Please log in to watch this conference skillscast.
In this talk, Dr Sharmanska will start with a fundamental question, what is and what is not visual data in machine versus human perspective.
She will then explain the underlying principles of how do we teach computers ‘to see’ using machine learning methods with examples of recognising objects in visual data.
Subsequently Dr Sharmanska will focus on how can you enhance an automatic systems’ capacity to recognise complex real-world scenes like human actions and emotions using a deep-learning approach.
YOU MAY ALSO LIKE:
- Fast Track to Machine Learning with Louis Dorard (in London on 3rd - 5th September 2018)
- Real-time Data Engineering in the Cloud (in London on 24th - 25th September 2018)
- Brian Sletten's Data Science with R Workshop (in London on 5th - 7th December 2018)
- F# eXchange 2019 (in London on 4th - 5th April 2019)
Towards visual intelligence: Modern Machine Learning in Computer Vision Research
Viktoriia Sharmanska works at Imperial College London as a research fellow leading the project in 'Deep Understanding of Human Behaviour from Video Data: Action Emotion Approach'. Her research interests include deep learning methods and cross-modal transfer that are suitable for learning from complex visual data. Viktoriia is passionate about designing intelligent systems that can learn concepts from visual data using machine learning models.