Persönlicher Status und Werkzeuge

Home Teaching Summer Semester 2017 Deep Learning for Computer Vision (IN2346) (2h + 2h, 6ECTS)

Deep Learning for Computer Vision (IN2346) (2h + 2h, 6ECTS)

SS 2017, TU München

Lecture

Location: Room 02.09.023
Date: Tuesday (14:00-16:00) - Thursday (16:00-18:00)
Lecturer: Dr. Laura Leal-Taixé
ECTS: 6
SWS: 4

Tutorial

Location: Room 02.09.023
Date: one hour each lecture day
Tutor: Thomas Frerix, Caner Hazirbas

Content
  • Introduction to Computer Vision and history of Deep Learning.
  • Machine learning Basics 1: linear classification, maximum likelihood
  • Machine learning basics 2: logistic regression, perceptron 
  • Introduction to neural networks and their optimization, SGD, Back-propagation
  • Training Neural Networks Part 1: regularization, activation functions, weight initialization, gradient flow, batch normalization, hyperparameter optimization
  • Training Neural Networks Part 2: parameter updates, ensembles, dropout
  • Convolutional Neural Networks
  • CNN for object detection (from MNIST to ImageNet), visualizing CNN (DeepDream)
  • Recurrent networks and LSTMs
  • Research 1: Prominent architectures, e.g. GoogleNet, ResNet
  • Research 2: Reinforcement learning
  • Research 3: Adversarial networks
Prerequisites

Passion for mathematics and the use of machine learning in order to solve complex computer vision problems. The course will be focused on practical projects, therefore, previous knowledge a programming language, preferably Python, is desired.

Lecture Slides

tba.

Last edited 21.02.2017 13:06 by Caner Hazirbas