic ideas and concepts of plasticity in the mammalian brain - implement alternative ANN learning algorithms to ‘error backpropagation’ in order to train deep neuronal networks. - use a diverse set of ANN regularization methods to improve learning - simulate spiking neuronal networks that learn simple (e.g. digit classification) tasks in a supervised manner.
Inhalt	Deep-learning a brain-inspired weak form of AI allows training of large artificial neuronal networks (ANNs) that, like humans, can learn real-world tasks such as recognizing objects in images. The origins of deep hierarchical learning can be traced back to early neuroscience research by Hubel and Wiesel in the 1960s, who first described the neuronal processing of visual inputs in the mammalian neocortex. Similar to their neocortical counterparts ANNs seem to learn by interpreting and structuring the data provided by the external world. However, while on specific tasks such as playing (video) games deep ANNs outperform humans (Minh et al, 2015, Silver et al., 2018), ANNs are still not performing on par when it comes to recognizing actions in movie data and their ability to act as generalizable problem solvers is still far behind of what the human brain seems to achieve effortlessly. Moreover, biological neuronal networks can learn far more effectively with fewer training examples, they achieve a much higher performance in recognizing complex patterns in time series data (e.g. recognizing actions in movies), they dynamically adapt to new tasks without losing performance and they achieve unmatched performance to detect and integrate out-of-domain data examples (data they have not been trained with). In other words, many of the big challenges and unknowns that have emerged in the field of deep learning over the last years are already mastered exceptionally well by biological neuronal networks in our brain. On the other hand, many facets of typical ANN design and training algorithms seem biologically implausible, such as the non-local weight updates, discrete processing of time, and scalar communication between neurons. Recent evidence suggests that learning in biological systems is the result of the complex interplay of diverse error feedback signaling processes acting at multiple scales, ranging from single synapses to entire networks.
Skript	The lecture slides will be provided as a PDF after each lecture.
Voraussetzungen / Besonderes	This advanced level lecture requires some basic background in machine/deep learning. Thus, students are expected to have a basic mathematical foundation, including linear algebra, multivariate calculus, and probability. The course is not to be meant as an extended tutorial of how to train deep networks in PyTorch or Tensorflow, although these tools used. The participation in the course is subject to the following conditions: 1) The number of participants is limited to 120 students (MSc and PhDs). 2) Students must have taken the exam in Deep Learning (263-3210-00L) or have acquired equivalent knowledge.
227-1033-00L	Neuromorphic Engineering I Registration in this class requires the permission of the instructors. Class size will be limited to available lab spots. Preference is given to students that require this class as part of their major.	W	6 KP	2V + 3U	T. Delbrück, G. Indiveri, S.‑C. Liu
Kurzbeschreibung	This course covers analog circuits with emphasis on neuromorphic engineering: MOS transistors in CMOS technology, static circuits, dynamic circuits, systems (silicon neuron, silicon retina, silicon cochlea) with an introduction to multi-chip systems. The lectures are accompanied by weekly laboratory sessions.
Lernziel	Understanding of the characteristics of neuromorphic circuit elements.
Inhalt	Neuromorphic circuits are inspired by the organizing principles of biological neural circuits. Their computational primitives are based on physics of semiconductor devices. Neuromorphic architectures often rely on collective computation in parallel networks. Adaptation, learning and memory are implemented locally within the individual computational elements. Transistors are often operated in weak inversion (below threshold), where they exhibit exponential I-V characteristics and low currents. These properties lead to the feasibility of high-density, low-power implementations of functions that are computationally intensive in other paradigms. Application domains of neuromorphic circuits include silicon retinas and cochleas for machine vision and audition, real-time emulations of networks of biological neurons, and the development of autonomous robotic systems. This course covers devices in CMOS technology (MOS transistor below and above threshold, floating-gate MOS transistor, phototransducers), static circuits (differential pair, current mirror, transconductance amplifiers, etc.), dynamic circuits (linear and nonlinear filters, adaptive circuits), systems (silicon neuron, silicon retina and cochlea) and an introduction to multi-chip systems that communicate events analogous to spikes. The lectures are accompanied by weekly laboratory sessions on the characterization of neuromorphic circuits, from elementary devices to systems.
