Machine Learning Capabilities of a Simulated Cerebellum
| Autor: | Peter Stone, Michael D. Mauk, Wen-Ke Li, Matthew Hausknecht |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Cerebellum
Computer Networks and Communications Computer science Models Neurological education Multi-task learning 02 engineering and technology Machine learning computer.software_genre Machine Learning 03 medical and health sciences 0302 clinical medicine Artificial Intelligence Basal ganglia 0202 electrical engineering electronic engineering information engineering medicine Animals Humans Reinforcement learning Computer Simulation Postural Balance Neurons Learning classifier system Artificial neural network business.industry Supervised learning Conditioning Eyelid Computer Science Applications medicine.anatomical_structure Pattern Recognition Physiological Pattern recognition (psychology) Robot Unsupervised learning 020201 artificial intelligence & image processing Neural Networks Computer Artificial intelligence business Reinforcement Psychology computer 030217 neurology & neurosurgery Software MNIST database |
| Zdroj: | IEEE Transactions on Neural Networks and Learning Systems. 28:510-522 |
| ISSN: | 2162-2388 2162-237X |
| DOI: | 10.1109/tnnls.2015.2512838 |
| Popis: | This paper describes the learning and control capabilities of a biologically constrained bottom-up model of the mammalian cerebellum. Results are presented from six tasks: 1) eyelid conditioning; 2) pendulum balancing; 3) proportional-integral-derivative control; 4) robot balancing; 5) pattern recognition; and 6) MNIST handwritten digit recognition. These tasks span several paradigms of machine learning, including supervised learning, reinforcement learning, control, and pattern recognition. Results over these six domains indicate that the cerebellar simulation is capable of robustly identifying static input patterns even when randomized across the sensory apparatus. This capability allows the simulated cerebellum to perform several different supervised learning and control tasks. On the other hand, both reinforcement learning and temporal pattern recognition prove problematic due to the delayed nature of error signals and the simulator's inability to solve the credit assignment problem. These results are consistent with previous findings which hypothesize that in the human brain, the basal ganglia is responsible for reinforcement learning, while the cerebellum handles supervised learning. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|