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 20 of 24 for “"discrete representations"”.
-
Compact Discrete Representations for Scalable Similarity Search
… The proposed techniques advocate the use of discrete codes for representing the similarity structure of data in a compact way. In particular, we will discuss how one can learn to map high-dimensional data onto binary codes with a metric learning approach. Then, we will describe a simple …
-
Variation in Speech: Describing continuous phenomena with discrete representations
Radboud Universiteit Nijmegen, 04 december 2009
-
Discrete representations of continuous data using deep learning and clustering
<p>The divide between continuous and discrete data is a fundamental one in computer science and mathematics, as well as related areas such as cognitive science. Historically, most of computing has operated in the discrete domain, but connectionism offers an alternative set of techniques for …
-
Simultaneous determination of relative permeability and capillary pressure from displacement data by simulated annealing.
… are represented by global empirical functions, discrete values, and piece-wise local functions. The simulated annealing method is implemented for non-linear global optimization. Applications to unsteady-state drainage and imbibition, and steady-state core flood tests are presented. Global …
-
Brain-wide cell assembly patterns for memory-guided behaviour
… cognitive domains. How does the brain integrate discrete representations spread across the brain to drive effective behaviour?</p> <p>I trained male mice to approach or avoid a dispenser delivering either rewarding or aversive outcomes contingent on sets of visual and auditory cues. I found that …
-
Bandlimited functions, curved manifolds, and self-adjoint extensions of symmetric operators
… the crucial connection between continuous and discrete representations of information that enables one store continuous signals as discrete, digital data with minimal error. It is this connection that allows communication engineers to realize many of our modern digital technologies including …
-
Design and Evaluation of a Specialized Computer Architecture for Manipulating Binary Decision Diagrams
… and verification applications. Symbolic problem representations make BDDs a feasible data structure for use on many problems that have discrete representations. Efficient implementations of BOD algorithms on general purpose computers has made manipulating large binary decision diagrams possible. …
-
Global normal forms and global properties in function spaces for second order Shubin type operators
… by operators acting on S(Rn) and admitting discrete representations. Finally, we study Cauchy problems on Rn globally in time for second order hyperbolic equations P(x;D)+R(x;D), where P(x;D) is a second or der self-adjoint globally elliptic Shubin pseudodifferential operator and R(x;D) is a …
-
Quality Representation in Multiobjective Programming
… emphasis has been placed on generating quality representations of the nondominated set of multiobjective programming problems. This manuscript presents two methods for generating discrete representations with equidistant points for multiobjective programs with solution sets determined by convex …
-
ADAPTIVE NEURAL NETWORK FOR DISCRETIZATION INVARIANT OPERATOR LEARNING
… with the capacity to process heterogeneous discrete representations of functions as inputs and/or outputs of a learning model. This paper proposes a novel deep learning framework based on integral autoencoders (IAE-Net) for discretization invariant learning. The basic building block of …
-
EFFICIENT SIGNAL SYNTHESIS FOR DATA AUGMENTATION USING GENERATIVE AI
… with either a decoder-only transformer or a discrete diffusion model. The VQ-VAE encodes high-dimensional signals into discrete latent tokens, significantly reducing model complexity while enabling symbolic sequence modeling. These discrete representations are then modeled using …
-
Cognitively-motivated geometric methods of pattern discovery and models of similarity in music
… thesis is concerned with cognitively-motivated representations of musical structure. Three problems are addressed, each related in terms of their focus on music as an object of perception, and in the application of geometrical methods of knowledge representation. The problem of pattern discovery …
-
Domain Playground: Extending Deep Learning Models to Open Domain Boundaries
… them to build a model dynamically in the form of discrete representations. We evaluate the DP framework's domain adaptation capabilities compared to existing approaches and demonstrate compelling performance in domain adaptation tasks. From the domain adaptation evaluation, we have confirmed that …
-
AMoEBA: the adaptive modeling by evolving blocks algorithm
… of the algorithm are its ability to work with discrete data types and its unique geometric representation of the domain. AMoEBA uses genetic programming generated parse trees to define data segregation schemes. These trees also place solver/descriptors in the decomposed regions. Since the …
-
Shape Processing across Lateral Occipital Cortex
… Our later work then assessed neural shape representations across visual cortex, identifying two discrete representations; ‘Shape-profile’ (essentially retinotopic responses) and ‘Shape-complexity’ (responses based upon the complexity of a shape’s contour). The latter dimension captured …
-
Neural Computations Underpinning Anxiety in Health and Disease
… Markov decision process that involves fictive representations of potential future outcomes. Next, I explored the neural representations underpinning these anxiety-like behaviors, aiming to determine whether non-local representations occur during periods of anxious conflict. To do this, I …
-
Hierarchies, search, and generative models in sequential decision-making
… planning, and generative modeling, with discrete latent representations as a technical foundation. Hierarchical learning can shorten the planning horizon in extended tasks. Search-based planning can support reasoning and exploration. Generative models, particularly diffusion models, can …
-
Topological and geometrical considerations for Maxwell's equations on unstructured meshes
A discrete differential form approach to solving Maxwell's equations numerically on unstructured meshes is presented. A differential form representation of Maxwell's equations provides a natural and coordinate-free means of studying these equations and their solutions in the presence of curved …
-
Bridging topology optimisation and discrete structural systems through reconstruction
… Through morphological processes, it produces discrete representations that preserve the topology of the original continuum designs. Numerical investigations demonstrate that, for the cases that involved bending-dominated structures, the displacement response of the discretised systems exhibit …
-
Generalizing sampling theory for time-varying Nyquist rates using self-adjoint extensions of symmetric operators with deficiency indices (1,1) in Hilbert spaces
… studies the equivalence between continuous and discrete representations of information. This equivalence is ubiquitously used in communication engineering and signal processing. For example, it allows engineers to store continuous signals as discrete data on digital media. The classical sampling …
Page 1 of 2