Deep Learning is currently a big & growing trend in data analysis and prediction - and the main fuel of a new era of AI. Google, Facebook and others have shown tremendous success in pushing image, object & speech recognition to the next level.
But Deep Learning can also be used for so many other things! The list of application domains is literally endless.
Although rooted in Neural Network research already in the 1950's, the current trend in Deep Learning is unstoppable, and new approaches and improvements are presented almost every month.
We would like to meet and discuss the latest trends in Deep Learning, Neural Networks and Machine Learning, and reflect the latest developments, both in industry and in research.
The Vienna Deep Learning Meetup is positioned at the cross-over of research to industry - having both a focus on novel methods that are published in such a fast pace, and interesting new applications in the startup and industry world. We usually have 2 speakers from either academia, startups or industry, complemented by a "latest news and hot topics" section. Occasionally we do tutorials about software frameworks and how to use Deep Learning in practice. Each evening ends with networking & discussions over drinks and snacks.
Note that this meetup has an intermediate to advanced level (we have done introductions to Deep Learning and neural networks only in the beginning, but try to repeat the most important concepts regularly).
If you want to attend this meetup, sign up at our Meetup page.
- Meetup page: https://www.meetup.com/Vienna-Deep-Learning-Meetup/
- Wiki: https://github.com/vdlm/meetups/wiki
- Youtube Channel: https://www.youtube.com/channel/UCAVBJhzHK-jleJbyYTDp8cA
 |
Thomas Lidy has been a researcher in music information retrieval combined with machine learning at TU Wien from 2004 to 2017. After his position as Head of Machine Learning at Musimap, he currently is the Senior Director of AI and Data Science at Utopia Music, a company that uses Deep Learning for music analysis, with use cases such as music identification, music tagging, music emotion recognition and mood-based music recommendation. |
 |
Jan Schlüter has been pursuing research on deep learning for audio processing since 2010, currently as a university assistant at the Johannes Kepler University Linz. |
 |
Alexander Schindler researches audio-visual aspects of music information. He is machine learning specialist at the Digital Insight Lab of the AIT Austrian Institute of Technology and lecturer at the Technical University of Vienna. [Research Profile / LinkedIn] |
 |
René Donner is Co-Founder and former CTO at contextflow and currently building the medical image annotation platform mva.ai |
| Date | # | Speaker | Topic | Slides | Details | Video | Photos |
|---|---|---|---|---|---|---|---|
| 2024-09-11 | 61 | VDLM | Intro / Events | details | |||
| 2024-09-11 | 61 | Martin Trapp | Uncertainty Quantification in Deep Learning | details | |||
| 2024-03-19 | 57 | VDLM | Intro / Events | details | |||
| 2024-03-19 | 57 | Paul Puntschart | Artificial Intelligence for the Pen-and-Paper Game "SIM" | details | |||
| 2024-01-17 | 56 | Anastasia Pustozerova | Differential Privacy for Machine Learning | details | |||
| 2023-11-16 | 55 | Alexander Schindler, Mina Schütz | Countering fake news with deep learning - a retrospective summary of five years of research | details | |||
| 2023-11-16 | 55 | Meder Kamalov | From Development to Deployment: Leveraging 'fal' for Efficient AI Model Serving | details | |||