Literatur	S.-C. Liu et al.: Analog VLSI Circuits and Principles; various publications.
Voraussetzungen / Besonderes	Particular: The course is highly recommended for those who intend to take the spring semester course 'Neuromorphic Engineering II', that teaches the conception, simulation, and physical layout of such circuits with chip design tools. Prerequisites: Background in basics of semiconductor physics helpful, but not required.

Statistics
Nummer	Titel	Typ	ECTS	Umfang	Dozierende
401-0625-01L	Applied Analysis of Variance and Experimental Design	W	5 KP	2V + 1U	L. Meier
Kurzbeschreibung	Principles of experimental design, one-way analysis of variance, contrasts and multiple comparisons, multi-factor designs and analysis of variance, complete block designs, Latin square designs, random effects and mixed effects models, split-plot designs, incomplete block designs, two-series factorials and fractional designs, power.
Lernziel	Participants will be able to plan and analyze efficient experiments in the fields of natural sciences. They will gain practical experience by using the software R.
Inhalt	Principles of experimental design, one-way analysis of variance, contrasts and multiple comparisons, multi-factor designs and analysis of variance, complete block designs, Latin square designs, random effects and mixed effects models, split-plot designs, incomplete block designs, two-series factorials and fractional designs, power.
Literatur	G. Oehlert: A First Course in Design and Analysis of Experiments, W.H. Freeman and Company, New York, 2000.
Voraussetzungen / Besonderes	The exercises, but also the classes will be based on procedures from the freely available, open-source statistical software R, for which an introduction will be held.
401-0649-00L	Applied Statistical Regression	W	5 KP	2V + 1U	M. Dettling
Kurzbeschreibung	This course offers a practically oriented introduction into regression modeling methods. The basic concepts and some mathematical background are included, with the emphasis lying in learning "good practice" that can be applied in every student's own projects and daily work life. A special focus will be laid in the use of the statistical software package R for regression analysis.
Lernziel	The students acquire advanced practical skills in linear regression analysis and are also familiar with its extensions to generalized linear modeling.
Inhalt	The course starts with the basics of linear modeling, and then proceeds to parameter estimation, tests, confidence intervals, residual analysis, model choice, and prediction. More rarely touched but practically relevant topics that will be covered include variable transformations, multicollinearity problems and model interpretation, as well as general modeling strategies. The last third of the course is dedicated to an introduction to generalized linear models: this includes the generalized additive model, logistic regression for binary response variables, binomial regression for grouped data and poisson regression for count data.
Skript	A script will be available.
Literatur	Faraway (2005): Linear Models with R Faraway (2006): Extending the Linear Model with R Draper & Smith (1998): Applied Regression Analysis Fox (2008): Applied Regression Analysis and GLMs Montgomery et al. (2006): Introduction to Linear Regression Analysis
Voraussetzungen / Besonderes	The exercises, but also the classes will be based on procedures from the freely available, open-source statistical software package R, for which an introduction will be held. In the Mathematics Bachelor and Master programmes, the two course units 401-0649-00L "Applied Statistical Regression" and 401-3622-00L "Statistical Modelling" are mutually exclusive. Registration for the examination of one of these two course units is only allowed if you have not registered for the examination of the other course unit.
401-3612-00L	Stochastic Simulation Findet dieses Semester nicht statt.	W	5 KP	3G
Kurzbeschreibung	This course provides an introduction to statistical Monte Carlo methods. This includes applications of simulations in various fields (Bayesian statistics, statistical mechanics, operations research, financial mathematics), algorithms for the generation of random variables (accept-reject, importance sampling), estimating the precision, variance reduction, introduction to Markov chain Monte Carlo.
Lernziel	Stochastic simulation (also called Monte Carlo method) is the experimental analysis of a stochastic model by implementing it on a computer. Probabilities and expected values can be approximated by averaging simulated values, and the central limit theorem gives an estimate of the error of this approximation. The course shows examples of the many applications of stochastic simulation and explains different algorithms used for simulation. These algorithms are illustrated with the statistical software R.
