Locally Weighted Learning for Control
Artificial Intelligence Review - Special issue on lazy learning
The Handbook of Brain Theory and Neural Networks
The Handbook of Brain Theory and Neural Networks
Parallel Fiber Coding in the Cerebellum for Life-Long Learning
Autonomous Robots
IEEE Transactions on Neural Networks
An Hypothesis for a Novel Learning Mechanism in the Cerebellar Cortex
Autonomous Robots
Parallel Fiber Coding in the Cerebellum for Life-Long Learning
Autonomous Robots
Context separability mediated by the granular layer in a spiking cerebellum model for robot control
IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part I
Event and time driven hybrid simulation of spiking neural networks
IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part I
Real-time spiking neural network: an adaptive cerebellar model
IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems
Bioinspired adaptive control for artificial muscles
Living Machines'13 Proceedings of the Second international conference on Biomimetic and Biohybrid Systems
Hi-index | 0.00 |
Continuous and real-time learning is a difficult problem in robotics. To learn efficiently, it is important to recognize the current situation and learn appropriately for that context. To be effective, this requires the integration of a large number of sensorimotor and cognitive signals. So far, few principles on how to perform this integration have been proposed. Another limitation is the difficulty to include the complete contextual information to avoid destructive interference while learning different tasks.We suggest that a vertebrate brain structure important for sensorimotor coordination, the cerebellum, may provide answers to these difficult problems. We investigate how learning in the input layer of the cerebellum may successfully encode contextual knowledge in a representation useful for coordination and life-long learning. We propose that a sparsely-distributed and statistically-independent representation provides a valid criterion for the self-organizing classification and integration of context signals. A biologically motivated unsupervised learning algorithm that approximate such a representation is derived from maximum likelihood. This representation is beneficial for learning in the cerebellum by simplifying the credit assignment problem between what must be learned and the relevant signals in the current context for learning it. Due to its statistical independence, this representation is also beneficial for life-long learning} by reducing the destructive interference across tasks, while retaining the ability to generalize. The benefits of the learning algorithm are investigated in a spiking model that learns to generate predictive smooth pursuit eye movements to follow target trajectories.