Europe 2023 Schedule!
All sessions are scheduled in the GMT time zone (UK time zone)
- ODSC Talks schedule includes Wednesday, June 14th – Thursday, June 15th. In-person sessions are available to Platinum and Mini-Bootcamp pass holders. Virtual Sessions are available to Virtual Premium, Virtual Platinum & Virtual Mini-Bootcamp pass holders.
- ODSC Trainings are scheduled from June 14th – Thursday, June 15th. In-person sessions are available to Platinum & Mini-Bootcamp Pass holders. Virtual Sessions are available to Virtual Platinum & Virtual Mini-Bootcamp pass holders.
- ODSC Workshop/Tutorials are scheduled from June 14th to Thursday, June 15th. All in-person sessions are available to Platinum & Mini-Bootcamp holders. Virtual Sessions are available for Virtual Premium, Virtual Platinum & Virtual Mini-Bootcamp pass holders.
- ODSC Bootcamp Sessions are scheduled VIRTUALLY on Tuesday, June 13 as pre-conference training. They are ONLY available for In-person Mini-Bootcamp, and VIP Pass and Virtual Mini-Bootcamp holders.
Speaker and speaker schedule times are subject to change.
Please Note: In-Persons attendees will have access to virtual sessions. If you have a virtual Pass, please note that we will not live-stream any in-person sessions. Only virtual sessions will be recorded.
The prerequisites to the workshop and training sessions are available HERE
Please review the final schedule:
– for in-person: Download TBM Engage app
Enter the app code: europe2023 in the App Store
– for virtual: live.odsc.com (agenda section) Log in using your email address while registering.
In-person | Bootcamp | Machine Learning | Beginner
In this workshop, you will get acquainted with the pandas library, which is the most widely used package for reading, analyzing and exporting datasets in Python. You will also learn how to visualize many kinds of tabular data using the plotnine package, along with some tips and tricks on how to make your visualizations stand out. Lastly, you will have the opportunity make predictions and take decisions using data, based on basic statistical methods…more details
Virtual | Bootcamp | Machine Learning | Beginner
The Introduction to Machine Learning Workshop will build upon the attendee’s foundation of math and coding knowledge to develop a basic understanding of the most popular machine learning algorithms used in industry today. We will answer such questions as: What are the different types of ML algorithms ? What is Overfitting and how can we avoid it? Why is XGBoost consistently outperform other algorithms?…more details
Virtual | Bootcamp | Beginner
In this class students will install Anaconda Python and Jupyter Labs. Using this Jupyter Lab interface I will cover the basics of Python programming. Topics will include built in data structures, functions, looping, decisions, and importing other libraries…more details
In-person | Talk | AI Safety | Machine Learning | Deep Learning | Advanced
In this talk, I will cover several new and practical tools for improving evaluation in safety-critical settings that improve statistical guarantees of estimates, as well as provide more insights on how to perform robust evaluation in situations where traditional assumptions cannot be met. I will draw connections with topics from interpretability, causal inference and uncertainty estimation and discuss how these are all key for evaluation…more details
In-person | Track Keynote | Machine Learning | Intermediate
In this talk I will present two new open-source packages that make up a powerful and state-of-the-art marketing analytics toolbox. Specifically, PyMC-Marketing is a new library built on top of the popular Bayesian modeling library PyMC. PyMC-Marketing allows robust estimation of customer acquisition costs (via media mix modeling) as well as customer lifetime value…more details
Virtual | Keynote | All | All Levels
In this session we take a deep-dive into Azure Machine Learning, a cloud service that you can use to track as you build, train, deploy, and manage models. We use the Azure Machine Learning Python SDK to manage the complete life cycle of a PyTorch model, from managing the data, to train the model and finally run it into a production Kubernetes cluster…more details
In-person | Talk | Machine Learning | Deep Learning | Intermediate-Advanced
In this session, we will provide examples of when quantum computing is best applied to accelerate health care-specific applications and biomedical research. We will also provide an overview of how quantum computing works and a short overview of how to leverage open-source libraries, specifically Qiskit and Q#, to build, train, and evaluate a machine learning model for breast cancer prediction using an open dataset. We will also review how to build and run these models on local simulators and how these algorithms can be deployed on quantum hardware through cloud providers such as Azure…more details
In-person | Talk | Data Engineering & Big Data | ALL | All Levels
During this session, we will discuss the enablers that organizations need to unlock productivity with analytics and the importance of optimized algorithmic performance in the cloud to reduce costs, so organizations can derive maximum value from their investments...more details