Inhalt	Examples of simulations in different fields (computer science, statistics, statistical mechanics, operations research, financial mathematics). Generation of uniform random variables. Generation of random variables with arbitrary distributions (quantile transform, accept-reject, importance sampling), simulation of Gaussian processes and diffusions. The precision of simulations, methods for variance reduction. Introduction to Markov chains and Markov chain Monte Carlo (Metropolis-Hastings, Gibbs sampler, Hamiltonian Monte Carlo, reversible jump MCMC).
Skript	A script will be available in English.
Literatur	P. Glasserman, Monte Carlo Methods in Financial Engineering. Springer 2004. B. D. Ripley. Stochastic Simulation. Wiley, 1987. Ch. Robert, G. Casella. Monte Carlo Statistical Methods. Springer 2004 (2nd edition).
Voraussetzungen / Besonderes	Familiarity with basic concepts of probability theory (random variables, joint and conditional distributions, laws of large numbers and central limit theorem) will be assumed.
401-3621-00L	Fundamentals of Mathematical Statistics	W	10 KP	4V + 1U	S. van de Geer
Kurzbeschreibung	The course covers the basics of inferential statistics.
Lernziel
401-3622-00L	Statistical Modelling	W	8 KP	4G	C. Heinze-Deml
Kurzbeschreibung	In der Regression wird die Abhängigkeit einer zufälligen Response-Variablen von anderen Variablen untersucht. Wir betrachten die Theorie der linearen Regression mit einer oder mehreren Ko-Variablen, hoch-dimensionale lineare Modelle, nicht-lineare Modelle und verallgemeinerte lineare Modelle, Robuste Methoden, Modellwahl und nicht-parametrische Modelle.
Lernziel	Einführung in Theorie und Praxis eines umfassenden und vielbenutzten Teilgebiets der Statistik, unter Berücksichtigung neuerer Entwicklungen.
Inhalt	In der Regression wird die Abhängigkeit einer beobachteten quantitativen Grösse von einer oder mehreren anderen (unter Berücksichtigung zufälliger Fehler) untersucht. Themen der Vorlesung sind: Einfache und multiple Regression, Theorie allgemeiner linearer Modelle, Hoch-dimensionale Modelle, Ausblick auf nichtlineare Modelle. Querverbindungen zur Varianzanalyse, Modellsuche, Residuenanalyse; Einblicke in Robuste Regression. Durchrechnung und Diskussion von Anwendungsbeispielen.
Skript	Vorlesungsskript
Voraussetzungen / Besonderes	This is the course unit with former course title "Regression". Credits cannot be recognised for both courses 401-3622-00L Statistical Modelling and 401-0649-00L Applied Statistical Regression in the Mathematics Bachelor and Master programmes (to be precise: one course in the Bachelor and the other course in the Master is also forbidden).
401-3628-14L	Bayesian Statistics	W	4 KP	2V	F. Sigrist
Kurzbeschreibung	Introduction to the Bayesian approach to statistics: decision theory, prior distributions, hierarchical Bayes models, empirical Bayes, Bayesian tests and model selection, empirical Bayes, Laplace approximation, Monte Carlo and Markov chain Monte Carlo methods.
Lernziel	Students understand the conceptual ideas behind Bayesian statistics and are familiar with common techniques used in Bayesian data analysis.
Inhalt	Topics that we will discuss are: Difference between the frequentist and Bayesian approach (decision theory, principles), priors (conjugate priors, noninformative priors, Jeffreys prior), tests and model selection (Bayes factors, hyper-g priors for regression),hierarchical models and empirical Bayes methods, computational methods (Laplace approximation, Monte Carlo and Markov chain Monte Carlo methods)
Skript	A script will be available in English.
Literatur	Christian Robert, The Bayesian Choice, 2nd edition, Springer 2007. A. Gelman et al., Bayesian Data Analysis, 3rd edition, Chapman & Hall (2013). Additional references will be given in the course.
Voraussetzungen / Besonderes	Familiarity with basic concepts of frequentist statistics and with basic concepts of probability theory (random variables, joint and conditional distributions, laws of large numbers and central limit theorem) will be assumed.
