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- 66th Vienna Deep Learning MeetupUniversity of Vienna Biology Building (UBB), Wien
Dear Deep Learners,
Our next meetup is on May 22, featuring:
- A deep dive into CLIP embeddings - by Damien Stewart
- Insights from the winning team of the WSDM Cup Multilingual Chatbot Competition - by Michael Pieler
Please find the details below:
***
Agenda:18:30
- Introduction & Welcome by the meetup organizers
18:45
- Talk 1: Multimodal Meaning: Math at the Limits of CLIP
by Damian Stewart
19:30
- Announcements
- Networking Break & Discussions
20:00
- Talk 2: Winner of the WSDM Cup Multilingual Chatbot Arena Kaggle Competition: Summary & Details
by Michael Pieler
20:40
- Networking & Discussions
22:00 Wrap up & End
***
Talk Details:
Talk 1: Multimodal Meaning: Math at the Limits of CLIP
CLIP embeddings are at the heart of multimodal AI. This talk moves beyond basic applications to delve into how CLIP maps language to images, critically examining the power and unexpected limitations of its mathematical similarity measures through concrete examples. We’ll explore creative ways to manipulate CLIP’s latent space, uncovering untapped potential for generative and search applications. Finally we'll broaden our focus to the challenge of modelling visual meaning more generally. Taking a very gentle step into poststructuralist philosophy, we'll consider the logical limits of systems like CLIP, and the pitfalls of web-scale visual pre-training. By the end we'll have a solid understanding of what CLIP is, what it can and cannot do - and why.Outline:
1. Understanding CLIP Embeddings:
An introduction to how CLIP models map images and text into a shared latent space: what embeddings are, how they are trained, and what they enable. Examples: image search, text-to-image generation.
2. The Limits of Mathematical Meaning:
How cosine similarity, zero-shot classification, and semantic proximity work, and where these approaches break down. Examples: successful classifications, revealing failures.
3. Manipulating Conceptual Space:
Using embeddings as a creative tool: vector arithmetic (adding, subtracting, blending), semantic pathfinding, interpolation.
Examples: semantic exploration, search augmentations, prompt engineering beyond weighting and word selection.
4. Meaning Beyond Mathematics:
A deeper reflection on relational meaning through CLIP embeddings, drawing (very gently) on post-structuralist philosophy. - How CLIP mirrors Saussurian linguistics, what the means for the influence of culture and ideology on embedding spaces, and why understanding these forces is crucial for building next-generation ML-powered systems.About the speaker:
Damian Stewart is a software engineer with a distinctive combination of technical depth and humanistic insight. With over 25 years of experience across industry and research, he designs and builds systems that extend capability, foster creativity, and make innovation accessible to a wider world.Talk 2: Winner of the WSDM Cup Multilingual Chatbot Arena Kaggle Competition: Summary & Details
In the WSDM Cup Multilingual Chatbot Arena Kaggle competition the challenge was to predict which responses users will prefer in a head-to-head battle between LLM-powered chatbots. Our winning solution consisted of the model training which involved a pre-training, a teacher-training, and a distillation stage and an optimized inference setup to get the highest performance in a specific time-frame with the provided hardware.Michael Pieler, an independent researcher, will give a short presentation of the winning solution of his team. In this talk he will summarize and share some details about the winning entry in this competition.
We are thankfully hosted by University of Vienna Biology center this time. Please note that we cannot provide food or drinks at this meetup.
Looking forward to seeing you at our next meetup,
Your VDLM Organizers
