Theses and Dissertations at Montana State University (MSU)

Permanent URI for this collectionhttps://scholarworks.montana.edu/handle/1/733

Browse

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Using semi-supervised learning for predicting metamorphic relations
    (Montana State University - Bozeman, College of Engineering, 2018) Hardin, Bonnie Elizabeth; Chairperson, Graduate Committee: Upulee Kanewala
    Software testing is difficult to automate, especially in programs which face the oracle problem, where an oracle does not exist, or is too hard to develop. Metamorphic testing is a solution to this problem. Metamorphic testing uses metamorphic relations to determine if tests pass or fail. A large amount of time is needed for a domain expert to determine which metamorphic relations can be used to test a given program. Metamorphic relation prediction removes this need for such an expert. We propose a method using semi-supervised learning algorithms to detect which metamorphic relations are applicable to a given code base. Semi-supervised learning is useful in this problem domain as most programs do not have pre-defined metamorphic relations. These programs are considered unlabeled data in a semi-supervised algorithm. We compare two semi-supervised models with a supervised model, and show that the addition of unlabeled data improves the classification accuracy of the metamorphic relation prediction model.
  • Thumbnail Image
    Item
    Efficient machine learning using partitioned restricted Boltzmann machines
    (Montana State University - Bozeman, College of Engineering, 2016) Tosun, Hasari; Chairperson, Graduate Committee: John Sheppard
    Restricted Boltzmann Machines (RBM) are energy-based models that are used as generative learning models as well as crucial components of Deep Belief Networks (DBN). The most successful training method to date for RBMs is Contrastive Divergence. However, Contrastive Divergence is inefficient when the number of features is very high and the mixing rate of the Gibbs chain is slow. We develop a new training method that partitions a single RBM into multiple overlapping atomic RBMs. Each partition (RBM) is trained on a section of the input vector. Because it is partitioned into smaller RBMs, all available data can be used for training, and individual RBMs can be trained in parallel. Moreover, as the number of dimensions increases, the number of partitions can be increased to reduce runtime computational resource requirements significantly. All other recently developed methods for training RBMs suffer from some serious disadvantage under bounded computational resources; one is forced to either use a subsample of the whole data, run fewer iterations (early stop criterion), or both. Our Partitioned-RBM method provides an innovative scheme to overcome this shortcoming. By analyzing the role of spatial locality in Deep Belief Networks (DBN), we show that spatially local information becomes diffused as the network becomes deeper. We demonstrate that deep learning based on partitioning of Restricted Boltzmann Machines (RBMs) is capable of retaining spatially local information. As a result, in addition to computational improvement, reconstruction and classification accuracy of the model is also improved using our Partitioned-RBM training method.
  • Thumbnail Image
    Item
    Route planning using an emergent hierarchical architecture
    (Montana State University - Bozeman, College of Engineering, 1993) Izurieta, Clemente Ignacio
    A cognitive map is a representation of an environment that consists of both nodes and connections. How this hierarchical structure might emerge from a computational standpoint is the focus of this research. The system builds a cognitive map by traversing routes in an environment. A hierarchical structure emerges when a certain place has been visited often enough to justify its coming to be representative of an entire region. Places are considered to be connected to one another when there is a traversable route that directly links them. Each time the route is traversed, the cognitive relationship between the two places strengthens. If a place is visited often enough, it will come to symbolize an entire region. Once a region is symbolized, all other places in the region are inhibited, allowing each region to be only symbolized by one place. This process can continue indefinitely, leading to a hierarchy with more and more levels. We explore some of the properties of such a hierarchical model including how it develops and how it affects the quality of a planned route.
Copyright (c) 2002-2022, LYRASIS. All rights reserved.