401-4623-00L	Time Series Analysis Findet dieses Semester nicht statt.	W	6 KP	3G	N. Meinshausen
Kurzbeschreibung	Statistical analysis and modeling of observations in temporal order, which exhibit dependence. Stationarity, trend estimation, seasonal decomposition, autocorrelations, spectral and wavelet analysis, ARIMA-, GARCH- and state space models. Implementations in the software R.
Lernziel	Understanding of the basic models and techniques used in time series analysis and their implementation in the statistical software R.
Inhalt	This course deals with modeling and analysis of variables which change randomly in time. Their essential feature is the dependence between successive observations. Applications occur in geophysics, engineering, economics and finance. Topics covered: Stationarity, trend estimation, seasonal decomposition, autocorrelations, spectral and wavelet analysis, ARIMA-, GARCH- and state space models. The models and techniques are illustrated using the statistical software R.
Skript	Not available
Literatur	A list of references will be distributed during the course.
Voraussetzungen / Besonderes	Basic knowledge in probability and statistics

Machine Learning and Artificial Intelligence
Nummer	Titel	Typ	ECTS	Umfang	Dozierende
227-0689-00L	System Identification	W	4 KP	2V + 1U	R. Smith
Kurzbeschreibung	Theory and techniques for the identification of dynamic models from experimentally obtained system input-output data.
Lernziel	To provide a series of practical techniques for the development of dynamical models from experimental data, with the emphasis being on the development of models suitable for feedback control design purposes. To provide sufficient theory to enable the practitioner to understand the trade-offs between model accuracy, data quality and data quantity.
Inhalt	Introduction to modeling: Black-box and grey-box models; Parametric and non-parametric models; ARX, ARMAX (etc.) models. Predictive, open-loop, black-box identification methods. Time and frequency domain methods. Subspace identification methods. Optimal experimental design, Cramer-Rao bounds, input signal design. Parametric identification methods. On-line and batch approaches. Closed-loop identification strategies. Trade-off between controller performance and information available for identification.
Literatur	"System Identification; Theory for the User" Lennart Ljung, Prentice Hall (2nd Ed), 1999. "Dynamic system identification: Experimental design and data analysis", GC Goodwin and RL Payne, Academic Press, 1977.
Voraussetzungen / Besonderes	Control systems (227-0216-00L) or equivalent.
252-0535-00L	Advanced Machine Learning	W	8 KP	3V + 2U + 2A	J. M. Buhmann
Kurzbeschreibung	Machine learning algorithms provide analytical methods to search data sets for characteristic patterns. Typical tasks include the classification of data, function fitting and clustering, with applications in image and speech analysis, bioinformatics and exploratory data analysis. This course is accompanied by practical machine learning projects.
Lernziel	Students will be familiarized with advanced concepts and algorithms for supervised and unsupervised learning; reinforce the statistics knowledge which is indispensible to solve modeling problems under uncertainty. Key concepts are the generalization ability of algorithms and systematic approaches to modeling and regularization. Machine learning projects will provide an opportunity to test the machine learning algorithms on real world data.
Inhalt	The theory of fundamental machine learning concepts is presented in the lecture, and illustrated with relevant applications. Students can deepen their understanding by solving both pen-and-paper and programming exercises, where they implement and apply famous algorithms to real-world data. Topics covered in the lecture include: Fundamentals: What is data? Bayesian Learning Computational learning theory Supervised learning: Ensembles: Bagging and Boosting Max Margin methods Neural networks Unsupservised learning: Dimensionality reduction techniques Clustering Mixture Models Non-parametric density estimation Learning Dynamical Systems
Skript	No lecture notes, but slides will be made available on the course webpage.
Literatur	C. Bishop. Pattern Recognition and Machine Learning. Springer 2007. R. Duda, P. Hart, and D. Stork. Pattern Classification. John Wiley & Sons, second edition, 2001. T. Hastie, R. Tibshirani, and J. Friedman. The Elements of Statistical Learning: Data Mining, Inference and Prediction. Springer, 2001. L. Wasserman. All of Statistics: A Concise Course in Statistical Inference. Springer, 2004.
