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 953 for “"differentiable"”.
-
Differentiable Functions
The primary purpose of this thesis is to carefully develop and prove some of the fundamental, classical theorems of the differential calculus for functions of two real variables.
-
DIFFERENTIABLE ROBOTICS: COMPOSITIONAL DEEP LEARNING WITH DIFFERENTIABLE ALGORITHM NETWORKS
… how is it trained? This thesis introduces the Differentiable Algorithm Network (DAN), a compositional architecture for designing robot learning systems. The DAN is composed of neural network modules, each encoding an algorithm and associated models; and it is trained end-to-end from data. The …
-
Directly Differentiable Arcs
Abstract Not Provided
-
Differentiable Subdivision Surface Fitting
In this paper we present a powerful differentiable surface fitting technique to derive a compact surface representation for a given dense point cloud or mesh, with application in the domains of graphics and CAD/CAM. We have chosen the Loop subdivision surface, which in the limit yields the smooth …
-
EMPIRICAL LIKELIHOOD AND DIFFERENTIABLE FUNCTIONALS
… results subject to non-linear but Hadamard differentiable statistical functional constraints. In this purpose, a study of differentiable functional with respect to hazard functions is done. We also generalize our results to two sample problems. Stochastic process and martingale theories will …
-
Continuous Deformation of Differentiable Planes
… . . . . . . . . . . . . . . . . . . . . . . 41 3 Differentiable Planes 42 3.1 Differentiable Projective Planes . . . . . . . . . . . . . . . . . . . . . . . . 42 3.2 Differentiable Generalized Planes . . . . . . . . . . . . . . . . . . . . . . . 44 3.3 Regularity and the Characteristic Map . . . . …
-
Differentiable Boundary Value Problem Solver
This thesis proposes a differentiable architecture for solving boundary value problems. That framework is then verified on several problems, including problems related to autonomous vehicle control. It is then shown that the proposed architecture can have greatly reduced convergence times by two …
-
Generative Modeling with Differentiable Dynamics
Deep Learning has focused around building differentiable models for a variety of data modalities, but there are still some types of data that deep neural networks struggle to handle natively. In particular, data that come from high-dimensional distributions, time-stamped data that are sampled at …
-
Structural foundations for differentiable programming
… It focuses on the foundational aspects of differentiable programming in a simply typed functional setting. Although most of the category theory used can be boiled down to a more elementary presentation, its influence was certainly key in obtaining the results presented in this dissertation. …
-
Lie Algebroids over Differentiable Stacks
We develop a theory of Lie algebroids over differentiable stacks that extends the standard theory of Lie algebroids over manifolds. In particular we show that Lie algebroids satisfy descent for submersions, define the category of Lie algebroids over a differentiable stack, construct a cohomology …
-
Differentiable and Robust Optimization Algorithms
Imposing appropriate structure or constraints onto optimization problems is often the key to deriving guarantees or improving generalization of performance aspects like generalization or interpretability. The main contribution of this dissertation is developing algorithms that can leverage …
-
Static analysis of differentiable programs
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms
-
Differentiable engulfing and coverings of manifolds
… theorems for topological, piecewise linear, and differentiable manifolds. Differentiable engulfing so far was reduced to piecewise linear engulfing using the J. H. C. Whitehead triangulation of a differentiable manifold and J. R. Munkres' theory of obstructions to the smoothing of …
-
Gateaux Differentiable Points of Simple Type
… defined on a separable Banach space is Gateaux differentiable on a dense G^ subset of the space E [Mazur]. Suppose we are given a sequence (xn) that Is dense in E. Can we always find a Gateaux differentiable point x such that x = z^=^anxn.for some sequence (an) with infinitely many non-zero …
-
Machine Learning with Differentiable Physics Priors
Differentiable physics priors enable gradient-based learning systems to adhere to physical dynamics. By making physics simulations differentiable, we can backpropagate through the physical consequences of actions. This pipeline allows agents to quickly learn to achieve desired effects in the …
-
Model Uncertainty-Aware Differentiable Architecture Search
We present a Model Uncertainty-aware Differentiable ARchiTecture Search (μDARTS) that optimizes neural networks to achieve high accuracy and low uncertainty simultaneously. We introduce concrete dropout within DARTS cells and include a Monte-Carlo regularizer within the training loss to optimize …
-
Differentiable rendering for synthetic aperture radar imagery
… Consequently, there is increasing interest in differentiable rendering, which allows explicitly modeling geometric priors and constraints into an optimization pipeline. Existing efforts in differentiable rendering have focused on imagery from electro-optical sensors, particularly conventional …
-
Differentiable manifolds modelled on locally convex spaces
We construct differentiable manifolds modelled on locally convex spaces using Yamamuro ' s theory of Γ-differentiation [81], [ 82] , manifolds which we term as Γ-manifolds . Then corresponding to the strong notion of BΓ-differentiability in Yamamuro ' s theory [82] we obtain the subclass of …
-
Boosting 3D Reconstruction with Differentiable Imaging Systems
… light systems. First, we present novel differentiable reformulations of rendering pipelines and apply them in unsupervised, single-view 3D object reconstruction. Compared to previous methods, our novel designs demonstrate more accurate shape and texture recovery, as well as enable new …
-
Differentiable Hebbian Consolidation for Continual Lifelong Learning
… novel edge cases. In this thesis, we propose a Differentiable Hebbian Consolidation model which replaces the traditional softmax layer with a Differentiable Hebbian Plasticity (DHP) Softmax that adds a fast learning plastic component to the fixed (slowly changing) parameters of the softmax …
Page 1 of 48