Level Up Your AI Game with More ODSC West Announced Sessions

ODSC West is still months away, but we’re thrilled to share our recently added sessions with you! At the leading AI technical conference, you’ll find deep dives into a whole range of cutting-edge topics, tools, and techniques. Check out a few of them below.

Synthetic Data for Anonymization, Efficiency and Insights

Tobias Hann, PhD | CEO | MOSTLY AI

The rise of GenAI models has reframed the discussion around synthetic data. In this session, you’ll explore what AI-generated synthetic data is, how it is used today, and what its benefits and its limitations are. In particular, you’ll focus on tabular (or structured) synthetic data and the privacy-preserving benefits of working with synthetic data. You’ll even get hands-on with the open-source tool (DataLLM) and create tabular synthetic data yourselves.

Gen AI in Software Development. What should you be looking for?

Mabel Geronimo | Senior Solutions Engineer | GitHub

Dive into the exciting world of AI-assisted development tools to explore the valuable lessons learned and common use cases observed by customers around the globe. You’ll learn about the critical factors to consider when evaluating AI-assisted development tools, focusing on compliance and future product roadmaps. You’ll also be introduced to prompt engineering, a crucial skill for optimizing AI interactions.

Towards Deployable Robot Learning Systems

Zipeng Fu | PhD Student | Stanford University

The field of robotics has recently witnessed a significant influx of learning-based methodologies, revolutionizing areas such as manipulation, navigation, locomotion, and drones. In this session, you’ll delve into the forefront of robot learning systems, particularly focusing on their scalability and deployability to open-world problems, through two main paradigms of learning-based methods for robotics: reinforcement learning and imitation learning.

AI for Work: How GenAI Improve the Way We Work and Collaborate

Sam Liang, PhD | Co-founder and CEO | Otter.ai

Join this discussion on how emerging AI technologies will revolutionize voice communication and meetings, enhance collaboration, transform how teams work, create a knowledge base that ensures transparency across organizations, and empower professionals with personalized AI avatars that can speak and make decisions on their behalf.

Streamlining Unstructured Data for Retrieval Augmented Generation

Matt Robinson | Open Source Tech Lead | Unstructured

Learn about the complexities of handling unstructured data, and practical strategies for extracting usable text and metadata from it. You’ll explore data ingestion from multiple sources, preprocessing unstructured data into a normalized format that facilitates uniform chunking across various file types, and metadata extraction. You’ll also discuss loading processed data into destination storage.

Using APIs in Data Science Without Breaking Anything

Ryan Day | Advanced Data Scientist | Conference of State Bank Supervisors

Join this hands-on workshop to learn step-by-step the process of consuming a REST API in a Jupyter notebook. You’ll create fault-tolerant code that validates the output of APIs and handles errors intelligently. As well as advanced techniques such as progressive backoff to avoid breaking the system you’re trying to call. Finally, you will learn how to make that code reusable by creating a software development kit (SDK) for the API.

Creating APIs That Data Scientists Will Love with FastAPI, SQLAlchemy, and Pydantic

Ryan Day | Advanced Data Scientist | Conference of State Bank Supervisors

In this session, you’ll learn best practices for making APIs that conform to data scientists’ and machine learning engineers’ unique needs. You’ll start with an overview of the primary tasks that data scientists perform in their daily work and the tools in the Python ecosystem that they use such as Jupyter Notebooks, Airflow, FastAPI, and Streamlit, and how those tools interact with APIs.

Develop LLM Powered Applications with LangChain and LangGraph

Eden Marco | LLM Specialist | Google

This intensive hands-on workshop will equip you with the skills needed to unleash the power of LLM agents using the LangGraph library by LangChain. This two-hour session is crafted for AI practitioners who already possess a background in Python and familiarity with LangChain, aiming to elevate their skills in developing cutting-edge LLM agentic applications.

You’ll dive deep into the advanced capabilities of LangGraph, exploring its integration with LangChain to create robust, efficient, and versatile LLM solutions. You’ll also receive a comprehensive introduction to key components such as LCEL, multi-agents, reflection agents, Reflexion agents, and more. Participants will also get hands-on experience with advanced RAG architectures.

Frontiers of Foundation Models for Time Series

Yan Liu, PhD | Professor | University of Southern California

Recently there have been significant research advances in time series modeling and analysis. The best-performing architectures vary highly across applications and domains. In NLP, the Generative Pre-trained Transformer (GPT) has demonstrated impressive performance via training one general-purpose model across various textual datasets.

Furthermore, practical applications of time series raise a series of new challenges, such as multi-resolution, multimodal, missing value, distributeness, and interpretability. In this talk, You’ll explore the recent development in the area, possible paths to foundation models for time series data, and possible future directions for time series research and foundation models.

Bitter Lessons Learned While Building Production-quality RAG Systems for Professional Users of Academic Data

Jeremy Miller | Product Manager, Academic AI Platform | Clarivate

In this session, you’ll learn about the critical challenges faced and the steps needed when transitioning from a demo to a production-quality RAG system for professional users of academic data, such as researchers, students, librarians, research officers, and others.

In particular, you’ll explore the criticality of data quality and availability, making data accessible through APIs, and techniques for making data GenAI-ready.

Sign me up!

Are you intrigued? Get your in-person or virtual pass today to join us at these sessions and more. Plus, you’ll lock in our Early Bird Pricing before it ends this Friday!

Originally posted on OpenDataScience.com

Read more data science articles on OpenDataScience.com, including tutorials and guides from beginner to advanced levels! Subscribe to our weekly newsletter here and receive the latest news every Thursday. You can also get data science training on-demand wherever you are with our Ai+ Training platform. Interested in attending an ODSC event? Learn more about our upcoming events here.