|
Lab Course Machine Learning in Signal Processing (LabMLISP)2.5 ECTS (englische Bezeichnung: Lab Course Machine Learning in Signal Processing)
(Prüfungsordnungsmodul: Technical Lab Courses)
Modulverantwortliche/r: Veniamin Morgenshtern Lehrende:
Veniamin Morgenshtern
Start semester: |
SS 2018 | Duration: |
1 semester | Cycle: |
halbjährlich (WS+SS) |
Präsenzzeit: |
60 Std. | Eigenstudium: |
15 Std. | Language: |
Englisch |
Lectures:
-
-
Anleitung zu wissenschaftlichen Arbeiten
(Anleitung zu wiss. Arbeiten, 4 SWS, André Kaup, nach Vereinbarung)
-
Anleitung zu wissenschaftlichen Arbeiten
(Anleitung zu wiss. Arbeiten, 4 SWS, Walter Kellermann, nach Vereinbarung)
-
Lab Course Machine Learning in Signal Processing
(Praktikum, 4 SWS, Anwesenheitspflicht, Veniamin Morgenshtern, single appointment on 18.6.2018, 10:00 - 14:00, 06.021; block seminar 20.6.2018-11.7.2018 Wed, 12:00 - 16:00, 06.021; block seminar 25.6.2018-11.7.2018 Mon, 8:00 - 12:00, 06.021)
Empfohlene Voraussetzungen:
Knowledge of Python programming language is required. Basic theoretical knowledge in machine learning is assumed: consider taking the Machine Learning in Signal Processing (MLSIP) course in the same semester.
Inhalt:
Imagine a car driving on an autobahn in an automatic mode. Among other things, the car needs to steer itself to keep driving in it's own lane. To accomplish this, the central problem is to detect the road-lane markings. These are the white solid or dashed lines that are drawn on each side of the lane. The standard modern approach to solve this type of problems is to take a large dataset of labled examples and train a deep neural network model to accomplish the task. This is how car and pedestrian detection algorithms are developed. The difficulty with the road-lane markings is that there is no labled dataset of them and creating such dataset would cost millions of dollars.
In this lab course we will solve this problem using transfer learning and mathematical modeling:
Create cartoon-like artificial images of a road with known locations for the lane markings.
Train deep neural network on these artificial images with heavy data augmentations that mimic real-world images.
Create a dataset of unlabeled real-life videos by downloading and organizing examples from youtube.
Create a machine learning pipeline for working with these videos efficiently.
Apply the neural network that has been trained on artificial data to the real world videos.
Analyze the quality of results produced by the network.
Use mathematical modeling to correct the outputs of the network.
Retrain the network on the dataset composed of the corrected outputs.
Measure and analyze the quality of the results.
The software will be written in Python using JupyterLab development framework. Access to modern GPU servers will be provided. This is an intensive research-level course; the result of the course might be the creation of state-of-the-art lane detection system for self-driving cars.
Verwendbarkeit des Moduls / Einpassung in den Musterstudienplan:
- Advanced Signal Processing & Communications Engineering (Master of Science)
(Po-Vers. 2016w | TechFak | Advanced Signal Processing & Communications Engineering (Master of Science) | Masterprüfung | Wahlpflichtmodule | Technical Lab Courses)
Dieses Modul ist daneben auch in den Studienfächern "Communications and Multimedia Engineering (Master of Science)" verwendbar. Details
Studien-/Prüfungsleistungen:
Praktikum Machine Learning in der Signalverarbeitung (Prüfungsnummer: 878210)
(englischer Titel: Lab Course Machine Learning in Signal Processing)
- Studienleistung, Praktikumsleistung, unbenotet
- weitere Erläuterungen:
The participants have to provide software.
- Prüfungssprache: Englisch
- Erstablegung: SS 2018, 1. Wdh.: WS 2018/2019
1. Prüfer: | Veniamin Morgenshtern |
|
|
|