In-person | Talk | Machine Learning for Finance | Intermediate-Advanced
In the last years, several machine learning innovations have been introduced to improve the robustness of asset allocation with hierarchical clustering and seriation-based approaches, to improve the transparency of these heuristics with explainable AI and to generate synthetic correlations and correlated market returns to improve the coverage of backtests and scenario analysis beyond the historical paths. Together, these innovations offer a consistent pipeline for better understanding rule-based dynamic portfolio allocation strategies. This talk reviews recent developments and puts them into the context of the current market challenges…more details
In-person | Talk | Generative AI | Machine Learning, Deep Learning | All Levels
The session will cover the importance of explaining AI models and their limitations, building effective next-gen data products, evaluating audience and user needs, and the aspects of visualisation that will always require human input. It will focus on the practical implications of AI tools on the roles of data professionals – and look at how we can thrive in this exciting new era…more details
In-person | Talk | ML for Finance | ML Safety (AI Safety) & ML Security | MLOps and Data Engineering | Intermediate
In this talk, I will explain what Zero Trust Architecture is, which problems in data science it solves and how you could implement this into DataOps and MLOps processes. Furthermore, I will connect the concepts to the GDPR and the new/ proposed AI Act and use concrete examples from my projects in cyber security, banking and retail…more details
In-person | Talk
Data Storytelling for Business delves into two indispensable elements of giving great presentations with and about data: compelling data visualizations and designing a coherent and persuasive narrative around data. These skills are relevant across all industries…more details
Virtual | Talk | Responsible AI | NLP | Deep Learning | GenAI | Machine Learning | All Levels
Western societies are marked by diverse and extensive biases and inequality that are unavoidably embedded in the data used to train machine learning. Algorithms trained on biased data will, without intervention, produce biased outcomes and increase the inequality experienced by historically disadvantaged groups…more details
Virtual | Talk | Machine Learning | Deep Learning | NLP | Beginner-Intermediate
In the field of healthcare, AI has been applied across the spectrum from diagnostics to prognostics. Many of these applications have been successfully commercialised yet only some are used in everyday patient care. This talk will introduce the audience to the science behind AI for disease detection (diagnosis) and prediction (prognosis) with a particular focus on musculoskeletal health. We will explore the link between big health data and AI, and finally highlight challenges and opportunities in reliable, representative, scalable and ethical uptake of AI technology in real-world clinical practice…more details
In-person | Talk | Machine Learning | Intermediate
Pandas 2 brings new Arrow data types, faster calculations and better scalability. Dask scales Pandas across cores. Polars is a new competitor to Pandas designed around Arrow with native multicore support. Which should you choose for modern research workflows? We’ll solve a “just about fits in ram” data task using the 3 solutions, talking about the pros and cons so you can make the best choice for your research workflow. You’ll leave with a clear idea of whether Pandas 2, Dask or Polars is the tool to invest in…more details
In-person | Talk | Generative AI | Machine Learning | Deep Learning | Beginner
ChatGPT is the fastest-growing user application in history. Still, this application only has access to information it saw during training and sometimes produces false information, called hallucinations. In this talk, we will show you how to bring your data to LLMs and how to evaluate LLMs for your use case using open-source technology…more details
In-person | Talk | Machine Learning for Finance
In this talk, we will look at how deep learning techniques can be used for building fast option pricers. A large set of representative training data is generated by using the numerical pricers. Then deep neural networks are used to learn the non-linear pricing functions…more details
In-person | Talk | Machine Learning Safety and Security | Deep Learning | Intermediate
This lecture will describe progress with developing automated certification techniques for learnt software components to ensure safety and adversarial robustness of their decisions. I will discuss different dimensions of robustness, including to bounded perturbations and causal interventions, as well as the role of uncertainty and explainability…more details
In-person | Track Keynote | Data Engineering & Big Data | Deep Learning | Machine Learning | All Levels
