Synthetic Observability Data Generation using GANs
* Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay
Obtaining real-world dataset for AI/ML model development and testing for NFV use cases is extremely difficult for those who are not actively working in this domain for a telco. This difficulty arises due to the nature of business – stringent policies and rules under which the telecom companies have to adhere to. Even the infrastructure metrics, which is the focus of this work, and which may not include any sensitive information, is very difficult to obtain from the real-world NFV environments. This challenge (ITU-T) – generating observability data using GANs, is the first step towards overcoming this difficulty. This talk will elaborate on the problem, explain in detail the dataset, and discuss why GANs can help to solve this problem.
This live event includes a 30-minute networking event hosted on the AI for Good Neural Network. This is your opportunity to ask questions, interact with the panelists and participants and build connections with the AI for Good community.