Fast and Robust Learning by Reinforcement Signals: Explorations in the Insect Brain

• Published in: Neural computation Vol. 21; no. 8; pp. 2123 - 2151
• Main Authors: Huerta, Ramón, Nowotny, Thomas
• Format: Journal Article
• Language: English
• Published: One Rogers Street, Cambridge, MA 02142-1209, USA MIT Press 01.08.2009; MIT Press Journals, The
• Subjects: Animal cognition; Animals; Applied sciences; Artificial intelligence; Behavior, Animal; Biological and medical sciences; Brain; Brain - physiology; Computer science; control theory; systems; Exact sciences and technology; Fundamental and applied biological sciences. Psychology; General aspects; Humans; Insecta - anatomy & histology; Insecta - physiology; Insects; Learning - physiology; Learning and adaptive systems; Letters; Mathematics; Mathematics in biology. Statistical analysis. Models. Metrology. Data processing in biology (general aspects); Miscellaneous; Models, Biological; Multivariate analysis; Mushroom Bodies - physiology; Nonlinear Dynamics; Probability and statistics; Recognition (Psychology) - physiology; Reinforcement (Psychology); Sciences and techniques of general use; Statistics; Brain; Neural computation; Stimulus; Error estimation; Insecta; Reinforcement learning; Benchmarks; Brain models; Classifier; Pattern recognition; Neural network; Knowledge; Stationary condition; Statistical test; System performance; Dynamics; Arthropoda; Classification; Plasticity; Database; Invertebrata; Cultivated mushroom
• ISSN: 0899-7667; 1530-888X
• DOI: 10.1162/neco.2009.03-08-733

We propose a model for pattern recognition in the insect brain. Departing from a well-known body of knowledge about the insect brain, we investigate which of the potentially present features may be useful to learn input patterns rapidly and in a stable manner. The plasticity underlying pattern recognition is situated in the insect mushroom bodies and requires an error signal to associate the stimulus with a proper response. As a proof of concept, we used our model insect brain to classify the well-known MNIST database of handwritten digits, a popular benchmark for classifiers. We show that the structural organization of the insect brain appears to be suitable for both fast learning of new stimuli and reasonable performance in stationary conditions. Furthermore, it is extremely robust to damage to the brain structures involved in sensory processing. Finally, we suggest that spatiotemporal dynamics can improve the level of confidence in a classification decision. The proposed approach allows testing the effect of hypothesized mechanisms rather than speculating on their benefit for system performance or confidence in its responses.