Abstract
Neuromorphic chips embody computational principles operating in the nervous system, into microelectronic devices. In this domain it is important to identify computational primitives that theory and experiments suggest as generic and reusable cognitive elements. One such element is provided by attractor dynamics in recurrent networks. Point attractors are equilibrium states of the dynamics (up to fluctuations), determined by the synaptic structure of the network; a ‘basin’ of attraction comprises all initial states leading to a given attractor upon relaxation, hence making attractor dynamics suitable to implement robust associative memory. The initial network state is dictated by the stimulus, and relaxation to the attractor state implements the retrieval of the corresponding memorized prototypical pattern. In a previous work we demonstrated that a neuromorphic recurrent network of spiking neurons and suitably chosen, fixed synapses supports attractor dynamics. Here we focus on learning: activating on-chip synaptic plasticity and using a theory-driven strategy for choosing network parameters, we show that autonomous learning, following repeated presentation of simple visual stimuli, shapes a synaptic connectivity supporting stimulus-selective attractors. Associative memory develops on chip as the result of the coupled stimulus-driven neural activity and ensuing synaptic dynamics, with no artificial separation between learning and retrieval phases.
Highlights
Since its birthdate in 1989, with the publication of Carver Mead’s book[1], the field of neuromorphic engineering aims at embodying computational principles operating in the nervous system into analog VLSI electronic devices
Two visual stimuli were repeatedly presented on a LCD screen, acquired in real time by the silicon retina, and mapped onto the recurrent network distributed on two neural chips; our goal was to achieve autonomous associative learning leading to the formation of stimulus-selective attractor states as internal representations (‘memories’) of the stimuli
We demonstrated a neuromorphic network of spiking neurons and plastic, Hebbian, spike-driven synapses which autonomously develops attractor representations of real visual stimuli acquired by a silicon retina
Summary
Since its birthdate in 1989, with the publication of Carver Mead’s book[1], the field of neuromorphic engineering aims at embodying computational principles operating in the nervous system into analog VLSI electronic devices. To make progress in this direction, beyond special-purpose solutions for specific functions, it seems important to identify neural circuitry implementing basic, and hopefully generic, dynamic building blocks, to provide reusable computational primitives, possibly subserving many types of information processing; this is both a theoretical quest and an item in the agenda of neuromorphic science. Steps in this direction have been taken recently in[6], where ‘soft winner-take-all’ subnetworks provide reliable generic elements to compose finite-states machine capable of context-dependent computation. In a previous paper[10] we demonstrated attractor dynamics in a neuromorphic chip, where synaptic efficacies were chosen and fixed so as to support the desired attractor states
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
