Browsing Systems Design Engineering by Supervisor "Tripp, Bryan"
Now showing items 1-8 of 8
-
Contour Integration in Artifical Neural Networks
(University of Waterloo, 2022-02-08)Under difficult viewing conditions, the brain's visual system uses a variety of modulatory techniques to supplement its core feedforward signal. One such technique is contour integration, whereby contextual stimuli from ... -
Correlated Noise in Deep Convolutional Neural Networks
(University of Waterloo, 2019-08-28)This thesis explores one of the differences between the visual cortex and deep convolutional neural networks, namely, correlated fluctuations of neuron response strength. First, we describe the similarities and differences ... -
Development of an Integrated Model of Primary Visual Cortex
(University of Waterloo, 2016-02-16)Network-level models of visual processing have potentially important insights for applications such as computer vision and robotics. Primary visual cortex is a key stage of visual processing with involvement in many circuits ... -
Driving Scene Understanding using Spiking Neural Networks
(University of Waterloo, 2022-01-24)One of the applications of AI lies in developing intelligent systems for safe on-road driving, other than building and perfecting self-driving vehicles, and many others. Driving Scene Understanding (DSU) is one such area ... -
An Empirical Model of Area MT: Investigating the Link between Representation Properties and Function
(University of Waterloo, 2018-10-16)The middle temporal area (MT) is one of the visual areas of the primate brain where neurons have highly specialized representations of motion and binocular disparity. Other stimulus features such as contrast, size, and ... -
Robotic Grasping using Demonstration and Deep Learning
(University of Waterloo, 2019-09-11)Robotic grasping is a challenging task that has been approached in a variety of ways. Historically grasping has been approached as a control problem. If the forces between the robotic gripper and the object can be calculated ... -
Studying CNN representations through activation dimensionality reduction and visualization
(University of Waterloo, 2021-10-01)The field of explainable artificial intelligence (XAI) aims to explain the decisions of DNNs. Complete DNN explanations accurately reflect the inner workings of the DNN while interpretable explanations are easy for humans ... -
Task-Parameterized Transformer for Learning Gripper Trajectory from Demonstrations
(University of Waterloo, 2024-02-26)The goal of learning from demonstration or imitation learning is to teach the model to generalize across unseen tasks based on available demonstrations. This ability can be important for the stable performance of a robot ...