Starting Date: June 2024
Prerequisites: Having good knowledge of Python programming is essential. Familiarity with Deep Learning and the PyTorch framework is also important.
Will results be assigned to University: No
Continual learning [1], also known as lifelong learning, refers to the ability of an artificial intelligence system to continuously learn and adapt from new experiences over time. This is an important capability as it allows AI models to acquire new knowledge and skills as more data becomes available, without forgetting previously learned information. Continual learning aims to mimic how biological intelligences like the human brain are able to constantly absorb, retain, and apply new information throughout their lifetimes. Achieving continual learning in AI could lead to more flexible and adaptable systems that don’t become outdated as the world changes.
This project will leverage the recent results in understanding the high-dimensional loss landscapes [2] of deep neural networks to develop and implement new algorithms for continual learning.
Students are welcome to email (anand.subramoney@rhul.ac.uk) for informal discussions.
Reading:
- Delange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., Tuytelaars, T., 2021. A continual learning survey: Defying forgetting in classification tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence 1–1. https://doi.org/10.1109/TPAMI.2021.3057446
- Benton, G., Maddox, W., Lotfi, S., Wilson, A.G.G., 2021. Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling, in: Proceedings of the 38th International Conference on Machine Learning. Presented at the International Conference on Machine Learning, PMLR, pp. 769–779. https://proceedings.mlr.press/v139/benton21a.html