Lectures

8.3377 Quantum Machine Learning (KOGW-MWPM-KI, KOGW-MWPM-NIR)

Mattingley-Scott

Type Language Semester Credits Hours Room Time Term Year
S e 4 6 3 50/E07 W 2018
Blockveranstaltung 15.-19.10.2018
BSc: optional compulsory (Wahlpflichtbereich)
BSc examination field: Neuroinformatics (KOGW-WPM-NI)
BSc examination field: Artificial Intelligence (KOGW-WPM-KI)
MSc major: Artificial Intelligence
MSc major: Neuroinformatics and Robotics

Syllabus:

Prerequisites: Basic Knowledge in linear algebra, optimization and computation theory. Good understanding of machine learning. No specific knowledge of quantum physics is required. Familiarity with Python and Jupyter notebooks would be an advantage.

The course will introduce the participants to the fundamentals of Quantum Computing and how it can be used in Machine Learning. Introduction to basic Quantum computing operation, gate level explanations, universal gates milestone algorithms: shor, grover, oracles, qfft, magic bits, etc quantum computing landscape, who offers what use case areas: chemistry, optimization, machine learning, cryptography computational complexity theory review superposition & entanglement, bloch sphere linear algebra review technologies for Q: transmons, annealing, & others, how superposition & entanglement work on the device quantum theory, observation, theories of david deutsch traditional ML review unsupervised learning, pattern recognition & ML, supervised learning and SVM's regression, boosting etc.

Specific goals are Q ML Introduction, Including Q KMeans, Q NN's, Boosting, SVM's with Grover, exponential speedup, outlook hybrid ML, neuromorphic project

Link: http://www


Administration