Überblick
- Das Seminar ist auf max. 30 Teilnehmer/innen des Masterstudiengangs Data Science begrenzt.
Um an dem Seminar teilzunehmen, müssen Sie sich im AlmaWeb für das Modul Skalierbare Datenbanktechnologien 1 (10-INF-DS01) und das Seminar anmelden sowie an der Einführungsveranstaltung teilnehmen, bei der die endgültige Platz- und Themenvergabe erfolgt.
Bei Fragen und Problemen zur An- und Abmeldung wenden Sie sich bitte an das Studienbüro via einschreibung [at] math.uni-leipzig.de (einschreibung(at)math.uni-leipzig.de)
- Einführungsveranstaltung 30.10. 13:30 im Moodle-Kurs
- Die studentischen Vorträge finden an den Freitagsterminen im Jan./Feb 2021 (jeweils ab 13:15 Uhr) statt.
Leistungsbewertung
Ein erfolgreiches Seminar setzt die Teilnahme an allen Seminarterminen voraus, die selbständige Erarbeitung eines Themas sowie einen Vortrag sowie eine schriftliche Ausarbeitung (15-20 Seiten) über das Thema. Die Benotung setzt sich aus der Note zu Vortrag und Diskussion sowie der Note für die Ausarbeitung zusammen. Einige Hinweise zum Verfassen der schriftlichen Ausarbeitung finden Sie hier.
Literatur
Für das Verständnis ist es hilfreich sich folgende Studentenarbeiten oder Originalliteratur Quellen zum Thema Deep Learning anzuschauen.
Thema | Quelle |
---|---|
Einleitung Deep-Learning | Studentenarbeit,[1],[2] |
Autoencoder und CNN | Studentenarbeit,[1] |
Recurrent Neural Networks | [1] [2] |
Themen und Betreuer
Nr | Thema | Betreuer | Votragender | Quellen | Termin Vortrag | Folien | Ausarbeitung |
---|---|---|---|---|---|---|---|
0 | Einführung in Seminar und Themen | - | Prof. Rahm | 30.10.2020 | - | ||
Machine Learning in Databases | |||||||
DB1 | Data Management in Machine Learning:Challenges, Techniques, and Systems | Christen | [1], [2] | ||||
DB2 | DBMS Tuning with ML-Techniques | Christen | [1] | ||||
DB3 | Security and Privacy on Blockchain | Franke | [1], [2] | ||||
Privacy & Security | |||||||
P1 | Membership Inference Attacks Against Machine Learning Models | Schneider | [1] | ||||
P2 | Preventing Membership Inference Attacks with PATE | Schneider | [1] | ||||
P3 | Generating Differential Private Datasets Using GANs | Schneider | [1] | ||||
P4 | Clustered federated Learning: Model-Agnostic Distributed Multitask Optimization under Privacy Constraints | Sehili | [1] | ||||
P5 | Practical Secure Aggregation for Privacy-Preserving Machine Learning | Sehili | [1] | ||||
P6 | ABY3: A Mixed Protocol Framework for Machine Learning | Sehili | [1] | ||||
P7 | Privacy-Preserving Classification on Deep Neural Network | Sehili | [1] | ||||
P8 | Crime Data Analysis | Franke | [1] | ||||
Techniques for limited labeled data | |||||||
LD1 | Human in the Loop for Entity Resolution | Köpcke | [1], [2] | ||||
LD2 | Cross-Modal Entity Resolution Based on Co-Attentional Generative Adversarial Network | Köpcke | [1] | ||||
LD3 | Transfer Learning for Entity Resolution | Wilke | [1],[2] | ||||
LD4 | Effective and Efficient Data Cleaning for Entity Matching | Köpcke | [1] | ||||
LD5 | Semi-automated Labelling for ML | Wilke | [1] | ||||
LD6 | Machine Learning for Entity Resolution | Saeedi | [1] | ||||
Time Series Analysis | |||||||
TS1 | Time-series forecasting with Deep Learning | Täschner | [1], [2] | ||||
TS2 | Time Series Classification with Machine Learning: HIVE-COTE and InceptionTime | Burghardt | [1], [2] | ||||
Graphs | |||||||
G1 | Programming Abstractions for Distributed Graph Processing | Rost | [1] | ||||
G2 | Graph Stream Summarization Techniques | Rost | [1], [2] | ||||
G3 | Dynamic/Stream Graph Neural Network | Alkamel | [1] | ||||
G4 | Graph Analytics on GPUs | Gomez | [1] | ||||
G5 | The Message Passing Framework for Graph Neural Networks | Petit | [1] | ||||
G6 | Graph Neural Networks from a Spectral Perspective | Petit | [1] | ||||
G7 | Attention Models in Graphs | Petit | [1] | ||||
G8 | Large-Scale Machine Learning on Graphs | Schuchart | [1] | ||||
G9 | Bootstrapping Entity Alignment with Knowledge Graph Embeddings | Obraczka | [1] | ||||
G10 | Multi-view Knowledge Graph Embedding for Entity Alignment | Obraczka | [1] | ||||
Signal & Image processing | [1] | ||||||
SP1 | Location Tracking using Mobile Device Sensors | Rohde | [1], [2] | ||||
SP2 | Automated Reverse Engineering and Privacy Analysis of Modern Cars | Grimmer | [1] | ||||
SP3 | Advances in pedestrian detection systems | Täschner | [1], [2], [3] | ||||
SP4 | Person Detection With a Fisheye Camera | Burghardt | [1] | ||||
SP5 | Bird Voice Recognition | Franke | [1], [2] | ||||
SP6 | Marine Bioacoustics I : ORCA-SPOT: An Automatic Killer Whale Sound Detection Toolkit Using Deep Learning | Lin | [1] | ||||
SP7 | Marine Bioacoustics II : Marine Mammal Species Classification using Convolutional Neural Networks and a Novel Acoustic Representation | Lin | [1] | ||||
Deep Learning in Physics | |||||||
PH1 | Physics Informed Deep Learning | Uhrich | [1] | ||||
PH2 | Deep Neural Networks motivated by Partial Differential Equations | Uhrich | [1] | ||||
Bio-Medical Applications | |||||||
BM1 | Deep Learning for Prediction of Survival of Brain Tumors | Martin | [1] | ||||
BM2 | Machine Learning for Genomics Data | Christen | [1], [2] | ||||
BM3 | Construction of biomedical knowledge graphs | Christen | [1], [2] | ||||
BM4 | Electronic Health Record Data Quality | Rohde | [1], [2] | ||||
BM5 | Human Behavioural Analysis For Ambient Assisted Living | Burghardt | [1] | ||||
BM6 | Active survival learning in precision medicine | Pogany | [1] |