All Outputs (4)

Integrating spiking neural networks and deep learning algorithms on the neurorobotics platform (2022)
Presentation / Conference
Stentiford, R., Knowles, T. C., Feldoto, B., Ergene, D., Morin, F. O., & Pearson, M. J. (2022, July). Integrating spiking neural networks and deep learning algorithms on the neurorobotics platform. Paper presented at Living Machines 2022, Case Western Reserve University, Cleveland, Ohio, United States

We present a neurorobotic model that can associate self motion (odometry) with vision to correct for drift in a spiking neural network model of head direction based closely on known rodent neurophys-iology. We use a deep predictive coding network to... Read More about Integrating spiking neural networks and deep learning algorithms on the neurorobotics platform.

A spiking neural network model of rodent head direction calibrated with landmark free learning (2022)
Journal Article
Stentiford, R., Knowles, T. C., & Pearson, M. J. (2022). A spiking neural network model of rodent head direction calibrated with landmark free learning. Frontiers in Neurorobotics, 16, -. https://doi.org/10.3389/fnbot.2022.867019

Maintaining a stable estimate of head direction requires both self-motion (idiothetic) information and environmental (allothetic) anchoring. In unfamiliar or dark environments idiothetic drive can maintain a rough estimate of heading but is subject t... Read More about A spiking neural network model of rodent head direction calibrated with landmark free learning.

Multimodal Representation Learning for Place Recognition Using Deep Hebbian Predictive Coding (2021)
Journal Article
Pearson, M. J., Dora, S., Struckmeier, O., Knowles, T. C., Mitchinson, B., Tiwari, K., …Pennartz, C. M. (2021). Multimodal Representation Learning for Place Recognition Using Deep Hebbian Predictive Coding. Frontiers in Robotics and AI, 8, Article 732023. https://doi.org/10.3389/frobt.2021.732023

Recognising familiar places is a competence required in many engineering applications that interact with the real world such as robot navigation. Combining information from different sensory sources promotes robustness and accuracy of place recogniti... Read More about Multimodal Representation Learning for Place Recognition Using Deep Hebbian Predictive Coding.

WhiskEye: A biomimetic model of multisensory spatial memory based on sensory reconstruction (2021)
Conference Proceeding
Knowles, T. C., Stentiford, R., & Pearson, M. J. (2021). WhiskEye: A biomimetic model of multisensory spatial memory based on sensory reconstruction. In TAROS 2021: Towards Autonomous Robotic Systems (408-418). https://doi.org/10.1007/978-3-030-89177-0_43

We present WhiskEye, a visual tactile robot supporting a neurorobotic investigation of spatial memory as a multisensory reconstructive process. This article outlines the motivation for building WhiskEye; the technical details of the physical robot, a... Read More about WhiskEye: A biomimetic model of multisensory spatial memory based on sensory reconstruction.