Wenn Sie an diesem Kurs teilnehmen möchten, registrieren Sie sich bitte über C@mpus.
***NEWS***
Den Deep Learning Zeitplan für das Sommersemester 2019 "Deep Learning time schedule for SS19" finden sie hier.
Neues 6ECTS Deep learning Modul (75960) im SS2019 ersetzt das alte 3ECTS Deep learning Modul (77920). Aber das ISS bietet auch noch die Prüfung für das alte 3ECTS Modul an. Das heißt, im SS2019 werden zwei verschiedene Prüfungen angeboten, eine für das alte 3ECTS und eine für das neue 6ECTS Modul.
Für weitere Informationen, schaue hier.
Empfohlene Voraussetzungen
Solid knowledge about matrix computation, probability theory as
well as basic knowledge about optimization as from the course
"Advanced mathematics for signal and information processing" are highly
recommended.
Knowledge about general methods for pattern recognition as from the
course “Detection and pattern recognition” is recommended.
Lernziele
• Learn the basic tasks and concepts of machine learning (density
estimation, regression, classification, model, representation, …)
• Learn the differences between conventional (shallow) concepts of
machine learning and deep learning
• Learn the most basic deep architectures (DNN, auto-encoder, CNN,
RBM, RNN) and issues of training (how to parametrize, initialize and
optimize)
• Learn to understand and reduce a trained DNN (visualization, model
reduction)
• Learn how to use Theano, a widespread Python Toolbox for deep
learning, to implement the introduced deep architectures in Python
Inhalt
• Important basics from statistics (Entropy, cross-entropy, KL-divergence,
important inequalities)
• Tasks and concepts from machine learning (density estimation,
regression, classification)
• The most basic deep architectures (DNN, auto-encoder, CNN, RBM,
RNN)
• How to train a network and to perform inference
• Concepts for visualization and reduction of a trained DNN
• Basic introduction to Python and Theano
• Implementation of DNN, auto-encoder, CNN, RBM with examples:
handwritten digit- and object-recognition, as well as image restauration /
inpainting