Abstract
This selective review explores biologically inspired learning as a model for intelligent robot control and sensing technology on the basis of specific examples. Hebbian synaptic learning is discussed as a functionally relevant model for machine learning and intelligence, as explained on the basis of examples from the highly plastic biological neural networks of invertebrates and vertebrates. Its potential for adaptive learning and control without supervision, the generation of functional complexity, and control architectures based on self-organization is brought forward. Learning without prior knowledge based on excitatory and inhibitory neural mechanisms accounts for the process through which survival-relevant or task-relevant representations are either reinforced or suppressed. The basic mechanisms of unsupervised biological learning drive synaptic plasticity and adaptation for behavioral success in living brains with different levels of complexity. The insights collected here point toward the Hebbian model as a choice solution for “intelligent” robotics and sensor systems.
Highlights
The Hebbian synapse and synaptic learning rules [1] are the fundamental conceptual basis of unsupervised learning in biological and artificial neural networks [2]
A synapse refers to a connection between two neurons in a biological or artificial neural network, where the neuron transmitting information via a synapse or synaptic connection is referred as the presynaptic neuron, and the neuron receiving the information at the other end of a synaptic connection as the postsynaptic neuron
The more a synapse is stimulated, the more effectively information flows through the connection, which results in what Hebb [1] and subsequently others have called the long-term potentiation (LTP) of neural connections
Summary
The Hebbian synapse and synaptic learning rules [1] are the fundamental conceptual basis of unsupervised learning in biological and artificial neural networks [2]. This selective review starts with a brief recall of the principles of Hebbian synapse-based learning (Section 2) On this basis, specific examples of biological learning in vertebrates and invertebrates (Sections 3 and 4) are brought to the forefront to illustrate the potential for bioinspired neural network models and self-organizing control of simple and complex agentic functions of robots or other artificially intelligent system. Specific examples of biological learning in vertebrates and invertebrates (Sections 3 and 4) are brought to the forefront to illustrate the potential for bioinspired neural network models and self-organizing control of simple and complex agentic functions of robots or other artificially intelligent system Such functions include rhythmic movement generation and control, goal-directed behaviors, task space coding, sequential action timing, alternative event choice, and sensorimotor integration for action. The hypothesis that the same timing principles apply to the long-range regime of functional interaction between neurons across distant cortical areas is supported by functional neuroanatomy and psychophysics [3,4]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
