It seems like generative AI has been in the news almost every day for the last several months. With so much information and hot takes out there, it’s hard to know what’s really going on with this watershed technology. To help you get beyond the hype, we added a new generative AI track to ODSC Europe. Check out a few of the sessions included in this track below.
From Probabilistic Logics to Neurosymbolic AI
Luc De Raedt | Director at Leuven.AI |Professor at KU Leuven
In this session, Luc De Raedt addresses the challenge of integrating learning and reasoning in AI. He’ll posit that StarAI and Probabilistic Logic form an ideal basis for developing neuro-symbolic artificial intelligence techniques. And use the deep probabilistic logic programming languages DeepProbLog and DeepStochLog to illustrate his point.
A Walkthrough of Low-Code Deep Learning with KNIME
Roberto Cadili | Data Scientist | Knime and Emilio Silvestri | Junior Data Scientist | Knime
This session will explore the evolution of deep learning architectures and how KNIME Analytics Platform is naturally designed to keep up with these transformations. You will start off by introducing simple ANNs for a classification task, then focus on RNNs with LSTM units for text generation and time series forecasting; CNNs for image classification and styling; and GANs for synthetic image generation.
Distributed Hyperparameter Tuning: Finding the Right Model can be Fast and Fun
Matthias Seeger, PhD | Principal Applied Scientist, Machine Learning | Amazon Research
Join this session for an overview of modern hyperparameter optimization methods with a focus on hands-on practice with Syne Tune, a new open-source library for distributed hyperparameter tuning and global optimization.
Generative AI in Practice: How to build your own Stable Diffusion API
Tim Santos | Director of Product, AI Cloud Solutions | Graphcore
Join this hands-on workshop to learn how to easily deploy your own generative AI in production with model checkpoints, open-source libraries such as Hugging Face, and MLOps deployment pipelines.
Why GPU Clusters Don’t Need to Go Brrr? Leverage Compound Sparsity to Achieve the Fastest Inference Performance on CPUs
Damian Bogunowicz | Machine Learning Engineer | Neural Magic and Konstantin Gulin | Machine Learning Engineer | Neural Magic
In this session, you’ll learn the theory behind compound sparsity, state-of-the-art techniques, and how to apply it in practice using the Neural Magic platform. You’ll see how the combination of structured plus unstructured pruning (to 90%+ sparsity), quantization, and knowledge distillation can be used to create models that run an order of magnitude faster than their dense counterparts, without a noticeable drop in accuracy.
Introduction to Topological Data Analysis Workshop
Christian Ramirez | Machine Learning Technical Leader | MercadoLibre
Join this workshop for an introduction to topological data analysis (TDA). TDA strives to develop a more comprehensive understanding of data by analyzing its geometry and topology, and meet the need for more sophisticated methods for analyzing complex datasets.
Introduction to Deep Reinforcement Learning
Dr. Phil Winder | CEO | Winder Research
This tutorial will take you on a hands-on-ish walkthrough of what reinforcement learning is, why we need it to be deep, and how it’s used in practice. You will learn the background theory, explore use cases, and have fun with a notebook that provides a practical example of what we’re talking about.
Production ML for Mission-Critical Applications
Robert Crowe | Product Manager, MLOps and TF OSS | Google
This session will explore the use of ML pipeline architectures for implementing production ML applications, in particular Google’s experience with TFX, and available tooling for rigorous analysis of model performance and sensitivity.
Unifying ML With One Line of Code
Daniel Lenton, PhD | CEO | Ivy
Why should we try to unify the ML frameworks? Won’t we just create a new incompatible standard and make the ML fragmentation even worse? This session will argue that the answer to these sensible and important questions is no.
Using Deep Learning to Forecast Demand for Thousands of Grocery Items
Sam Blake, PhD | Lead Data Scientist | Ocado Technology
This session will explore how deep learning models can be adapted for e-commerce, specifically through the lens of an online grocery. You’ll get a glimpse into a real life example of deep learning in production and how it is having an impressive impact in the e-commerce space.
From Correlation to Causality in AI
Dr. Andre Franca | VP of Research and Development | causaLens
This session will take a look at recent developments in the science of causal discovery, as well as motivate why this tool should be part of every data scientist’s arsenal. You’ll cover topics such as randomized control trials, conditional independence tests, causal discovery from observational data, and causal inference.
Don’t miss your chance to dive deep into both the theory and practice of Generative AI with ODSC Europe’s hands-on training sessions, workshops, and talks. Plus, you’ll save on your pass when you register today.
Can’t make Europe? Check out our upcoming free virtual Generative AI Summit on July 20th.