From the Publisher:
Lifelong learning addresses situations in which a learner faces a series of different learning tasks providing the opportunity for synergy among them. Explanation-based neural network learning (EBNN) is a machine learning algorithm that transfers knowledge across multiple learning tasks. When faced with a new learning task, EBNN exploits domain knowledge accumulated in previous learning tasks to guide generalization in the new one. As a result, EBNN generalizes more accurately from less data than comparable methods. Explanation-Based Neural Network Learning: A Lifelong Learning Approach describes the basic EBNN paradigm and investigates it in the context of supervised learning, reinforcement learning, robotics, and chess.
Cited By
- Wu X, Dai P, Deng W, Chen H, Wu Y, Cao Y, Shan Y and Qi X CL-NeRF Proceedings of the 37th International Conference on Neural Information Processing Systems, (34426-34438)
- Basu S, Kveton B, Zaheer M and Szepesvári C No regrets for learning the prior in bandits Proceedings of the 35th International Conference on Neural Information Processing Systems, (28029-28041)
- Wick J, Hemberg E and O’Reilly U Getting a Head Start on Program Synthesis with Genetic Programming Genetic Programming, (263-279)
- Boutilier C, Hsu C, Kveton B, Mladenov M, Szepesv�ri C and Zaheer M Differentiable meta-learning of bandit policies Proceedings of the 34th International Conference on Neural Information Processing Systems, (2122-2134)
- Sodhani S, Chandar S and Bengio Y (2020). Toward Training Recurrent Neural Networks for Lifelong Learning, Neural Computation, 32:1, (1-35), Online publication date: 1-Jan-2020.
- Stark S, Peters J and Rueckert E A comparison of distance measures for learning nonparametric motor skill libraries 2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids), (624-630)
- Feuz K and Cook D (2017). Collegial activity learning between heterogeneous sensors, Knowledge and Information Systems, 53:2, (337-364), Online publication date: 1-Nov-2017.
- Yao R, Xia S, Zhou Y and Niu Q (2016). Robust lifelong visual tracking using compact binary feature with color attributes, Neurocomputing, 213:C, (172-182), Online publication date: 12-Nov-2016.
- Qing C, Huang Z and Xu X A Cross-Domain Lifelong Learning Model for Visual Understanding 17th Pacific-Rim Conference on Advances in Multimedia Information Processing - Volume 9916, (438-448)
- Feuz K and Cook D (2015). Transfer Learning across Feature-Rich Heterogeneous Feature Spaces via Feature-Space Remapping (FSR), ACM Transactions on Intelligent Systems and Technology, 6:1, (1-27), Online publication date: 11-Mar-2015.
- Cook D, Feuz K and Krishnan N (2013). Transfer learning for activity recognition, Knowledge and Information Systems, 36:3, (537-556), Online publication date: 1-Sep-2013.
- Silver D Machine lifelong learning Proceedings of the 4th international conference on Artificial general intelligence, (370-375)
- Bengio Y, Louradour J, Collobert R and Weston J Curriculum learning Proceedings of the 26th Annual International Conference on Machine Learning, (41-48)
- Hu B, Qu H, Wang Y and Yang S (2009). A generalized-constraint neural network model, Information Sciences: an International Journal, 179:12, (1929-1943), Online publication date: 1-May-2009.
- Madden M and Howley T (2004). Transfer of Experience Between Reinforcement Learning Environments with Progressive Difficulty, Artificial Intelligence Review, 21:3-4, (375-398), Online publication date: 1-Jun-2004.
- Caruana R (1997). Multitask Learning, Machine Language, 28:1, (41-75), Online publication date: 1-Jul-1997.
Recommendations
Integrating inductive neural network learning and explanation-based learning
IJCAI'93: Proceedings of the 13th international joint conference on Artifical intelligence - Volume 2Many researchers have noted the importance of combining inductive and analytical learning, yet we still lack combined learning methods that are effective in practice. We present here a learning method that combines explanation-based learning from a ...
Explanation-Based Learning and Reinforcement Learning: A Unified View
In speedup-learning problems, where full descriptions of operators are known, both explanation-based learning (EBL) and reinforcement learning (RL) methods can be applied. This paper shows that both methods involve fundamentally the same process of ...
Explanation-Based Learning: An Alternative View
In the last issue of this journal Mitchell, Keller, and Kedar-Cabelli presented a unifying framework for the explanation-based approach to machine learning. While it works well for a number of systems, the framework does not adequately capture certain ...