The biggest challenges for developers of AI applications very often consist in building & delivering software to be used as a decision-making tool by operational staff. We will present how these challenges have been addressed using 2 successful projects: a cash flow prediction application (for one of Europe’s largest retailers) and a sales prediction app for a Quick Restaurant service…more details
Virtual | Talk | Deep Learning | Machine Learning | NLP | Beginner-Intermediate
This talk compares a cloud-native data streaming architecture to traditional batch and big data alternatives and explains benefits like the simplified architecture, the ability of reprocessing events in the same order for training different models, and the possibility to build a scalable, mission-critical ML architecture for real time predictions with muss less headaches and problems…more details
Virtual | Talk | Machine Learning for Finance | All Levels
The principal component analysis (PCA) is a staple statistical and unsupervised machine learning technique in finance. The application of PCA in a financial setting is associated with several difficulties, such as numerical instability and nonstationarity. We attempt to resolve them by proposing two new variants of PCA: an iterated principal component analysis (IPCA) and an exponentially weighted moving principal component analysis (EWMPCA). Both variants rely on the Ogita-Aishima iteration as a crucial step…more details
Virtual | Talk | Deep Learning | Machine Learning | Intermediate
A central challenge to contemporary AI is to integrate learning and reasoning. The integration of learning and reasoning has been studied for decades already in the fields of statistical relational artificial intelligence and probabilistic programming. Statistical relational AI has focussed on unifying logic and probability, the two key frameworks for reasoning, and has extended this probabilistic logics machine learning principles…more details
Virtual | Talk | Generative AI | NLP | Deep Learning | Machine Learning
This session will provide an overview of these challenges and opportunities of PLMs for text summarisation using the biomedical domain as an example…more details
In-person | Talk | Generative AI | NLP
Language models are increasingly attracting interest from writers. However, such models lack long-range semantic coherence, limiting their usefulness for longform creative writing. We address this limitation by applying language models hierarchically, in a system we call Dramatron…more details
In-person | Talk | All Levels
Services like ChatGPT and others powered by Generative AI are fueling innovation and efficiency across industries. However, for enterprises these services do not come without their risks, as they raise critical questions regarding data privacy and contextual accuracy considerations. In this presentation, we delve into the deployment of open source LLMs within secure environments. We discuss the advantages of this approach for enterprises, including heightened data privacy, improved accuracy, and greater control over AI implementations in enterprise settings…more details
In-person | Talk | Machine Learning | Beginner-Intermediate
In this session, we confront the widely acknowledged limitation in traditional statistical analysis and machine learning: ‘correlation is not causation.’ We start by dissecting this concept, outlining the challenges it presents when trying to derive meaningful insights from data…more details
In-person | Talk | Machine Learning | Deep Learning | Intermediate
In this session, we’ll explore and discuss the following:
– Why and what is Ray
– How AIR, built atop Ray, allows you to program and scale your machine learning workloads easily
– AIR’s interoperability and easy integration points with other systems for storage and metadata needs
– AIR’s cutting-edge features for accelerating the machine learning lifecycle such as data preprocessing, last-mile data ingestion, tuning and training, and serving at scale..more details
In-person | Business Talk | Machine Learning | ML for Finance | MLOps and Data Engineering | Beginner-Intermediate
The successful deployment of machine learning (ML) models into production has traditionally been a complex and resource-intensive process that many organizations struggle with. With the rise of MLOps, a methodology that applies DevOps principles to ML, this process has become much more streamlined. At the Dutch fintech Mollie, we have fully embraced MLOps and implemented a cloud-based ML platform that supports both batch and real-time inference, as well as a suite of MLOps tools to facilitate the entire development cycle…more details
In-person | Talk | Generative AI | NLP Deep Learning | Machine Learning | Intermediate
Large Language Models (LLMs) such as GPT, LLaMa etc are everywhere these days. In this talk, we will see how to leverage the LLMs when using the Julia Programming Language. We will discuss how to run inference using these models from Julia, how to fine tune them, and even how to access third party hosted models from Julia code. At the end of this session, a Julia developer will have all the tools needed to use LLMs when writing Julia code…more details
