Radiation Effect on Learning Behavior in Memristor-Based Neuromorphic Circuit

Dahl, Sumedha Gandharava; Ivans, Rober C.; Cantley, Kurtis D.

doi:10.1109/mwscas.2019.8885288

Cited by 3 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More information about the network architecture can be found in refs. [18][19][20]. Neuron death in the network is imitated by disabling pre-synaptic neurons randomly during the simulation (STDP learning happens constantly).…”

Section: Neural Network Topologymentioning

confidence: 99%

See 1 more Smart Citation

Neuron Circuit Failure and Pattern Learning in Electronic Spiking Neural Networks

et al. 2022

View full text Add to dashboard Cite

Biological neural networks demonstrate remarkable resilience and the ability to compensate for neuron losses over time. Thus, the effects of neural/synaptic losses in the brain go mostly unnoticed until the loss becomes profound. This study analyses the capacity of electronic spiking networks to compensate for the sudden, random neuron failure (“death”) due to reliability degradation or other external factors such as exposure to ionizing radiation. Electronic spiking neural networks with memristive synapses are designed to learn spatio-temporal patterns representing 25 or 100-pixel characters. The change in the pattern learning ability of the neural networks is observed as the afferents (input layer neurons) in the network fail/die during network training. Spike-timing-dependent plasticity (STDP) learning behavior is implemented using shaped action potentials with a realistic, non-linear memristor model. This work focuses on three cases: (1) when only neurons participating in the pattern are affected, (2) when non-participating neurons (those that never present spatio-temporal patterns) are disabled, and (3) when random/non-selective neuron death occurs in the network (the most realistic scenario). Case 3 is further analyzed to compare what happens when neuron death occurs over time versus when multiple afferents fail simultaneously. Simulation results emphasize the importance of non-participating neurons during the learning process, concluding that non-participating afferents contribute to improving the learning ability and stability of the neural network. Instantaneous neuron death proves to be more detrimental for the network compared to when afferents fail over time. To a surprising degree, the electronic spiking neural networks can sometimes retain their pattern recognition capability even in the case of significant neuron death.

show abstract

Section: Neural Network Topologymentioning

confidence: 99%

“…More about the network behavior in absence of neuron death can be found in refs. [18,19]. The neural network used for the remaining parts of this study has 100 pre-synaptic neurons with 60 participating (firing mutually correlated spikes) and 40 non-participating (firing Poisson distributed uncorrelated spikes) afferents.…”

Section: No Neuron Death (Control Case)mentioning

confidence: 99%

Neuron Circuit Failure and Pattern Learning in Electronic Spiking Neural Networks

et al. 2022

View full text Add to dashboard Cite

show abstract

Effects of memristive synapse radiation interactions on learning in spiking neural networks

2021

Self Cite

View full text Add to dashboard Cite

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.

show abstract

The Effects of Radiation on Memristor-Based Electronic Spiking Neural Networks

Dahl¹

Self Cite

View full text Add to dashboard Cite

In this dissertation, memristor-based spiking neural networks (SNNs) are used to analyze the effect of radiation on the spatio-temporal pattern recognition (STPR) capability of the networks. Two-terminal resistive memory devices (memristors) are used as synapses to manipulate conductivity paths in the network. Spike-timing-dependent plasticity (STDP) learning behavior results in pattern learning and is achieved using biphasic shaped pre- and post-synaptic spikes. A TiO2 based non-linear drift memristor model designed in Verilog-A implements synaptic behavior and is modified to include experimentally observed effects of state-altering, ionizing, and off-state degradation radiation on the device. The impact of neuron "death" (disabled neuron circuits) due to radiation is also examined. In general, radiation interaction events distort the STDP learning curve undesirably, favoring synaptic potentiation. At lower short-term flux, the network is able to recover and relearn the pattern with consistent training, although some pixels may be affected due to stability issues. As the radiation flux and duration increases, it can overwhelm the leaky integrate-and-fire (LIF) post-synaptic neuron circuit, and the network does not learn the pattern. On the other hand, in the absence of the pattern, the radiation effects cumulate, and the system never regains stability. Neuron-death simulation results emphasize the importance of non-participating neurons during the learning process, concluding that non-participating afferents contribute to improving the learning ability of the neural network. Instantaneous neuron death proves to be more detrimental for the network compared to when the afferents die over time thus, retaining the network's pattern learning capability.

show abstract

Radiation Effect on Learning Behavior in Memristor-Based Neuromorphic Circuit

Cited by 3 publications

References 19 publications

Neuron Circuit Failure and Pattern Learning in Electronic Spiking Neural Networks

Neuron Circuit Failure and Pattern Learning in Electronic Spiking Neural Networks

Effects of memristive synapse radiation interactions on learning in spiking neural networks

The Effects of Radiation on Memristor-Based Electronic Spiking Neural Networks

Contact Info

Product

Resources

About