Show simple item record

dc.contributor.authorJackson, Scott Michaelen_US
dc.date.accessioned2014-07-26T08:00:18Z
dc.date.available2014-07-26T08:00:18Z
dc.date.issued2014-07-25en_US
dc.identifier.othervt_gsexam:3498en_US
dc.identifier.urihttp://hdl.handle.net/10919/49679
dc.description.abstractModern parallel computing techniques are subject to poor scalability. Their performance tends to suffer diminishing returns and even losses with increasing parallelism. Some methods of intelligent computing, such as neural networks and genetic algorithms, lend themselves well to massively parallel systems but come with other drawbacks that can limit their usefulness such as the requirement of a training phase and/or sensitivity to randomness. This thesis investigates the feasibility of a novel method of intelligent parallel computing by implementing a true multiple instruction stream, single data stream (MISD) computing system that is theoretically nearly perfectly scalable. Computational dreaming (CD) is inspired by the structure and dreaming process of the human brain. It examines previously observed input data during a 'dream phase' and is able to develop and select a simplified model to use during the day phase of computation. Using mazes as an example problem space, a CD simulator is developed and successfully used to demonstrate the viability and robustness of CD. Experiments that focused on CD viability resulted in the CD system solving 15% of mazes (ranging from small and simple to large and complex) compared with 2.2% solved by random model selection. Results also showed that approximately 50% of successful solutions generated match up with those that would be generated by algorithms such as depth first search and Dijkstra's algorithm. Experiments focusing on robustness performed repeated trials with identical parameters. Results demonstrated that CD is capable of achieving this result consistently, solving over 32% of mazes across 10 trials compared to only 3.6% solved by random model selection. A significant finding is that CD does not get stuck on local minima, always converging on a solution model. Thus, CD has the potential to enable significant contributions to computing by potentially finding elegant solutions to, for example, NP-hard or previously intractable problems.en_US
dc.format.mediumETDen_US
dc.publisherVirginia Techen_US
dc.rightsThis Item is protected by copyright and/or related rights. Some uses of this Item may be deemed fair and permitted by law even without permission from the rights holder(s), or the rights holder(s) may have licensed the work for use under certain conditions. For other uses you need to obtain permission from the rights holder(s).en_US
dc.subjectParallel computingen_US
dc.subjectcomputational dreamingen_US
dc.subjectMISDen_US
dc.subjectbio-inspired computer architectureen_US
dc.titleBuilding Maze Solutions with Computational Dreamingen_US
dc.typeThesisen_US
dc.contributor.departmentElectrical and Computer Engineeringen_US
dc.description.degreeMaster of Scienceen_US
thesis.degree.nameMaster of Scienceen_US
thesis.degree.levelmastersen_US
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen_US
thesis.degree.disciplineComputer Engineeringen_US
dc.contributor.committeechairPaul, JoAnn Maryen_US
dc.contributor.committeememberSilva, Luiz A.en_US
dc.contributor.committeememberWang, Wen-Lien_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record