Virtual | Talk | Responsible AI | NLP | Deep Learning | GenAI | Machine Learning | Beginner
In recent years fairness in machine learning (ML) and artificial intelligence (AI) has emerged as a highly active area of research and development. Most define fairness in simple terms, where fairness means reducing gaps in performance or outcomes between demographic groups while preserving as much of the accuracy of the original system as possible. This oversimplification of equality through fairness measures is troubling. Many current fairness measures suffer from both fairness and performance degradation, or “levelling down,” where fairness is achieved by making every group worse off, or by bringing better performing groups down to the level of the worst off…more details
Virtual | Talk | NLP | Machine Learning | Deep Learning | Generative AI | All Levels
In this talk, I will first introduce the field of semantics and the task of semantic analysis, a.k.a, semantic parsing from a multilingual perspective. In particular, we will first discuss the layers of meaning, from morphology to pragmatics, and then define the scope of semantics as a field…more details
Virtual | Talk | Responsible AI and Social Good | Machine Learning | Deep Learning | Intermediate
The presentation will provide information on value-alignment methods, will give insights on how to address the construction of morality in machines, and will discuss the importance of teaching tecno-ethics in education…more details
Virtual | Talk | Generative AI | Machine Learning | Deep Learning | Beginner
In this talk, I will describe the latest developments in methodologies that can be used to detect social biases in texts generated by GAI systems. In particular, I will describe methods that can be used to detect social biases expressed not only in English but other languages as well, with minimal human intervention…more details
In-person | Talk | Machine Learning | Intermediate
The session will commence with an overview of the bottom-up and top-down modelling approaches, highlighting their respective strengths and limitations in various data science applications. Attendees will learn how bottom-up modelling focuses on individual components and their interactions, such as modelling individual customer demand in a supply chain, while top-down modelling emphasises the high-level relationships between components to provide a broader perspective, like analysing the overall market trends affecting the supply chain…more details
In-person | Talk | ML for Finance | Machine Learning | Deep Learning | Intermediate
This talk will focus on forecasting inflation with ML and ‘alternative data’. It will show the steps of building such models, the improvements over the traditional econometric models, and will describe the many hurdles a practical implementation of such an approach entails…more details
In-person | Talk | NLP | Machine Learning | Intermediate
In this talk, I will first give an overview of the built-in functionality available in spaCy, using pretrained models. I will showcase how linguistic information such as part-of-speech tags and dependency parses can help you identify interesting patterns or phrases in your documents and ultimately perform document classification or other information retrieval tasks…more details
In-person | Talk | Machine Learning | Deep Learning | NLP | Beginner-Intermediate
During the talk, we’ll show how Ludwig’s novel compositional model architecture referred to as encoder-combiner-decoder makes it possible to easily mix multiple modalities of data such as text, images, audio with structured data in a way that is consistently easy across tasks like regressions, classification, and even generation…more details
In-person | Talk | Data Engineering | MLOps | Intermediate
In this talk, Leanne will take us through how the FT, already with a large number of models in production, are spearheading a journey to improve, iterate and upgrade the way they develop, deploy and monitor their ML and Data Science capabilities, all whilst keeping their current capabilities running. Leanne will highlight they key approaches and considerations when looking to improve your MLOps processes, and how you can expedite your ML in production activities, while ensuring you keep “the car on the road”…more details
In-person | Talk | MLOps & Data Engineering | Responsible AI | Beginner
From this talk you will learn:
– What ML Governance is meant to achieve
– How to get started with a template process
– The role of documentation (and especially Google Model Cards)
– Which roles have what responsibilities
– The relevance of a governance board
Virtual | Talk | Generative AI | Deep Learning | NLP | All Levels
Deep learning especially large language models has been gaining a lot of recent traction from research community. This talk builds some background in deep learning towards explaining the concepts of large language models. Afterward, this talk lists different popular large language models, conducts brief comparison in terms of techniques and accuracy results among different large language models…more details
