Evolutionary vs imitation learning for neuromorphic control at the edge*

Schuman, Catherine D.; Patton, Robert M.; Kulkarni, Shruti; Parsa, Maryam; Stahl, Christopher G.; Haas, Nicholas Quentin; Mitchell, J. Parker; Shay, Snyder,; Nagle, Amelie; Shanafield, Alexandra; Potok, Thomas E.

doi:10.1088/2634-4386/ac45e7

Cited by 10 publications

(9 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our example of a problem with a positive correlation between evaluation time and fitness is a spiking neural network (SNN) learning problem: we aim to learn an SNN controller to drive a simulated vehicle that corresponds to the F1TENTH autonomous racing platform (O'Kelly et al, 2020). 3 The fitness evaluation for the F1TENTH example computes the mean of how far (in units of distance) the car is able to drive, using the simulated SNN as a controller, before crashing across five training tracks (Schuman et al, 2022; Patton et al, 2021). We use the EA to determine the weights, thresholds, and synaptic delays of an SNN with 20 input neurons (for 10 LIDAR inputs that use a spike‐encoding scheme that requires 2 neurons per input), 10 hidden neurons, and 40 output neurons.…”

Section: Methodsmentioning

confidence: 99%

“…The fitness evaluation for the F1TENTH example computes the mean of how far (in units of distance) the car is able to drive, using the simulated SNN as a controller, before crashing across five training tracks (Schuman et al, 2022;Patton et al, 2021). We use the EA to determine the weights, thresholds, and synaptic delays of an SNN with 20 input neurons (for 10 LIDAR inputs that use a spike-encoding scheme that requires 2 neurons per input), 10 hidden neurons, and 40 output neurons.…”

Section: F1tenth: An Autonomous Vehicle Problemmentioning

confidence: 99%

See 1 more Smart Citation

Avoiding excess computation in asynchronous evolutionary algorithms

et al. 2022

Self Cite

View full text Add to dashboard Cite

Asynchronous evolutionary algorithms are becoming increasingly popular as a means of making full use of many processors while solving computationally expensive search and optimization problems. These algorithms excel at keeping large clusters fully utilized, but may sometimes inefficiently sample an excess of fast-evaluating solutions at the expense of higher-quality, slow-evaluating ones. We have previously introduced a steady-state parent selection strategy, SWEET ("Selection whilE Evalu-aTing"), that sometimes selects individuals that are still being evaluated and allows them to reproduce early. We perform a takeover-time analysis that confirms that this strategy gives slow-evaluating individuals that have higher fitnesses an increased ability to multiply in the population. We also find that SWEET appears effective at improving optimization performance on problems in which solution quality is positively correlated with evaluation time. We evaluate our approach on six simulated real-valued optimization problems and three real-world applications: an autonomous vehicle controller problem that involves tuning a spiking neural network and two adversarial EA problems. We further evaluate SWEET versus a basic asynchronous process in a simulated setting. We present evidence that SWEET outperforms basic asynchronous processes in a use-case in which performance is positively correlated with evaluation time, and performs comparably (and often better) than basic asynchronous processes in several use-cases where performance is negatively correlated with evaluation time. That said, in the cases where performance and evaluation time are negatively correlated the variance of outcomes for SWEET is notably high.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: F1tenth: An Autonomous Vehicle Problemmentioning

confidence: 99%

Avoiding excess computation in asynchronous evolutionary algorithms

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…EONS optimizes parameters of the network like number of neurons, number of synapses, connection between neurons and parameters of the neurons and synapses over time. Schuman et al [34] EONS uses the traditional evolutionary approach, it randomly initializes a parent network of a given population size, and then evaluates that network using a fitness score. It uses tournament selection and mutation to produce a child population.…”

Section: Evolutionary Optimizationmentioning

confidence: 99%

Hardware software co-design for leveraging STDP in a memristive neuroprocessor

Chakraborty,

Ameli,

Das

et al. 2024

Neuromorph. Comput. Eng.

View full text Add to dashboard Cite

In neuromorphic computing, different learning mechanisms are being widely adopted to improve the performance of a specific application. Among these techniques, Spike-Timing-Dependent Plasticity (STDP) stands out as one of the most favored. STDP is simply managed by the temporal information of an event, which is biologically inspired. However, most of the prior works on STDP are focused on circuit implementation or software simulation for performance evaluation. Previous works also lack a comparative analysis of the performances of different STDP implementations. This study aims to provide a comprehensive assessment of STDP, centering on the performance across various applications such as classification (static and temporal datasets), control, and reservoir computing. Different applications necessitate distinct STDP configurations to achieve optimal performance with the neuroprocessor. Additionally, this work introduces an Application-Specific Integrated Circuit (ASIC) design of STDP circuitry. The design is based on current-controlled memristive synapse principles and utilizes 65nm CMOS technology from IBM. The detailed presentation includes circuitry specifics, layout, and performance parameters such as energy consumption and design area.

show abstract

“…Then it must be stored as JSON in the format specified by the TENNLab software framework. TENNLab networks have been trained using genetic algorithms [14], [21], [26], deep learning [27], decision trees [23], and they have been hand-designed for various tasks [9], [16], [18]. It is anticipated that in the nearterm, network training will require support from TENNLab software; however, that is not a strict requirement.…”

Section: Trainingmentioning

confidence: 99%