Abstract
This paper presents a digital silicon neuronal network which simulates the nerve system in creatures and has the ability to execute intelligent tasks, such as associative memory. Two essential elements, the mathematical-structure-based digital spiking silicon neuron (DSSN) and the transmitter release based silicon synapse, allow us to tune the excitability of silicon neurons and are computationally efficient for hardware implementation. We adopt mixed pipeline and parallel structure and shift operations to design a sufficient large and complex network without excessive hardware resource cost. The network with 256 full-connected neurons is built on a Digilent Atlys board equipped with a Xilinx Spartan-6 LX45 FPGA. Besides, a memory control block and USB control block are designed to accomplish the task of data communication between the network and the host PC. This paper also describes the mechanism of associative memory performed in the silicon neuronal network. The network is capable of retrieving stored patterns if the inputs contain enough information of them. The retrieving probability increases with the similarity between the input and the stored pattern increasing. Synchronization of neurons is observed when the successful stored pattern retrieval occurs.
Highlights
The nervous system transmits signals by cooperation between neurons and synapses
We evaluated the functionality of our silicon neuronal network circuit by constructing an auto-associative memory network, which retrieves stored memory patterns in response to an input similar to one of them
The auto-associative memory task is one of the most fundamental task for the fully connected silicon neuronal networks because the analysis of spike generation and phase locking are available to evaluate the properties of the network
Summary
The nervous system transmits signals by cooperation between neurons and synapses. The waveform is distributed to the synapse and causes neuronal transmitters to be released. The silicon neuronal network is designed to reproduce activities of the nerve system in real-time. Compared to the current computers, the silicon neuronal network is based on the parallel and distributed processing mechanism rather than the serial centralized framework. This distinctive computational style is expected to allow real-time and large-scale processing of advanced task similar to that in the nerve system (Mallik et al, 2005; Mitra et al, 2009). A silicon half-center oscillator composed of silicon neurons is proposed for application as an embedded biomedical device and a motion controller (Simoni and DeWeerth, 2007)
Sign-in/Register to view highlights & summary 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.
