Browsing Theses by Supervisor "Orchard, Jeff"
Now showing items 1-7 of 7
-
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 ... -
Spiking Deep Neural Networks: Engineered and Biological Approaches to Object Recognition
(University of Waterloo, 2018-01-08)Modern machine learning models are beginning to rival human performance on some realistic object recognition tasks, but we still lack a full understanding of how the human brain solves this same problem. This thesis combines ...