The whole world seems to be focused on NLP and generative AI these days. But without a strong understanding of deep learning, you’ll have a difficult time getting the most out of the cutting-edge developments in the industry. At ODSC West this October 30th to November 2nd, you’ll build the core knowledge and skills you need with the sessions in the deep learning track, such as the ones listed below.

A Semi-Supervised Anomaly Detection System Through Ensemble Stacking Algorithm

Chuying Ma | Senior Data Scientist | Walmart

Because of the sheer amount and diversity of data that must be processed by retail giants, they experience a significant amount of inventory loss and shrinkage that could otherwise be avoided. In this session, you’ll explore a systematic, flexible, extensible, and holistic anomaly detection architecture to augment the existing labels and detect anomalies. This new system can flexibly incorporate deep learning-based anomaly detection models, or any other traditional machine learning models, and generate a unified anomaly score by the ensemble stacking algorithm to address different types of anomalies simultaneously.

Massively Speed-Up your Learning Algorithm, with Stochastic Thinning

Vincent Granville | CEO and Executive Machine Learning Scientist | MLtechniques.com

Explore how you can reduce computing time without decreasing the predictive power of your model with stochastic thinning. This session will use a real-world dataset to illustrate this method with a focus on both its benefits and its limitations.

How to Practice Data-Centric AI and Have AI Improve its Own Dataset

Jonas Mueller | Chief Scientist and Co-Founder | Cleanlab

Drastically decrease the time and manual labor required to improve a machine learning model’s performance with data-centric AI. This session will show you how to operationalize fundamental ideas from data-centric AI across a wide variety of datasets, with a focus on recent algorithms to automatically identify common issues in real-world data.

A Unified and User-Friendly Approach to Develop ML Solutions in MySQL HeatWave AutoML

Sanjay Jinturkar | Senior Director, MySQL HeatWave | Oracle

Sandeep Agrawal, PhD | Consulting Principal Member of Technical Staff | Oracle

Discover how to use MySQL API for HeatWave AutoML for different use cases and its ability to work with third-party applications. You’ll cover the way it can facilitate the development of classification, regression, anomaly detection, forecasting, and recommendation systems use cases.

Keras Core: Keras for TensorFlow, JAX, and PyTorch

Neel Kovelamudi | Software Engineer on Keras Team | Google

Discover what’s new with Keras in this session. You’ll explore the new features of Keras Core, which allows developers to create models with all of the simple high-level components of Keras while interchanging between frameworks to take advantage of the benefits of each.

Facial Recognition from Scratch with Python and JS

Serg Masis | Lead Data Scientist | Syngenta | Best Selling Author

This hands-on session will demonstrate how to build a facial recognition system from scratch using open-source technologies and publically available pre-trained models. During this process, you’ll get experience with Javascript, Python APIs, vector databases, and more.

Speed up Machine Learning Workflows in the Cloud with Lightning 

Noha Alon | Director of Engineering | Lightning AI

Daniela Dapena | Community Research Scientist | Lightning AI

Discover how to speed up machine learning workflows in the Cloud with Lightning, an open-source library. This workshop will demonstrate the library, starting with an introduction to the different methods and proceeding to a review of the best practices for utilizing its key features.

Beyond the Buzz: Decoding Popularity Bias in Large-Scale Recommender Systems

Amey Porobo Dharwadker | Engineering Manager, Machine Learning | Meta

This session will address the significant issue of popularity bias in recommender systems. You’ll explore the current landscape of bias, current approaches for solving it, and what the future might bring. By the end of this session, you should have a better understanding of the issues and the factors contributing to them.

Why Did My AI Do That? Decoding Decision-making in Machine Learning

Swagata Ashwani | Senior Data Scientist | Boomi

Large Language Models are essential for a business’s growth, but their lack of interpretability is a  major issue. In this session, you’ll take a deep dive into state-of-the-art techniques for AI explainability, providing a robust framework for understanding, evaluating, and enhancing model interpretability. You’ll cover intrinsic and post-hoc methods for model explainability, the practical implementation of these methods, and the ethical considerations created by model opacity.

Register here

The above sessions are just the start of your deep learning journey at ODSC WestGet your pass now to lock in our 40% discount. But you’d better act fast–this sale ends Friday!