Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 13 of 13 for “"Generative methods"”.
-
Developing Domain-Specific Generative Methods
Generative AI is a field that is rapidly developing and growing in scale. As research in this area shifts to building on large-scale foundation models and powerful architectures, careful thought has to go into adapting these models to new domains and tasks. The work in this thesis demonstrates …
-
Properties and Generative Methods of Scales and Sets
… why composers favor these collections. The methods that can be used to generate these sets also yield interesting information about the sets themselves. The properties andgenerative methods studied by scholars can be organized within two branches of set theory: chromatic and diatonic. …
-
Generative methods for image synthesis with applications to medical imaging
… for diagnostic and analytical improvements. Generative methods for image synthesis have been an active area of research in recent years. In this thesis, we explore the use of a hybrid model of generative adversarial networks (GANs) and transformer networks for image synthesis. We propose a …
-
Digital making : exploring design with computer controlled fabrication
… of digital modeling (explicit or with generative methods) and computer controlled fabrication machines. A series of explorations and studies are conducted to establish a procedure for the integration of representational techniques and fabrication processes into methods for digital …
-
Exploring the landscape of backdoor attacks on deep neural network models
… We draw on adversarial perturbations and generative methods to develop a framework for executing efficient, yet label-consistent, backdoor attacks. Furthermore, we propose the use of differential privacy as a defence against backdoor attacks. This prevents the model from relying heavily on …
-
Active prototyping : a computational framework for designing while making
… I conclude by proposing action recording and generative methods as two novel additions to existing frameworks for computational design and fabrication that can bring future tool-making strategies into a more creative context.
-
Generative morphologies of architectural organization in matter force field
This thesis investigates generative methods of architectural form finding in matter force fields that produce spatial subdivision and organizational variation. Unlike the style driven contemporary free-form architecture or decorative computational form making processes, this thesis is interested in …
-
Computer assisted application of stochastic structuring techniques in musical composition and control of digital sound synthesis systems
… techniques in musical composition, certain generative methods of forming and controlling data structures can be a powerful aid. This thesis proposes and develops such methods. Techniques of pattern formation are described which have been developed and used in the original compositions of the …
-
Stereo-tectonic choreography: A sculptural [re]surfacing of an enigmatic genius loci
… modelling and drawing serve as a conceptual generative methods to explore architectural space, materiality and form. It is this curiosity developed through my hands and the material that has served as a tooling in uncovering and sourcing intuitive work - the binary rationale of which lies in …
-
Learning for Visual Synthesis and Transformation
… semantic annotations and images. Recently, deep generative learning has greatly promoted the development of visual synthesis. However, the existing generative methods still suffer from several issues, including model interpretation, controllability, stability, efficiency and performance. In this …
-
Adversarial training objectives for generative attacks on text classifiers
… samples. This thesis has focused on refining generative models to produce textual adversarial examples, providing an alternative to the prevalent token-modification attacks that transform document tokens using methods such as word insertion and replacement. Generative approaches, which start …
-
Learning structured representations for perception and control
… hierarchical reinforcement learning, and generative models provides a promising avenue towards building agents that learn to produce goal-directed behavior given sensations. I present models and algorithms that learn from raw observations and will emphasize on minimizing their sample …
-
Interpreting Deep Learning for cell differentiation. Supervised and Unsupervised models viewed through the lens of information and perturbation theory.
… has nurtured the evolution of a variety of new methods to predict and interpret future scenarios. These data centric models can achieve exceptional performances on specific tasks, with their prediction boundaries continuously expanding towards new and more complex challenges. However, the model …