No abstract

No abstract

In this paper, a feed-forward spiking neural network with memristive synapses is designed to learn a spatio-temporal pattern representing the 25-pixel character 'B' by separating correlated and uncorrelated afferents. The network uses spike-timing-dependent plasticity (STDP) learning behavior, which is implemented using biphasic neuron spikes. A TiO2 memristor non-linear drift model is used to simulate synaptic behavior in the neuromorphic circuit. The network uses a many-to-one topology with 25 pre-synaptic neurons (afferent) each connected to a memristive synapse and one postsynaptic neuron. The memristor model is modified to include the experimentally observed effect of state-altering radiation. During the learning process, irradiation of the memristors alters their conductance state, and the effect on circuit learning behavior is determined. Radiation is observed to generally increase the synaptic weight of the memristive devices, making the network connections more conductive and less stable. However, the network appears to relearn the pattern when radiation ceases but does take longer to resolve the correlation and pattern. Network recovery time is proportional to flux, intensity, and duration of the radiation. Further, at lower but continuous radiation exposure, (flux 1x10 10 cm −2 s −1 and below), the circuit resolves the pattern successfully for up to 100 s. CCS CONCEPTS • Computer systems organization → Architectures →Other architectures → Neural networks • Hardware → Hardware test; Emerging technologies → Analysis and design of emerging devices and systems → Emerging architectures; Emerging Simulations

This study uses advanced modeling and simulation to explore the effects of external events such as radiation interactions on the synaptic devices in an electronic spiking neural network. Specifically, the networks are trained using the spike-timing-dependent plasticity (STDP) learning rule to recognize spatio-temporal patterns (STPs) representing 25 and 100-pixel characters. Memristive synapses based on a TiO2 non-linear drift model designed in Verilog-A are utilized, with STDP learning behavior achieved through bi-phasic pre- and post-synaptic action potentials. The models are modified to include experimentally observed state-altering and ionizing radiation effects on the device. It is found that radiation interactions tend to make the connection between afferents stronger by increasing the conductance of synapses overall, subsequently distorting the STDP learning curve. In the absence of consistent STPs, these effects accumulate over time and make the synaptic weight evolutions unstable. With STPs at lower flux intensities, the network can recover and relearn with constant training. However, higher flux can overwhelm the leaky integrate-and-fire post-synaptic neuron circuits and reduce stability of the network.

No abstract