Nengo and low-power AI hardware for robust, embedded neurorobotics
T DeWolf, P Jaworski, C Eliasmith - Frontiers in Neurorobotics, 2020 - frontiersin.org
In this paper we demonstrate how the Nengo neural modeling and simulation libraries
enable users to quickly develop robotic perception and action neural networks for simulation …
enable users to quickly develop robotic perception and action neural networks for simulation …
Learning to select actions with spiking neurons in the basal ganglia
We expand our existing spiking neuron model of decision making in the cortex and basal
ganglia to include local learning on the synaptic connections between the cortex and …
ganglia to include local learning on the synaptic connections between the cortex and …
Dynamical systems in spiking neuromorphic hardware
AR Voelker - 2019 - uwspace.uwaterloo.ca
Dynamical systems are universal computers. They can perceive stimuli, remember, learn
from feedback, plan sequences of actions, and coordinate complex behavioural responses …
from feedback, plan sequences of actions, and coordinate complex behavioural responses …
Methods and systems for artificial cognition
CD Eliasmith, TC Stewart, FX Choo… - US Patent …, 2018 - Google Patents
Methods, systems and apparatus that provide for perceptual, cognitive, and motor behaviors
in an integrated system implemented using neural architectures. Components of the system …
in an integrated system implemented using neural architectures. Components of the system …
Spaun 2.0: Extending the world's largest functional brain model
FX Choo - 2018 - uwspace.uwaterloo.ca
Building large-scale brain models is one method used by theoretical neuroscientists to
understand the way the human brain functions. Researchers typically use either a bottom-up …
understand the way the human brain functions. Researchers typically use either a bottom-up …
Third generation neural nets and their applications in multi-modal deep learning: a survey
I El Sayad, M Pannu, J Gourde… - Proceedings of the Future …, 2023 - Springer
Deep learning has demonstrated remarkable success in a variety of fields in the past
decade and experienced remarkable developments. Despite improved performance, the …
decade and experienced remarkable developments. Despite improved performance, the …
A scalable spiking amygdala model that explains fear conditioning, extinction, renewal and generalization
P Duggins, C Eliasmith - European Journal of Neuroscience, 2024 - Wiley Online Library
The amygdala (AMY) is widely implicated in fear learning and fear behaviour, but it remains
unclear how the many biological components present within AMY interact to achieve these …
unclear how the many biological components present within AMY interact to achieve these …
Learning spiking neural network models of drosophila olfaction
We present research in the modeling of neurons within Drosophila (fruit fly) olfaction. We
describe the process from data collection, to model creation, and spike generation. Our …
describe the process from data collection, to model creation, and spike generation. Our …
Biologically inspired methods in speech recognition and synthesis: closing the loop
T Bekolay - 2016 - uwspace.uwaterloo.ca
Current state-of-the-art approaches to computational speech recognition and synthesis are
based on statistical analyses of extremely large data sets. It is currently unknown how these …
based on statistical analyses of extremely large data sets. It is currently unknown how these …
A neural model of the motor control system
T DeWolf - 2015 - uwspace.uwaterloo.ca
In this thesis I present the Recurrent Error-driven Adaptive Control Hierarchy (REACH); a
large-scale spiking neuron model of the motor cortices and cerebellum of the motor control …
large-scale spiking neuron model of the motor cortices and cerebellum of the motor control …