UWSpace will be migrating to a new version of its software from July 29th to August 1st. UWSpace will be offline for all UW community members during this time.
Browsing Mathematics (Faculty of) by Supervisor "Orchard, Jeff"
Now showing items 1-6 of 6
-
Bidirectional Learning in Recurrent Neural Networks Using Equilibrium Propagation
(University of Waterloo, 2018-09-26)Neurobiologically-plausible learning algorithms for recurrent neural networks that can perform supervised learning are a neglected area of study. Equilibrium propagation is a recent synthesis of several ideas in biological ... -
Biological Plausibility in Modern Hopfield Networks
(University of Waterloo, 2022-12-19)Modern Hopfield Networks (HNs) have the ability to store a large number of target memories (e.g. binary patterns) and then recall a memory in its entirety when prompted by a sub-set or perturbed version of it; in this ... -
Biologically Plausible Neural Learning using Symmetric Predictive Estimators
(University of Waterloo, 2016-08-04)A predictive estimator (PE) is a neural microcircuit hypothesized to explain how the brain processes certain types of information. They participate in a hierarchy, passing predictions to lower layers, which send back ... -
The Computational Advantages of Intrinsic Plasticity in Neural Networks
(University of Waterloo, 2019-10-17)In this work, I study the relationship between a local, intrinsic update mechanism and a synaptic, error-based learning mechanism in ANNs. I present a local intrinsic rule that I developed, dubbed IP, that was inspired by ... -
Decay Makes Supervised Predictive Coding Generative
(University of Waterloo, 2020-08-19)Predictive Coding is a hierarchical model of neural computation that approximates backpropagation using only local computations and local learning rules. An important aspect of Predictive Coding is the presence of feedback ... -
Learning-Free Methods for Goal Conditioned Reinforcement Learning from Images
(University of Waterloo, 2021-04-27)We are interested in training goal-conditioned reinforcement learning agents to reach arbitrary goals specified as images. In order to make our agent fully general, we provide the agent with only images of the environment ...