Biologically Plausible Illusionary Contrast Perception with Spiking Neural Networks

Cohen-Duwek, Hadar; Tsur, Elishai Ezra

doi:10.1109/icip46576.2022.9897264

Cited by 3 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This framework is anchored in three foundational principles: representation, transformation, and dynamics, which serve as essential building blocks for the development of neuromorphic models [10]. NEF has been used to design neural circuits for applications ranging from robotic control [18] to visual processing [19] and perception [20,21]. Furthermore, the NEF has been effectively implemented in a plethora of prominent digital neuromorphic hardware architectures such as TrueNorth [22], Loihi [23], NeuroGrid [8], and SpiNNaker [24].…”

Section: Neural Engineering Framework (Nef)mentioning

confidence: 99%

Continuous adaptive nonlinear model predictive control using spiking neural networks and real-time learning

Halaly,

Tsur

2024

Neuromorph. Comput. Eng.

View full text Add to dashboard Cite

Model Predictive Control (MPC) is a prominent control paradigm providing accurate state prediction and subsequent control actions for intricate dynamical systems with applications ranging from autonomous driving to star tracking. However, there is an apparent discrepancy between the model’s mathematical description and its behavior in real-world conditions, affecting its performance in real-time. In this work, we propose a novel neuromorphic spiking neural network for continuous adaptive non-linear MPC. By using real-time learning, our design significantly reduces dynamic error and augments model accuracy, while simultaneously addressing unforeseen situations. We evaluated our framework using real-world scenarios in autonomous driving, implemented in a physics-driven simulation. We tested our design with various vehicles (from a Tesla Model 3 to an Ambulance) experiencing malfunctioning and swift steering scenarios. We demonstrate significant improvements in dynamic error rate compared with traditional MPC implementation with up to 89.87% median prediction error reduction with 5 spiking neurons and up to 96.95% with 5000 neurons. Our results may pave the way for novel applications in real-time control and stimulate further studies in the adaptive control realm with spiking neural networks.

show abstract

Section: Neural Engineering Framework (Nef)mentioning

confidence: 99%

Continuous adaptive nonlinear model predictive control using spiking neural networks and real-time learning

Halaly,

Tsur

2024

Neuromorph. Comput. Eng.

View full text Add to dashboard Cite

show abstract

“…NEF provides mathematical constructs that enable encoding, decoding, and transformation of numerical values using spiking neurons, facilitating the implementation of functional large-scale SNNs (Eliasmith and Anderson, 2003). NEF has been used in the design of various neuromorphic systems spanning robotics control (DeWolf et al, 2020) and visual processing (Tsur and Rivlin-Etzion, 2020) to perception (Cohen Duwek and Ezra Tsur, 2021;Cohen-Duwek et al, 2022). Additionally, the framework has been demonstrated on prominent digital neuromorphic hardware architectures, including TrueNorth (Fischl et al, 2018), the Loihi (Lin et al, 2018), the NeuroGrid (Boahen, 2017), and the SpiNNaker (Mundy et al, 2015), as well as deployed on dedicated analog circuitry (Hazan and Ezra Tsur, 2022).…”

Section: Introductionmentioning

confidence: 99%

Autonomous driving controllers with neuromorphic spiking neural networks

Halaly

Tsur

2023

Front. Neurorobot.

View full text Add to dashboard Cite

Autonomous driving is one of the hallmarks of artificial intelligence. Neuromorphic (brain-inspired) control is posed to significantly contribute to autonomous behavior by leveraging spiking neural networks-based energy-efficient computational frameworks. In this work, we have explored neuromorphic implementations of four prominent controllers for autonomous driving: pure-pursuit, Stanley, PID, and MPC, using a physics-aware simulation framework. We extensively evaluated these models with various intrinsic parameters and compared their performance with conventional CPU-based implementations. While being neural approximations, we show that neuromorphic models can perform competitively with their conventional counterparts. We provide guidelines for building neuromorphic architectures for control and describe the importance of their underlying tuning parameters and neuronal resources. Our results show that most models would converge to their optimal performances with merely 100–1,000 neurons. They also highlight the importance of hybrid conventional and neuromorphic designs, as was suggested here with the MPC controller. This study also highlights the limitations of neuromorphic implementations, particularly at higher (> 15 m/s) speeds where they tend to degrade faster than in conventional designs.

show abstract

“…It brings forth a theory for a neuromorphic encoding, decoding, and transformation of mathematical constructs with spiking neurons, allowing the implementation of functional large-scale spiking neural networks (SNNs) [9]. NEF was used to design a broad spectrum of neuromorphic systems ranging from robotic control [10] and visual processing [11] to perception [12]. It serves as the foundation of Nengo, a Python-based 'neural compiler', which translates high-level functional descriptions to low-level neural models [13].…”

Section: Introductionmentioning

confidence: 99%

LiDAR-driven spiking neural network for collision avoidance in autonomous driving

Shalumov¹,

Halaly²,

Tsur³

2021

Bioinspir. Biomim.

View full text Add to dashboard Cite

Facilitated by advances in real-time sensing, low and high-level control, and machine learning, autonomous vehicles draw ever-increasing attention from many branches of knowledge. Neuromorphic (brain-inspired) implementation of robotic control has been shown to outperform conventional control paradigms in terms of energy efficiency, robustness to perturbations, and adaptation to varying conditions. Here we propose LiDAR-driven neuromorphic control of both vehicle's speed and steering. We evaluated and compared neuromorphic PID control and online learning for autonomous vehicle control in static and dynamic environments, finally suggesting proportional learning as a preferred control scheme. We employed biologically plausible basal-ganglia and thalamus neural models for steering and collision-avoidance, finally extending them to support a null controller and a target-reaching optimization, significantly increasing performance.

show abstract

Biologically Plausible Illusionary Contrast Perception with Spiking Neural Networks

Cited by 3 publications

References 10 publications

Continuous adaptive nonlinear model predictive control using spiking neural networks and real-time learning

Continuous adaptive nonlinear model predictive control using spiking neural networks and real-time learning

Autonomous driving controllers with neuromorphic spiking neural networks

LiDAR-driven spiking neural network for collision avoidance in autonomous driving

Contact Info

Product

Resources

About