A neuromorphic transfer learning algorithm for orthogonalizing highly overlapping sensor array responses

Borthakur, Ayon; Cleland, Thomas A.

doi:10.1109/isoen.2017.7968869

Cited by 8 publications

(13 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As hypothesized for the biological olfactory bulb, odor learning in the network induces the permanent differentiation of granule cells that thereby become selective for higher-order feature combinations that are relatively diagnostic of the learned odor 37 (Figure 2b). We tested whether increased allocations of GCs, enabling each MC to be inhibited by a broader selection of feature combinations, would improve odor learning and identification under noise.…”

Section: Odor Learning Enables Identification Of Occluded Stimulimentioning

confidence: 74%

Rapid online learning and robust recall in a neuromorphic olfactory circuit

2020

Self Cite

View full text Add to dashboard Cite

The mammalian olfactory system learns new odors rapidly, exhibits negligible interference among odor memories, and identifies known odors under challenging conditions. The mechanisms by which it does so are unknown. We here present a general theory for odor learning and identification under noise in the olfactory system, and demonstrate its efficacy using a neuromorphic model of the olfactory bulb. As with biological olfaction, the spike timing-based algorithm utilizes distributed, event-driven computations and rapid online learning. Localized spike timing-dependent plasticity rules are employed iteratively over sequential gammafrequency packets to construct odor representations from the activity of chemosensor arrays mounted in a wind tunnel. Learned odors then are reliably identified despite strong destructive interference. Noise resistance is enhanced by neuromodulation and contextual priming. Lifelong learning capabilities are enabled by adult neurogenesis. The algorithm is applicable to any signal identification problem in which high-dimensional signals are embedded in unknown backgrounds.

show abstract

Section: Odor Learning Enables Identification Of Occluded Stimulimentioning

confidence: 74%

Rapid online learning and robust recall in a neuromorphic olfactory circuit

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Stage 2 would compile the location on each of these four plots to determine the composition of the unknown gas sample. Although this method could work, a superior algorithm that is capable of separating these data points and/or a different combination of sensing materials would result in a better sensor array for these four gases …”

Section: Resultsmentioning

confidence: 99%

Evaluation of doped and undoped poly (o‐anisidine) as sensing materials for a sensor array for volatile organic compounds

Stewart

Scott

Penlidis

2020

Polymers for Advanced Techs

View full text Add to dashboard Cite

Poly (o-anisidine) (PoANI) and PoANI doped with nickel oxide and zinc oxide were evaluated as sensing materials for four gas analytes (methanol, ethanol, acetone, and benzene). The sensing materials had high sensitivity (showing an affinity towards the target analytes even at low concentrations, in the range of 1-5 ppm), but rather poor selectivity, especially when the gas analytes were in a mixture. To exploit the poor selectivity, the three sensing materials were combined into a sensor array using principal component analysis (PCA) as a sensing algorithm. It was found that using a sensor array, the four individual gases could be separated. However, when all four gases were present (in analyte mixtures), there was too much overlap in the responses to distinguish between individual gas analytes and their related mixtures. K E Y W O R D S gas sensor array, nickel oxide (NiO), poly (o-anisidine), principal component analysis (PCA), zinc oxide (ZnO)

show abstract

“…The parameters c m , r m , r shunt , E n , g max , τ 1 , and τ 2 were determined only once each for MCs and GCs using a synthetic data set (Borthakur and Cleland, 2017) and remained unchanged during the application of the algorithm to real datasets. The value of w i at each synapse also was set to a fixed starting value based on synthetic data, but was dynamically updated according to the STDP learning rule.…”

Section: Methodsmentioning

confidence: 99%

“…Excitatory MC-GC synapses were initialized with a uniformly distributed random probability cp of connection and a uniform weight w 0 ; synaptic weights were modified thereafter by learning. The initial connection probability cp was determined using a synthetic data set (Borthakur and Cleland, 2017), and was set to cp = 0.4 in the present simulations. For present purposes, as noted above, GC-MC inhibitory weights were set to zero to disable attractor dynamics.…”

Section: Methodsmentioning

confidence: 99%

A Spike Time-Dependent Online Learning Algorithm Derived From Biological Olfaction

Borthakur

Cleland

2019

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

We have developed a spiking neural network (SNN) algorithm for signal restoration and identification based on principles extracted from the mammalian olfactory system and broadly applicable to input from arbitrary sensor arrays. For interpretability and development purposes, we here examine the properties of its initial feedforward projection. Like the full algorithm, this feedforward component is fully spike timing-based, and utilizes online learning based on local synaptic rules such as spike timing-dependent plasticity (STDP). Using an intermediate metric to assess the properties of this initial projection, the feedforward network exhibits high classification performance after few-shot learning without catastrophic forgetting, and includes a none of the above outcome to reflect classifier confidence. We demonstrate online learning performance using a publicly available machine olfaction dataset with challenges including relatively small training sets, variable stimulus concentrations, and 3 years of sensor drift.

show abstract

A neuromorphic transfer learning algorithm for orthogonalizing highly overlapping sensor array responses

Cited by 8 publications

References 6 publications

Rapid online learning and robust recall in a neuromorphic olfactory circuit

Rapid online learning and robust recall in a neuromorphic olfactory circuit

Evaluation of doped and undoped poly (o‐anisidine) as sensing materials for a sensor array for volatile organic compounds

A Spike Time-Dependent Online Learning Algorithm Derived From Biological Olfaction

Contact Info

Product

Resources

About