Virtual | Talk | Machine Learning | Deep Learning | Intermediate
A common problem in the cybersecurity industry is how to detect and track botnets when there are billions of daily attacks. Botnets are internet connected devices that perform repetitive tasks, such as Distributed Denial of Service (DDoS). In many cases, these consumer devices are infected with malicious malware that is controlled by an external entity, often without the owner’s knowledge…more details
In-person | Talk | Generative AI | Beginner-Intermediate
Daily communication via text between customer service agents and clients is rapidly increasing day by day, and banking is not an exception. In this talk we will explain how we experimented with generative NLP models to assist financial advisors in their daily interactions with clients. For this work we have used a seq2seq deep learning neural network architecture based on two LSTM acting as encoder and decoder…more details
In-person | Business Talk | Deep Learning | Machine Learning | Beginner-Intermediate
Sam will lift the lid on the deep learning models used by Ocado Technology and how these have been adapted for the challenges faced in online grocery, showcasing the positive results achieved by the retailers who have adopted these forecasting solutions including 50% improvement in accuracy, drastically reduced waste, automation of replenishment decisions and big financial savings. Join this session to get a glimpse into a real life example of deep learning in production and how it is having an impressive impact in the ecommerce space…more details
In-person | Talk | MLOPs | All Levels
If your models are doing great in experimentation but you are still trying to put all the production pieces together, This session might help you understand what’s going wrong and how to fix it. By working according to this methodology data scientists can iterate rapidly which is at the core of a successful ML project…more details
Virtual | Talk | NLP | LLM | Intermediate-Advanced
In this talk, I address the challenge of learning from limited data for a range of natural language understanding tasks and applications. I will present our work on few-shot learning approaches to NLP in both monolingual and cross-lingual settings and present findings in tasks such as word sense disambiguation, syntactic parsing and text classification. Finally, I will present recent research on approaches that can enable higher levels of data efficiency, and show how they can outperform much more computationally complex counterparts…more details
Virtual | Talk | MLOps & Data Engineering | Intermediate
The benefits of Real-Time Machine Learning are becoming increasingly apparent. Digital native companies have long proven that use cases like fraud detection, recommendation systems, and dynamic pricing all benefit from lower latencies. In a recent KDD paper*, Booking.com found that even a 30% increase in model serving latency caused a .5% decrease in user conversion, a significant cost to their business…more details
Virtual | Talk | Responsible AI | Machine Learning | All Levels
AI-powered coding assistants, such as GitHub Copilot, are spreading rapidly in the software engineering community. Copilot was developed by Microsoft and OpenAI on top of Codex, a transformer-based Large Language Model, and overtook 400.000 subscribers in the first month. It was praised by influential engineers, including Guido van Rossum, the inventor of the Python language…more details
Virtual | Talk | Deep Learning | NLP | Machine Learning | All Levels
This talk will demonstrate the power of compound sparsity for model compression and inference speedup for NLP and CV domains, with a special focus on the recently popular Large Language Models…more details
In-person | Business Talk | AI for Transportation | All Levels
In this talk we will be focusing on the third point, showing how a digital strategy can be driven by information more than by data, while still relying on advanced algorithms to solve very large scale problems. We will draw from extensive expertise working with companies in the logistics and distribution industry, optimizing distribution networks and their operation: hub-and-spoke configuration, intermodal operation, truck scheduling, and driver fleet optimization. In all these cases, we will discuss how capturing and digitizing the right information in the form of constraints has been critical to producing realistic recommendations accepted by the operation teams on the ground. As a side yet non-negligible benefit, digitized information is knowledge that stays within the company instead of leaving when the expert employee changes job or retires. This results in more resilient companies, robust operations ready for scale, a proactive mindset instead of reactive, and a positive environmental impact in the form of supply chain decarbonization…more details
In-person | Talk | Machine Learning | Intermediate-Advanced
