HackMDDevelopment of algorithms for partial multi-label machine learning
Contents of this documents and quicklinks：
Title
[ENCCS Webinar]: Development of algorithms for partial multi-label machine learning
About the webinar
Machine learning is a branch of artificial intelligence that enables computers to learn from data and make predictions or decisions without being explicitly programmed. Multi-label learning is a type of machine learning problem where each data instance can be associated with multiple labels simultaneously. Partial multi-label learning addresses problems where each instance is assigned a candidate label set and only a subset of these candidate labels is correct. Partial multi-label learning is particularly useful in scenarios where perfect labeling is expensive or impractical, making it an essential area in weakly supervised learning, however, a major of partial multi-label learning is that the training procedure can be easily misguided by noisy labels.
In this webinar, we will talk about the general features of multiple partial multi-label methods, and then the development of learning algorithms to handle dataset with large noisy labels across different domains using varied frameworks, with a focus on the recently developed methods for partial multi-label learning based on the Encoder-Decoder framework.
Who is the webinar for?
This webinar is suitable for data scientists, software developers, scientific researchers, and AI practitioner who are:
- being familiar basics of with machine learning
- working on multi-label optimization and learning, and image processing
- algorithm development for scientific packages
Key takeaways
After attending this seminar, you will:
- Be familiar with classic optimization problems
- Get to know an empirical application of Transformers
- Understand the importance of algorithms design
- Be aware of how speed enhancements are important to the results
Speaker and moderataor
For any questions contact us at training@enccs.se
Registration & Zoom link
Register by visiting this link XXXXXXXXXXXXX
Zoom link: https://liu-se.zoom.us/j/61027533374?pwd=wji2q0z4sQcbIojpl8LkSNTIHLcHVX.1
Meeting ID: 610 2753 3374
Passcode: 267296
Disclaimer
Due to EuroCC2 regulations, we CAN NOT ACCEPT generic or private email addresses. Please use your official university or company email address for registration.
This training is intended for users established in the European Union or a country associated with Horizon 2020. You can read more about the countries associated with Horizon2020 HERE.
