Theses and Dissertations from UMD

Permanent URI for this communityhttp://hdl.handle.net/1903/2

New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a give thesis/dissertation in DRUM

More information is available at Theses and Dissertations at University of Maryland Libraries.

Browse

Filters

2013 - 201912020 - 20221

Settings

Subject: search.filters.subject.interpretability

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    ROBUSTNESS AND UNDERSTANDABILITY OF DEEP MODELS
    (2022) Ghiasi, Mohammad Amin; Goldstein, Thomas; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    Deep learning has made a considerable leap in the past few decades, from promising models for solving various problems to becoming state-of-the-art. However, unlike classical machine learning models, it is sometimes difficult to explain why and how deep learning models make decisions. It is also interesting that their performance can drop with small amounts of noise. In short, deep learning models are well-performing, easily corrupted, hard-to-understand models that beat human beings in many tasks. Consequently, improving these deep models requires a deep understanding. While deep learning models usually generalize well on unseen data, adding negligible amounts of noise to their input can flip their decision. This interesting phenomenon is known as "adversarial attacks." In this thesis, we study several defense methods against such adversarial attacks. More specifically, we focus on defense methods that, unlike traditional methods, use less computation or fewer training examples. We also show that despite the improvements in adversarial defenses, even provable certified defenses can be broken. Moreover, we revisit regularization to improve adversarial robustness. Over the past years, many techniques have been developed for understanding and explaining how deep neural networks make a decision. This thesis introduces a new method for studying the building blocks of neural networks' decisions. First, we introduce the Plug-In Inversion, a new method for inverting and visualizing deep neural network architectures, including Vision Transformers. Then we study the features a ViT learns to make a decision. We compare these features when the network trains on labeled data versus when it uses a language model's supervision for training, such as in CLIP. Last, we introduce feature sonification, which borrows feature visualization techniques to study models trained for speech recognition (non-vision) tasks.
  • Thumbnail Image
    Item
    Time and Form: Designing in the Fourth Dimension
    (2013) Petersen, Sasha Nicole; Lamprakos, Michele; Architecture; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    The human vision for the built environment is characterized by contradictory ideals. Society values buildings that are able to resist or at least mask the degradation that occurs over time so that they can continue to serve their intended purposes and yet, society also romanticizes the fragmentary and deeply evocative ruin that has been completely surrendered to the weathering effects of the environment. Would it be possible to design continually functioning buildings that make the natural and human forces of change manifest, thus developing a narrative that represents more honestly our own fundamental relationship with time? This thesis will investigate how architecture can serve as a record of change in our surroundings and extend our temporal awareness beyond the present condition. To this aim, interpretation center that addresses sea level rise will serve as a testing ground.