| 2023-10-18 | 54 | VDLM | Intro / Jobs | details | |||
| 2023-10-18 | 54 | Liad Magen | Extracting Gold From Your Paper Pile: State-of-the-art methods for information extraction from paper documents | details | |||
| 2023-10-18 | 54 | Jan Schlüter | Music Audio Generation in 2023: A Selective Review | details | |||
| 2023-10-12 | 53 | Julia Fuith | AI Act: Need to know Facts. | details | |||
| 2023-10-12 | 53 | Daniela Murhammer-Sas, Alexander Banfield-Mumb | AI Policy Forum – An Overview. | details | |||
| 2023-10-12 | 53 | Erich Prem | Reviewing the issues - What are the challenges and where are the limits of what an AI regulation can and should do? | details | |||
| 2023-09-13 | 52 | VDLM | Intro / Jobs | details | |||
| 2023-09-13 | 52 | Adrian Braşoveanu | From Transformers to Large Language Models | details | |||
| 2023-09-13 | 52 | Bogdan Pirvu | LLM Application Development | details | |||
| 2023-06-15 | 51 | VLDM | Intro / Events / Jobs | details | |||
| 2023-06-15 | 51 | Matthias Samwald | After ChatGPT | details | |||
| 2023-06-15 | 51 | René Donner | Segment Anything and the Rise of Foundation Models | details | |||
| 2023-05-04 | 50 | Michael Pieler | Intro, Events + Hot Papers: Large Language Models | details | |||
| 2023-05-04 | 50 | Sharwin Rezagholi | Introduction to (Deep) Reinforcement Learning | details | |||
| 2023-05-04 | 50 | Rudolf Mayer | Security of Machine Learning Systems – (How) Can We Get There? | details | |||
| 2023-03-29 | 49 | Rene Donner / Aaron Kaplan | VDLM, Survey, Jobs, Events, Hot Papers | details | |||
| 2023-03-29 | 49 | Jason Hoelscher-Obermaier | Truth or Dare - How LLMs disregard truth | details | |||
| 2023-03-29 | 49 | Sebastian Schaffer / Lukas Exl | Physics Inspired Neural Networks | details | |||
| 2023-02-28 | 48 | Michael Pieler, OpenBioML.org & Stability.AI | Jobs / Events / Hot Papers session: Language Models & Prompt Engineering | ||||
| 2023-02-28 | 48 | Gabriele Libardi, Pompeu Fabra University / Trayport | Neural Program Synthesis – An Overview | ||||
| 2023-02-28 | 48 | Marco Pasini, Johannes Kepler University | Musika! Fast Infinite Waveform Music Generation | ||||
| 2023-01-26 | 47 | Paul Tiwald, mostly.ai // MUW AI Institute | Synthetic Data // AI in BioMedicine | ||||
| 2022-11-17 | 46 | Rene Donner, mva.ai | Stealing Models from Compiled DNNs | ||||
| 2022-11-17 | 46 | Liad Magen, TU-INSO | Hot Papers – What's new in NLP? | ||||
| 2022-11-17 | 46 | Georg Braun, emotion3d.ai | Going Embedded: Real-time Deep Learning for automotive applications | ||||
| 2022-11-17 | 46 | Marc Javin, emotion3d.ai | Eye Analysis: Designing Neural Network for the Automotive Industry | ||||
| 2022-11-17 | 46 | VDLM | Job Openings | ||||
| 2022-10-18 | 45 | Lukas Zimmermann / Michael Pieler | Neural Radiance Fields / Stable Diffusion | ||||
| 2022-05-18 | 44 | Michael Pieler | Introduction to Transformers with a focus on Computer Vision | ||||
| 2022-05-18 | 44 | René Donner | ICLR 2022 - Trends & interesting highlights | ||||
| 2022-05-18 | 44 | Intro slides | |||||
| 2021-12-01 | 43 | Jan Schlüter | Transformers follow-up: What about audio? | ||||
| 2021-12-01 | 43 | Michael Pieler | Introduction to Transformers with a focus on Computer Vision | ||||
| ... | 42 | ||||||
| ... | 41 | ||||||
| ... | 40 | ||||||
| ... | 39 | ||||||
| 2021-02-17 | 38 | Jan Schlüter | Coordinate-based Neural Representations | ||||
