On the Continuous AI projectHumans have the extraordinary ability to learn continually from experience. Not only can we apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning. One of the grand goals of AI is building an artificial "continuous learning" agent that constructs a sophisticated understanding of the world from its own experience, through the autonomous incremental development of ever more complex skills and knowledge. This project aims to connect peolple and collect information about this topic.
( ! ) This site is sill in contruction but you can contact vincenzo lomonaco at vincenzo.lomonaco AT unibo.it or simply make a pull request on github if you want to collaborate!
People working on the subjectHere you can find some people working on the subject:
- Raia Hadsell, Razvan Pascanu, James Kirkpatrick - DeepMind
- Mark Ring - Cogitai
- Vincenzo Lomonaco, Davide Maltoni - University of Bologna
- Bing Liu - University of Illinois at Chicago (UIC)
- Eric Eaton - University of Pennsylvania
Papers and related materialsHere you can find all the papers, media articles and other materials related to Continuous Learning and Deep Neural Nets.
- Li, Zhizhong, and Derek Hoiem. "Learning without forgetting". European Conference on Computer Vision. Springer International Publishing, 2016.
- French, Robert M. "Catastrophic forgetting in connectionist networks". Trends in cognitive sciences 3.4 (1999): 128-135.
- Davide Maltoni and Vincenzo Lomonaco. "Semi-supervised Tuning from Temporal Coherence". International Conference on Pattern Recognition ICPR2016.
- Vincenzo Lomonaco and Davide Maltoni. "Comparing Incremental Learning Strategies for Convolutional Neural Networks". IAPR Workshop on Artificial Neural Networks in Pattern Recognition. Springer International Publishing, 2016.
- Vincenzo Lomonaco and Davide Maltoni. "CORe50: a new Dataset and Benchmark for Continuous Object Recognition". arXiv preprint arXiv:1705.03550, 2017.
- James Kirkpatrick et al. "Overcoming catastrophic forgetting in neural networks". Proceedings of the National Academy of Sciences (2017): 201611835.