Voraussetzungen / Besonderes	The course requires solid basic knowledge in analysis, statistics and numerical methods for CSE as well as practical programming experience for solving assignments. Students should have followed at least "Introduction to Machine Learning" or an equivalent course offered by another institution. PhD students are required to obtain a passing grade in the course (4.0 or higher based on project and exam) to gain credit points.
263-2400-00L	Reliable and Interpretable Artificial Intelligence	W	5 KP	2V + 1U + 1A	M. Vechev
Kurzbeschreibung	Creating reliable and explainable probabilistic models is a fundamental challenge to solving the artificial intelligence problem. This course covers some of the latest and most exciting advances that bring us closer to constructing such models.
Lernziel	The main objective of this course is to expose students to the latest and most exciting research in the area of explainable and interpretable artificial intelligence, a topic of fundamental and increasing importance. Upon completion of the course, the students should have mastered the underlying methods and be able to apply them to a variety of problems. To facilitate deeper understanding, an important part of the course will be a group hands-on programming project where students will build a system based on the learned material.
Inhalt	The course covers some of the latest research (over the last 2-3 years) underlying the creation of safe, trustworthy, and reliable AI (more information here: https://www.sri.inf.ethz.ch/teaching/riai2019): * Adversarial Attacks on Deep Learning (noise-based, geometry attacks, sound attacks, physical attacks, autonomous driving, out-of-distribution) * Defenses against attacks * Combining gradient-based optimization with logic for encoding background knowledge * Complete Certification of deep neural networks via automated reasoning (e.g., via numerical abstractions, mixed-integer solvers). * Probabilistic certification of deep neural networks * Training deep neural networks to be provably robust via automated reasoning * Understanding and Interpreting Deep Networks * Probabilistic Programming
Voraussetzungen / Besonderes	While not a formal requirement, the course assumes familiarity with basics of machine learning (especially probability theory, linear algebra, gradient descent, and neural networks). These topics are usually covered in “Intro to ML” classes at most institutions (e.g., “Introduction to Machine Learning” at ETH). For solving assignments, some programming experience in Python is excepted.
263-3210-00L	Deep Learning	W	5 KP	2V + 1U + 1A	T. Hofmann
Kurzbeschreibung	Deep learning is an area within machine learning that deals with algorithms and models that automatically induce multi-level data representations.
Lernziel	In recent years, deep learning and deep networks have significantly improved the state-of-the-art in many application domains such as computer vision, speech recognition, and natural language processing. This class will cover the mathematical foundations of deep learning and provide insights into model design, training, and validation. The main objective is a profound understanding of why these methods work and how. There will also be a rich set of hands-on tasks and practical projects to familiarize students with this emerging technology.
Voraussetzungen / Besonderes	This is an advanced level course that requires some basic background in machine learning. More importantly, students are expected to have a very solid mathematical foundation, including linear algebra, multivariate calculus, and probability. The course will make heavy use of mathematics and is not (!) meant to be an extended tutorial of how to train deep networks with tools like Torch or Tensorflow, although that may be a side benefit. The participation in the course is subject to the following condition: - Students must have taken the exam in Advanced Machine Learning (252-0535-00) or have acquired equivalent knowledge, see exhaustive list below: Advanced Machine Learning https://ml2.inf.ethz.ch/courses/aml/ Computational Intelligence Lab http://da.inf.ethz.ch/teaching/2019/CIL/ Introduction to Machine Learning https://las.inf.ethz.ch/teaching/introml-S19 Statistical Learning Theory http://ml2.inf.ethz.ch/courses/slt/ Computational Statistics https://stat.ethz.ch/lectures/ss19/comp-stats.php Probabilistic Artificial Intelligence https://las.inf.ethz.ch/teaching/pai-f18
263-5210-00L	Probabilistic Artificial Intelligence	W	5 KP	2V + 1U + 1A	A. Krause
Kurzbeschreibung	This course introduces core modeling techniques and algorithms from statistics, optimization, planning, and control and study applications in areas such as sensor networks, robotics, and the Internet.