| 2021-02-17 | 38 | Michael Pieler | OpenAI: CLIP & DALL·E | ||||
| 2021-01-13 | 37 | René Donner | NeurIPS 2020 Review | ||||
| 2020-12-09 | 36 | Antonis Makropoulos | Practical experiences in accurate video segmentation | n/a | |||
| 2020-10-13 | 35 | Liad Magen | Introduction to Graph Neural Networks | ||||
| 2020-08-20 | 34 | Sander Dieleman | Generating music in the waveform domain | ||||
| 2020-02-26 | 33 | Jan Schlüter, René Donner and Thomas Lidy | Deep Learning Hardware Overview: What and where to buy or rent | ||||
| 2020-02-26 | 33 | Markus Toman | And then they began to speak! Towards end-to-end speech synthesis, and back again? | ||||
| 2020-01-30 | 32 | René Donner | Report from NeurIPS 2019 | ||||
| 2020-01-30 | 32 | Christoph Bonitz | Self-Supervised Deep Learning | ||||
| 2019-12-02 | 31 | Sebastian Böck, Katharina Prinz | ISMIR 2019 Review | ||||
| 2019-12-02 | 31 | Vladimir Macko | How to do ML if you have lots of Google’s GPUs | ||||
| 2019-12-02 | 31 | Jan Schlüter | Taming Horses in Singing Voice Detection | ||||
| 2019-10-29 | 30 | Thomas Schlegl | Anomaly Detection with GANs | ||||
| 2019-10-29 | 30 | Alexander Schindler | Fake News. From Shallow to Deep. How to create, detect and fight it. | ||||
| 2019-09-24 | 29 | Jakub Mačina | RecSys2019 Review | ||||
| 2019-09-24 | 29 | Michael Pieler | The Fastai Deep Learning Library | ||||
| 2019-09-24 | 29 | Jakub Mačina | Deep Learning for Recommender Systems | ||||
| 2019-06-24 | 28 | Franz Fürbass | Deep Learning for Electrical Biosignals and their Application in Medical Products | ||||
| 2019-06-24 | 28 | Rudolf Mayer | Adversarial Machine Learning - An Introduction to Backdoor, Evasion and Inversion Attacks | ||||
| 2019-05-22 | 27 | Florian Seitner, Michael Hödlmoser | Advances in Automotive In-Cabin Monitoring: Present & Future | ||||
| 2019-05-22 | 27 | Daniel Ressi | Deep Learning for Predictive Quality & Predictive Maintenance | ||||
| 2019-04-29 | 26 | Jakob Klepp | Computer Vision Models in Production | ||||
| 2019-04-29 | 26 | Simon Stiebellehner, Bernhard Redl | Continuous Integration and Deployment for Machine Learning Applications | ||||
| 2019-03-27 | 25 | Jason Hoelscher-Obermaier | Teaching machines to understand natural language conversations: a bag of tricks | ||||
| 2019-03-27 | 25 | Liad Magen | An introduction to state of the art in NLP using Deep Learning | ||||
| 2019-02-28 | 24 | Alexander Hirner | Computer Vision Annotation Tool | ||||
| 2019-02-28 | 24 | Hrvoje Bogunovic | Deep Learning for Ophthalmology - Diagnosis and Treatment of Eye Disorders | ||||
| 2019-01-31 | 23 | Rene Donner | Interesting Papers & Trends from NeurIPS 2018 | ||||
| 2019-01-31 | 23 | Ahmad Haj Mosa, Fabian Schneider | Explainable Neural Symbolic Learning | ||||
| 2018-11-12 | 22 | Stephanie Cox | AI Strategy for Austria | strategy paper | |||
| 2018-11-12 | 22 | Michelangelo Fiore & Florian Matusek | Deep Learning for Object Detection in Video Surveillance | ||||
| 2018-10-15 | 21 | Richard Vogl | Drum Transcription via Joint Beat and Drum Modeling using Convolutional Recurrent Neural Networks | ||||
| 2018-10-15 | 21 | Thomas Lidy and Alexander Schindler | Deep Learning for Music & Audio Analysis | ||||
| 2018-09-18 | 20 | Peter Ferenczy | They Grow Up So Fast | ||||
| 2018-09-18 | 20 | Eric Steinberger | Deep Reinforcement Learning: Learning Like a Baby Rather Than a Copier | ||||
| 2018-06-07 | 19 | Matthias Hecker | Mon Style - Machine Learning in the Fashion Domain | ||||
