Enterprise Connect is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Next generation UC Application Powered by Machine Learning and Synthetic Data

Jon Hanzelka  (Technical Art Director, AI/ML, Endava)

Location: Enterprise Case Studies Theater

Date: Tuesday, March 26

Time: 3:00 pm - 3:25 pm

Pass Type: 3-Day Conference Pass, 4-Day Conference Pass, Expo Plus Orlando, Half-Day Training - Get your pass now!

Session Type: Enterprise Connect Theater

Vault Recording: TBD


In this presentation we will explore the role synthetic data plays in enhancing machine learning solutions for Unified Communications applications. We'll examine how synthetic data aids in developing more robust algorithms by unlocking diverse training and validation datasets tailored to each unique application. We’ll highlight the advantages synthetic data can offer in overcoming real-world data acquisition challenges and showcase how it serves as an enabler for developing next-generation solutions
1. Introduction to Synthetic Data:
- Definition and overview of synthetic data.
- Distinction between synthetic data and real-world data.
2. Why does Machine Learning need Synthetic Data in Unified Communications:
- Identify the current challenges for Machine Learning in UC that synthetic data can address.
- Examples of limitations in traditional data collection methods.
- Solutions provided by synthetic data to these scenarios.
3. Overview of Synthetic Data Generation for UC:
- Brief introduction to the methods and technologies used in generating synthetic data.
- Discuss the use of proceduralism to create highly varied datasets.
- The importance of photorealism in overcoming the domain gap.
4. Application in Machine Learning Development:
- How synthetic data enhances training and validation of algorithms.
- Edge cases, niche scenarios, and regression analysis.
5. ML Advancements Enabled by Synthetic Data:
- Exploration of advanced features in UC that can be enabled by synthetic data (e.g., action/reaction recognition, etc.)