Spatio-temporal pattern recognition in neural circuits with memory-transistor-driven memristive synapses

Cantley, Kurtis D.; Ivans, Robert C.; Subramaniam, Anand Bala; Vogel, Eric M.

doi:10.1109/ijcnn.2017.7966444

Cited by 7 publications

(6 citation statements)

References 39 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…8b (light color) are firing mutually correlated spikes at regular interval as shown in Fig. 8a, N 12 and N 13 [60,61]. Conversely, non-participating afferents Fig.…”

Section: Pattern Learningmentioning

confidence: 88%

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

“…8b (light color) are firing mutually correlated spikes at regular interval as shown in Fig. 8a, N 12 and N 13 [60,61]. Conversely, non-participating afferents Fig.…”

Section: Pattern Learningmentioning

confidence: 88%

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

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…3b depicts how the STM effect plays a crucial role in extracting temporal features from the input pulse stream. 65 When subjected to sequential inputs, the device exhibits a nonlinear transient response attributed to the STM effect. By aligning the measurement parameters and decay time appropriately, the captured dynamical device state is recorded using fixed time steps, generating nodes that represent reservoir states.…”

Section: Stm Analysis Of Devicementioning

confidence: 99%

Unveiling transient current response in bilayer oxide-based physical reservoirs for time-series data analysis

Lai,

Chen,

Chaurasiya

et al. 2024

Nanoscale

View full text Add to dashboard Cite

show abstract

“…, within the context of spiking neural networks (SNN), is the process by which a spatiotemporal pattern is abstracted down to an output on a single neuron. STPR has been demonstrated using SNNs with synapses with spike-timing-dependent plasticity (STDP) a learning rule that updates synaptic weight according to a spiketiming-dependent learning rule [1]- [7]. In one common approach to STPR, SNNs are trained to recognize a pattern by repeatedly exposing them to the pattern embedded in noise [1], [2].…”

Section: Introduction Spatiotemporal Pattern Recognition (Stpr)mentioning

confidence: 99%

“…STPR has been demonstrated using SNNs with synapses with spike-timing-dependent plasticity (STDP) a learning rule that updates synaptic weight according to a spiketiming-dependent learning rule [1]- [7]. In one common approach to STPR, SNNs are trained to recognize a pattern by repeatedly exposing them to the pattern embedded in noise [1], [2]. After repeated exposures, the synaptic weights adjust in accordance with an STDP learning rule so that the output neuron produces a spike which tends to coincide with the presentation of the pattern.…”

Section: Introduction Spatiotemporal Pattern Recognition (Stpr)mentioning

confidence: 99%

A Spatiotemporal Pattern Detector

Ivans

Cantley

2019

2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS)

Self Cite

View full text Add to dashboard Cite

A spatiotemporal pattern detector design is presented which can identify three fundamental spatiotemporal patterns consisting of two spikes (from different neurons or from the same neuron). These fundamental cases provide the building blocks for construction of more complicated arbitrary spatiotemporal patterns. The overall design consists of three primary subcircuits, and the operation of each is described. The detection of the three cases of spatiotemporal patterns, and the detection of a more complicated pattern by a network of Spatiotemporal Pattern Detectors, is then demonstrated through simulation using the Cadence Virtuoso platform.

show abstract

Spatio-temporal pattern recognition in neural circuits with memory-transistor-driven memristive synapses

Cited by 7 publications

References 39 publications

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

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

Unveiling transient current response in bilayer oxide-based physical reservoirs for time-series data analysis

A Spatiotemporal Pattern Detector

Contact Info

Product

Resources

About