CS-233(a): Introduction to machine learning (BA3)Machine learning and data analysis are becoming increasingly central in many sciences and applications. In this course, fundamental principles and methods of machine learning will be introduced, analyzed and practically implemented.
CS-605: Computational and statistical learning theoryStatistical learning theory for supervised learning and generalization in PAC and online models (VC theory, MDL/SRM, covering numbers, Radamacher Averages, boosting, compression, stability and connection with strong convexity in Banch spaces); Computational tractability of learning.
CS-487: Industrial automationThis course consists of two parts:
- architecture of automation systems, hands-on lab
- handling of faults and failures in real-time systems, including fault-tolerant computing
EE-556: Mathematics of data: from theory to computationThis course provides an overview of key advances in continuous optimization and statistical analysis for machine learning. We review recent learning formulations and models as well as their guarantees, describe scalable solution techniques and algorithms, and illustrate the trade-offs involved.
EE-608: Deep Learning For Natural Language ProcessingThe Deep Learning for NLP course provides an overview of neural network based methods applied to text. The focus is on models particularly suited to the properties of human language, such as categorical, unbounded, and structured representations, and very large input and output vocabularies.
EE-623: Perception and learning from multimodal sensorsThe course will cover different aspects of multimodal processing (complementarity vs redundancy; alignment and synchrony; fusion), with an emphasis on the analysis of people, behaviors and interactions from multimodal sensor, using statistical models and deep learning as main modeling tools.
BIO-642: State of the Art Topics in Neuroscience XIIIThe Loss Landscape of Neural Networks is in general non-convex and rough, but recent mathematical results lead provide insights of practical relevance.
9 online lectures, lecturers from NYU, Stanford, Shanghai, IST Austria, Google, Facebook, EPFL.
BIOENG-450: In silico neuroscience"In silico Neuroscience" introduces students to a synthesis of modern neuroscience and state-of-the-art data management, modelling and computing technologies.
BIOENG-456: Controlling behavior in animals and robotsStudents will acquire an integrative view on biological and artificial algorithms for controlling autonomous behaviors in animals and robots. Students will synthesize and apply this knowledge in oral presentations and exercises.
COM-406: Foundations of Data ScienceWe discuss a set of topics that are important for the understanding of modern data science but that are typically not taught in an introductory ML course. In particular we discuss fundamental ideas and techniques that come from probability, information theory as well as signal processing.