| 2018-06-07 | 19 | Enes Deumić, Vedran Vekić | Fast, Accurate And Customized Visual Similarity Search On Real-world Images | ||||
| 2018-06-07 | 19 | Alexander Schindler | Visual Computing: then and now | ||||
| 2018-05-07 | 18 | Sarah Spiekermann-Hoff | The Big Data Illusion and its Impact on Flourishing with General AI | ||||
| 2018-05-07 | 18 | Moshe Vardi | Deep Learning and the Crisis of Trust in Computing | ||||
| 2018-04-23 | 17 | Christoph Goetz | ImageBiopsyLab: Enhancing the medical expert - how to help doctors with AI | ||||
| 2018-04-23 | 17 | Anouk Visser | Birds.ai: AI to provide a bird’s-eye view | ||||
| 2018-02-27 | 16 | Christoph Bonitz | Review of Andrew Ng’s Deep Learning Specialization on Coursera | ||||
| 2018-02-27 | 16 | Navid Rekabsaz | Demystifying Neural Word Embedding: Applications in Financial Sentiment Analysis, and Gender Bias Detection | ||||
| 2018-01-09 | 15 | Rene Donner | Deep Learning on 3D Medical Image Data at Contextflow | ||||
| 2018-01-09 | 15 | Alexander Hirner | Transfer Learning for fun and profit | ||||
| 2017-11-20 | 14 | Lukáš Vrabel | Evolution of Image Search @ Seznam.cz | ||||
| 2017-10-24 | 13 | Valentyn Boreiko | One Model To Learn Them All | ||||
| 2017-10-24 | 13 | Yufeng Guo | TensorFlow Wide & Deep: Data Classification the easy way | ||||
| 2017-09-04 | AI | Ulla Kruhse-Lehtonen | Seizing the Machine Learning Opportunity | ||||
| 2017-09-04 | AI | Calvin Seward | Deep Learning: More Than Classification | ||||
| 2017-09-04 | AI | Dave Elliott | Machine Learning with Google Cloud | ||||
| 2017-09-04 | AI | Tomáš Mikolov | Neural Networks for Natural Language Processing | ||||
| 2017-09-04 | AI | Sepp Hochreiter | Deep Learning is Evolving into the Key Technology of Artificial Intelligence | ||||
| 2017-06-20 | 12 | Michal Šustr | Generative Adversarial Networks | ||||
| 2017-06-20 | 12 | Philipp Kranen | Microsoft Cognitive Toolkit and Applications in Image Object Recognition | ||||
| 2017-05-17 | 11 | Ana Jalali | An Introduction to Bidirectional LSTM-HMM for Sound Event Detection | ||||
| 2017-05-17 | 11 | Peter Ruch | A Comparison of Deep Learning Frameworks for Distributed Training | ||||
| 2017-03-23 | 10 | Oleg Leizerov | Deep Learning for Self-Driving Cars | ||||
| 2017-02-21 | 9 | Alexander Schindler | Coding in Keras: Hard-Disk Failure Prediction with SMART data using RNNs | ||||
| 2017-02-21 | 9 | Philipp Omenitsch | Visionlabs: Face Recognition for Businesses | ||||
| 2017-01-17 | 8 | Thomas Lidy | Deep Learning Tutorial in Python with Keras | Github | |||
| 2016-12-01 | 7 | Kornél Kis | Convolutional Neural Networks: Applications and a short timeline | ||||
| 2016-12-01 | 7 | Sabria Lagoun | How can we learn from Neuroscience? | ||||
| 2016-10-12 | 6 | Kornél Kis | Deep learning in practice - a Text-to-Speech system built with neural networks | ||||
| 2016-10-12 | 6 | Benjamin Freundorfer | An Intro to Neural Networks | ||||
| 2016-09-22 | 5 | Christoph Körner | Going Deeper with GoogLeNet and CaffeJS | ||||
| 2016-09-22 | 5 | Josef Puchinger | Deep Learning & The Future of Automation | ||||
| 2016-06-06 | 3 | Jan Schlüter | Open-source Deep Learning with Theano and Lasagne | ||||
| 2016-05-09 | 2 | Gregor Mitscha-Baude | Recurrent Neural Networks | ||||
| 2016-05-09 | 2 | Alex Champandard | Neural Networks for Image Synthesis | ||||
| 2016-04-07 | 1 | Thomas Lidy & Jan Schlüter | Deep Learning: History, Approaches, Applications |