Über uns
Deep Learning is currently a big & growing trend in data analysis and prediction - and the main fuel of a new era of Artificial Intelligence (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.
Please find all slides of our past meetups, links to photos and some video recordings of our meetups + a wealth of resources to Deep Learning tutorials and more here: https://github.com/vdlm/meetups
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).
Bevorstehende Events (1)
Alles ansehen- 62nd Deep Learning Meetup: Examining LLM judges + musicSportradar, Vienna
Dear Deep Learners,
We kindly invite you to our next Deep Learning meetup on October 9th, hosted by Sportradar.
Our topics will be Examining LLM Judges and Deep Learning for Music Producers.
***
Agenda
18:30
- Introduction by the meetup organizers
- Welcome by the host
18:45
- Talk 1: From Calculation to Adjudication: Examining LLM Judges on Mathematical Reasoning Tasks
Andreas Stephan, University of Vienna
19:45
- Announcements: Events & Job Openings
- Networking Break & Discussions
20:30
- Talk 2: Deep Learning for Music Producers: Enhanced Symbolic Music Generation with Beat Shaper
Taylor Peer, Beat Shaper - Networking & Discussions
21:30 Wrap up & End
***
Talk Details:
Talk 1: From Calculation to Adjudication: Examining LLM Judges on Mathematical Reasoning Tasks
A major reason for the current success of large language models (LLMs) is their ability to perform zero-shot reasoning, or in other words, the ability to solve tasks without explicit training data. While this is great for practical scenarios, there is the tendency or danger to rely on “vibe checks”, i.e., just relying on single input / output examples without a proper performance evaluation.
Therefore, recently LLM judges have been proposed to automatically judge the quality of other candidate LLMs. In this talk, we study LLM judges on mathematical reasoning tasks. These require multi-step reasoning, and the correctness of their solutions is verifiable, enabling an objective evaluation. This talk presents 1) a detailed performance evaluation of LLM judges on mathematical reasoning tasks, 2) an investigation of regularities, such as intriguing correlations, in the judgement process and 3) the usage of textual signals to analyze those regularities.About the Speaker: After working as an NLP Data Scientist, Andreas Stephan started his PhD in 2021 and is about to graduate. In his research, he focuses on the usage and analysis of multiple imperfect learning signals in the NLP domain. He is broadly interested in everything NLP. (http://andst.github.io)
Talk 2: Deep Learning for Music Producers: Enhanced Symbolic Music Generation with Beat Shaper
Symbolic music generation offers a powerful and flexible approach to AI-generated music by creating editable musical notation, opening new possibilities for creative tools for music producers. This talk explores the key model architectures used in symbolic generation, including Variational Autoencoders and Transformers, and discusses their advantages and limitations compared to audio-based systems like those used by Suno and Udio.
One of the major challenges in the field is the absence of standardized benchmarks and datasets, which makes it difficult to compare model performance across different studies. The talk will also explore current evaluation practices, including the use of computable metrics and subjective listening tests, and the issues these present for generative music systems.
Finally, the talk will introduce Beat Shaper, a deep learning powered platform for music producers. Beat Shaper uses multimodal models to generate music notation data as well as the corresponding synthesizer and effect settings necessary to render them to audio, thus bridging the gap between traditional symbolic music generation and audio generation.
About the Speaker: Taylor Peer is CEO and co-founder of Beat Shaper, an AI startup based in Vienna, as well as a lecturer in machine learning and data engineering at the Bern University of Applied Sciences. His master's thesis at the TU Wien compared and evaluated generative music models under the supervision of Richard Vogl and Peter Knees.
Hot Topics & Latest News:
Do you have some interesting breaking news about Deep Learning? Did you read an interesting paper that you want to share? Did you create an exciting application or achieve some break-through? It would be great to share this in our meetup's Hot Topics section! Please get in touch through contact@vdlm.atWe are looking forward to seeing you at our next meetup!
Sportradar will kindly provide drinks & snacks.
