Browsing Dissertations & Theses by Title
Now showing items 354-373 of 596
-
Learning Partially Observable Markov Decision Processes Using Abstract Actions
(Computer Science & Engineering, 2014-03-10)Transfer learning and Abstraction are among the new and most interesting research topics in AI and address the use of learned knowledge to improve learning performance in subsequent tasks. While there has been significant ... -
LEARNING PERCEPTION TO ACTION MAPPING FOR FUNCTIONAL IMITATION
(2016-12-09)Imitation leaning is the learning of advanced behavior whereby an agent acquires a skill by observing another's behavior while performing the same skill. The main objective of imitation learning is to make robots usable ... -
Learning Representations Using Reinforcement Learning
(2019-05-09)The framework of reinforcement learning is a powerful suite of algorithms that can learn generalized solutions to complex decision making problems. However, the applications of reinforcement learning algorithms to traditional ... -
LEARNING ROBOT MANIPULATION TASKS VIA OBSERVATION
(2019-12-06)The coexistence of humans and robots has been the aspiration of many scientific endeavors in the past century. Most anthropomorphic or industrial robots are highly articulated and complex machines, which are designed to ... -
Learning State And Action Space Hierarchies For Reinforcement Learning Using Action-Dependent Partitioning
(Computer Science & Engineering, 2007-08-23)Autonomous systems are often dicult to program. Reinforcement learning (RL) is an attractive alternative, as it allows the agent to learn behavior on the basis of sparse, delayed reward signals provided only when the ... -
LEARNING TO GENERATE INDIVIDUAL DATA SEQUENCE FROM POPULATION STATISTICS USING DYNAMIC BAYESIAN NETWORKS
(2018-05-11)Data collection rose exponentially with the dawn of the 21st Century, However the most important data to humans, individual health data, is difficult to get approved for public research, as medical history is very sensitive ... -
LEARNING TOPOLOGY PRESERVING EMBEDDINGS FOR SPEEDING UP NEAREST NEIGHBOR RETRIEVAL
(2022-05-06)Given a database of objects and a query object, it’s possible to gather a number of the closest neighbors to the query object. This operation is important to a number of diverse fields such as computer vision, content- based ... -
LEARNING TRANSFERABLE META-POLICIES FOR HIERARCHICAL TASK DECOMPOSITION AND PLANNING COMPOSITION
(2019-12-16)In real world scenarios where situated agents are faced with dynamic, high-dimensional, partially observable environments with action and reward uncertainty, the traditional states space Reinforcement Learning (RL) becomes ... -
Learning Video Preferences Using Visual Features And Closed Captions
(Computer Science & Engineering, 2008-04-22)Viewers of video now have more choices than ever. As the number of choices increases, the task of searching through these choices to locate video of interest is becoming more difficult. Current methods for learning a ... -
Lilac: Architecture For Anonymous Light Weight Communication
(Computer Science & Engineering, 2013-10-23)We present lilac; a circuit based low latency anonymous light weight instant messaging communication system. This browser based chat platform provides anonymity in context with unlinkability and unobservability for the ... -
LILAC: THE SECOND GENERATION LIGHTWEIGHT LOW-LATENCY ANONYMOUS CHAT.
(2016-08-15)Instant messaging is one of the most used modes of communication and there are many instant messaging systems available online. Studies from the Electronic Frontier Foundation show that there are only a few instant messengers ... -
Limitations Of IEEE 802.15.4 Based Wireless Mesh Networks For Wireless Localization
(Computer Science & Engineering, 2008-04-22)It is highly desirable to create rapidly and inexpensively deployable mesh networks in certain scenarios. Consider the case of a large storage warehouse; workers are constantly moving in the area and not only do they need ... -
LINCHPIN: A YAML TEMPLATE BASED CROSS CLOUD RESOURCE PROVISIONING TOOL
(2016-12-09)A cloud application developed, will have a specific requirement of particular cloud resources and software stack to be deployed to make it run. Resource templates enable the environment design and deployment required for ... -
LINK PREDICTION BASED FACE CLUSTERING USING VARIATIONAL ATTENTIONAL GRAPH AUTOENCODER
(2020-12-01)In this work, we address the problem of clustering faces according to their individual identities present inherently in the dataset.The current clustering frameworks are either based on some heuristic method or require ... -
Linking Entity Profiles
(Computer Science & Engineering, 2014-09-17)Entity linking allows one to have collections of data from multiple sources as a global dataset and then query those data. Entity linking allows us to do knowledge discovery on this global dataset which might result in the ... -
Liquid: A Detection Resistant Covert Timing Channel Based On Ipd Shaping
(Computer Science & Engineering, 2009-09-16)Covert timing channels provide a way to surreptitiously leak information from an entity in a higher-security level to an entity in a lower level. The difficulty of detecting or eliminating such channels makes them a desirable ... -
LOCALIZATION AND CONTROL OF DISTRIBUTED MOBILE ROBOTS WITH THE MICROSOFT KINECT AND STARL
(2016-05-11)With the increasing availability of mobile robotic platforms, interest in swarm robotics has been growing rapidly. The coordinated effort of many robots has the potential to perform a myriad of useful and possibly dangerous ... -
Location Privacy In Sensor Networks Against A Global Eavesdropper
(Computer Science & Engineering, 2008-09-17)While many protocols for sensor network security provide con dentiality for the content of messages, contextual information usually remains exposed. Such contextual information can be exploited by an adversary to derive ... -
LOW-DOSE CT IMAGE DENOISING USING DEEP LEARNING METHODS
(2021-05-07)Low-dose computed tomography (LDCT) has raised highly attention since the counterpart, full-dose computed tomography (FDCT), brings potential ionizing radiation influence to patients. However, LDCT still suffers from several ... -
LUNG CANCER SUBTYPE CLASSIFICATION FROM WHOLE SLIDE HISTOPATHOLOGICAL IMAGES
(2015-12-16)Lung Cancer is one of the most serious diseases causing death for human be- ings. The progression of the disease and response to treatment di ers widely among patients. Thus it is very important to classify the type of ...