This session is designed for data practitioners who wish to maintain control and confidence over their projects even after deployment in production. We will explore two methods from the O’Reilly book “Fundamentals of Data Observability” that can be easily adopted to ensure the reliability of data pipelines throughout the whole process, from ingestion to analytics…more details
In-person | Talk | Deep Learning | MLOps | Intermediate
Deploying advanced Machine Learning technology to serve customers and/or business needs requires a rigorous approach and production-ready systems. This is especially true for maintaining and improving model performance over the lifetime of a production application. Unfortunately, the issues involved and approaches available are often poorly understood…more details
Virtual | Talk | Machine Learning | All Levels
The talk is intended for graduate students, professionals, and MBA students seeking an introduction to forecasting methods without diving too deep into theoretical details. Participants will develop skills, mindsets, and behaviors sought after in the industry today…more details
Virtual | Talk | Responsible AI | Machine Learning | All Levels
Statistical reasoning shapes our collective sense of what is true, what is best, and what should happen next. Even before we mechanized statistical prediction through machine learning, it was a habitual convention that was used as a marker of quality, rigorous science and democratic fairness…more details
Virtual | Talk | Machine Learning for Finance | Intermediate
The objective of this session is to make attendees familiar with the reasons why probabilistic machine learning is the next generation of AI in finance and investing…more details
In-person | Talk | Machine Learning | MLOps and Data Engineering | Beginner
Machine learning has become an integral part of modern business operations, but the success of these projects depends on the quality of the underlying software. Unfortunately, many machine-learning prototypes fail to reach production systems because data science teams incur accidental and intentional technical debt faster than they get to their solution…more details
In-person | Business Talk | Machine Learning for Finance | Machine Learning | All Levels
The purpose of this talk is to explain which business skills are most needed by analytics professionals, illustrate why each is so critical, and help analytics leaders to foster these skills within their teams. We will progress through the skills roughly in the order they are needed—from skills for the first year out of university up through skills needed to run an entire analytics program. In this talk, Dr. Stephenson will draw on best practices, case studies, research, and personal anecdotes from his twenty years of hands-on analytic leadership of teams of analytics professionals spanning six continents, as well as several years helping design and teach executive programs as an adjunct at the Amsterdam Business School…more details
In-person | Talk | Machine Learning | Machine Learning Safety and Security | Data Engineering & Big Data | Responsible AI | Intermediate
If you’ve ever asked one of the questions above, then this talk is for you! You’ll learn how the ability to interpret a model can identify poor model performance or, worse, bias that could ultimately impact the fairness of your machine learning applications. You’ll learn about some of the most common algorithms, how they work and how you can get started using them yourself…more details
In-person | Tutorial | Data Engineering & Big Data | Deep Learning | Machine Learning | All Levels
This workshop presents Taipy, a new low-code Python package that allows you to create complete Data Science applications, including graphical visualization and managing algorithms, pipelines, and scenarios…more details
In-person | Tutorial | Generative AI | Machine Learning | Deep Learning | NLP | Intermediate-Advanced
In the first part of the talk I will provide an overview of the latest generative AI models and how they work. This will include discussing the various types of generative AI models, such as diffusion models for image generation and transformer (GPT-like) models for text generation and their underlying architectures and key concepts…more details
In-person | Half-Day Training | Machine Learning for Finance | Intermediate
This half-day trading session covers the most important Python topics and skills to apply AI and Machine Learning (ML) to Algorithmic Trading. The session shows how to make use of the Oanda trading API (via a demo account) to retrieve data, to stream data, to place orders, etc. Building on this, a ML-based trading strategy is formulated and backtested. Finally, the trading strategy is transformed into an online trading algorithm and is deployed for real-time trading on the Oanda trading platform…more details
In-person | Workshop | Machine Learning | Deep Learning | Intermediate
In this workshop we will illustrate both approaches using a consistent single example. We will use TensorFlow in a Colab notebooks, so all you need is a recent version of Chrome and a Google login. You will not need prior knowledge with TensorFlow, but need a good understanding of how training neural networks work as a prerequisite…more details
