Search
Skip to Search Results- 2Abdi Oskouie, Mina
- 2Birkbeck, Neil Aylon Charles
- 2Cai, Zhipeng
- 2Chen, Jiyang
- 2Chowdhury, Md Solimul
- 2Chubak, Pirooz
- 83Machine Learning
- 76Reinforcement Learning
- 42Artificial Intelligence
- 37Machine learning
- 24Natural Language Processing
- 23reinforcement learning
-
Fall 2014
This thesis is concerned with the ultrasonic heart image segmentation problem using parametric active contour model. Most of the existing parametric models consider only either the edge or the regional information. In this thesis, we propose a new parametric active contour model considering both...
-
Uncalibrated Vision-Based Control and Motion Planning of Robotic Arms in Unstructured Environments
DownloadFall 2012
Many robotic systems are required to operate in unstructured environments. This imposes significant challenges on algorithm design. Particularly, motion control and planning algorithms should be robust to noise and outliers, because uncertainties are inevitable. In addition, independence from...
-
Fall 2022
Some real-world deployments of deep reinforcement learning (RL) may require a human-in-the-loop. Whether to ask-for-help, obtain new demonstrations and data, or handle out-of-distribution states, many methods rely on uncertainty estimates from a neural network to determine when to solicit a...
-
Fall 2019
In this thesis, we study merge-and-shrink (M&S), a flexible abstraction technique for generating heuristics for cost optimal planning. We first propose three novel merging strategies for M&S, namely, Undirected Min-Cut (UMC), Maximum Intermediate Abstraction Size Minimizing (MIASM), and Dynamic...
-
Fall 2020
This thesis is offered as a step forward in our understanding of forgetting in artificial neural networks. ANNs are a learning system loosely based on our understanding of the brain and are responsible for recent breakthroughs in artificial intelligence. However, they have been reported to be...
-
Fall 2021
In Activities of Daily Living (ADLs), humans perform thousands of arm and hand object manipulation tasks, such as picking, pouring and drinking a drink. Interpreting such tasks and grasping the underlying concepts of manipulation from vision is straightforward for humans, but difficult for...
-
Fall 2014
The recovery of 3D information from 2D images is a well-studied problem in computer vision, with many competing methods that can achieve highly accurate results. However, relatively little attention has been paid to the problem of 3D reconstruction in underwater environments. When cameras are...
-
Spring 2016
For years, panoramic image stitching has been an interesting problem for re- searchers. Several advances have been made in stitching images that are ac- quired outside of water, but the problem has been poorly explored for under- water images. Image stitching for underwater images can be used in...
-
Fall 2011
A fundamental component of stereo vision is that of epipolar geometry. It shows that the corresponding point of a pixel in one image is restricted to a line in another image. When a refractive surface is introduced, such as in underwater imaging, this constraint no longer holds. Instead, the...
-
Spring 2019
Juan Fernando Hernandez Garcia
Unifying seemingly disparate algorithmic ideas to produce better performing algorithms has been a longstanding goal in reinforcement learning. As a primary example, the TD(λ) algorithm elegantly unifies temporal difference (TD) methods with Monte Carlo methods through the use of eligibility...