Lernziel	How can we build systems that perform well in uncertain environments and unforeseen situations? How can we develop systems that exhibit "intelligent" behavior, without prescribing explicit rules? How can we build systems that learn from experience in order to improve their performance? We will study core modeling techniques and algorithms from statistics, optimization, planning, and control and study applications in areas such as sensor networks, robotics, and the Internet. The course is designed for upper-level undergraduate and graduate students.
Inhalt	Topics covered: - Search (BFS, DFS, A*), constraint satisfaction and optimization - Tutorial in logic (propositional, first-order) - Probability - Bayesian Networks (models, exact and approximative inference, learning) - Temporal models (Hidden Markov Models, Dynamic Bayesian Networks) - Probabilistic palnning (MDPs, POMPDPs) - Reinforcement learning - Combining logic and probability
Voraussetzungen / Besonderes	Solid basic knowledge in statistics, algorithms and programming

Big Data Systems
Nummer	Titel	Typ	ECTS	Umfang	Dozierende
252-0834-00L	Information Systems for Engineers Findet dieses Semester nicht statt.	W	4 KP	2V + 1U	Noch nicht bekannt
Kurzbeschreibung	This course provides the basics of relational databases from the perspective of the user. We will discover why tables are so incredibly powerful to express relations, learn the SQL query language, and how to make the most of it. The course also covers support for data cubes (analytics). After this course, you will be ready for Big Data for Engineers.
Lernziel	After visiting this course, you will be capable to: 1. Explain, in the big picture, how a relational database works and what it can do in your own words. 2. Explain the relational data model (tables, rows, attributes, primary keys, foreign keys), formally and informally, including the relational algebra operators (select, project, rename, all kinds of joins, division, cartesian product, union, intersection, etc). 3. Perform non-trivial reading SQL queries on existing relational databases, as well as insert new data, update and delete existing data. 4. Design new schemas to store data in accordance to the real world's constraints, such as relationship cardinality 5. Explain what bad design is and why it matters. 6. Adapt and improve an existing schema to make it more robust against anomalies, thanks to a very good theoretical knowledge of what is called "normal forms". 7. Understand how indices work (hash indices, B-trees), how they are implemented, and how to use them to make queries faster. 8. Access an existing relational database from a host language such as Java, using bridges such as JDBC. 9. Explain what data independence is all about and didn't age a bit since the 1970s. 10. Explain, in the big picture, how a relational database is physically implemented. 11. Know and deal with the natural syntax for relational data, CSV. 12. Explain the data cube model including slicing and dicing. 13. Store data cubes in a relational database. 14. Map cube queries to SQL. 15. Slice and dice cubes in a UI. And of course, you will think that tables are the most wonderful object in the world.
Inhalt	Using a relational database ================= 1. Introduction 2. The relational model 3. Data definition with SQL 4. The relational algebra 5. Queries with SQL Taking a relational database to the next level ================= 6. Database design theory 7. Databases and host languages 8. Databases and host languages 9. Indices and optimization 10. Database architecture and storage Analytics on top of a relational database ================= 12. Data cubes Outlook ================= 13. Outlook
Literatur	- Lecture material (slides). - Book: "Database Systems: The Complete Book", H. Garcia-Molina, J.D. Ullman, J. Widom (It is not required to buy the book, as the library has it)
Voraussetzungen / Besonderes	For non-CS/DS students only, BSc and MSc Elementary knowledge of set theory and logics Knowledge as well as basic experience with a programming language such as Pascal, C, C++, Java, Haskell, Python
263-2800-00L	Design of Parallel and High-Performance Computing	W	8 KP	3V + 2U + 2A	M. Püschel, T. Ben Nun
Kurzbeschreibung	Advanced topics in parallel / concurrent programming.
Lernziel	Understand concurrency paradigms and models from a higher perspective and acquire skills for designing, structuring and developing possibly large concurrent software systems. Become able to distinguish parallelism in problem space and in machine space. Become familiar with important technical concepts and with concurrency folklore.

Seite 1 von 2 Alle