In-person | Tutorial | Deep Learning | Machine Learning | NLP | Beginner
In this tutorial, we will illustrate the evolution of deep learning architectures and how KNIME Analytics Platform is naturally designed to keep up with these transformations. We will start off by introducing simple ANNs for a classification task. While easy to grasp, ANNs are not suitable to effectively work with sequential (e.g., texts and time series) or visual data (e.g, images and videos). Other, more complex architectures proved superior. We will zoom in on RNNs with LSTM units for text generation and time series forecasting; CNNs for image classification and styling; and GANs for synthetic image generation…more details
In-person | Full-Day Training | NLP | Beginner
In this course we will go through Natural Language Processing fundamentals, such as pre-processing techniques,tf-idf, embeddings, and more. It will be followed by practical coding examples, in python, to teach how to apply the theory to real use cases…more details
In-person | Workshop | Intermediate
Real-Time Analytics is one of the new trends in the streaming space, but it can be hard to keep track of everything, especially as it seems like new products are being released every week. We’ll start off this session with a presentation that will give you a map to understand the space. This map will hopefully make it easier to understand where current and new tools fit into the space…more details
In-Person | Tutorial | NLP | Machine Learning&Deep Learning | Intermediate-Advanced
While deep learning has driven impressive progress, one of the toughest remaining challenges is generalization beyond the training distribution. Few-shot learning is an area of research that aims to address this, by striving to build models that can learn new concepts rapidly in a more “human-like” way. While many influential few-shot learning methods were based on meta-learning, recent progress has been made by simpler transfer learning algorithms, and it has been suggested in fact that few-shot learning might be an emergent property of large-scale models. In this talk, I will give an overview of the evolution of few-shot learning methods and benchmarks from my point of view, and discuss the evolving role of meta-learning for this problem. I will discuss lessons learned from using larger and more diverse benchmarks for evaluation and trade-offs between different approaches, closing with a discussion about open questions…more details
Virtual | Workshop | Machine Learning | Intermediate-Advanced
In this tutorial we will dive into a particular space science / engineering domain: the calibration of space instruments. For this we take a dedicated look at calibration data from the so-called Cosmic Dust Analyzer (CDA) that was part of NASA’s Cassini mission in the Saturnian system. Together, we will see how the data has been generated, explore their features and limits and will determine how deep learning can help us to create new state-of-the art calibration solutions for space missions…more details
Virtual | Workshop | NLP | Machine Learning | Beginner-Intermediate
In this workshop, you’ll walk through a complete end-to-end example of using Hugging Face Transformers, involving both our open-source libraries and some of our commercial products. Starting from a dataset containing real-life product reviews from Amazon.com, you’ll train and deploy a text classification model predicting the star rating for similar reviews…more details
Virtual | Workshop | All | Beginner-Intermediate
The goal of this session is to get you familiarized with diffusion models, their inner workings, and different approaches to data generation. We’ll use Google Colab to build and train a simple diffusion model. You should be comfortable using Jupyter Notebooks, and training simple models in PyTorch…more details
In-person | Tutorial | Generative AI | NLP | Deep Learning | Machine Learning | All Levels
During this talk you will learn more about Transformer-based models and some best practice to optimize domain specific fully Open Source LLMs to be deployed and used in private managed environments having computational power constraints. Attendees will learn about the critical importance of the Engineering more than Data Science behind LLMs management…more details
In-person | Tutorial | Machine Learning | Data Engineering & Big Data | All Levels
The workshop objective is to use the Yelp Dataset to create business recommendations for users exploiting the network composed of reviews, users, friends, tips, and businesses. The workshop will start from the downloaded jsons of the Yelp dataset from which we will create csvs for the import on a Neo4j Database…more details
Virtual | Tutorial | MLOps & Data Engineering | Machine Learning | Intermediate
In this talk, Gal (Senior Data Scientist, Fiverr) and Itai (CPO, Mona) share how Fiverr utilizes advanced tools, both home-grown and bought, to bridge the gap between data science and business, empower data scientists to understand the behavior of their models in production and make sure their AI solutions bring the value they’re expected to deliver…more details