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 “"Computational graph"”.
-
Computational graph construction of adjoint sensitivities for low-thrust trajectory optimization and desensitized optimal control
… dependencies are indicated on a separate computational graph. The performance index is viewed as the output of an evaluation procedure dependent on its inputs. This allows unfolding the chain rule for differentiation in order to design efficient algorithms for trajectory optimization. The …
-
INCREMENTAL COMPUTATION OF TAYLOR SERIES AND SYSTEM JACOBIAN IN DAE SOLVING USING AUTOMATIC DIFFERENTIATION
… are based on topological ordering of a DAE's computational graph and then partitioning the topologically sorted nodes using structural information obtained from the DAE. Solving a DAE by Taylor series is carried out in stages. From one stage to another, partitions of the computational graph …
-
Efficient Jacobian Determination by Structure-Revealing Automatic Differentiation
… methods, to exploit the structure of the computational graph of the nonlinear system.This allows for the efficient determination of the Jacobian matrix using AD software. We will illustrate the promise of this approach with computational experiments.
-
Workload-Aware Performance Prediction and Data Movement for Data-Intensive Computing
… access patterns, data-sharing relationships, and computational graph properties are largely determined by descriptors known to the application before execution. However, general-purpose runtimes treat this structure as opaque, and the resulting gap between workload behavior and runtime decisions …
-
Towards explaining blackbox models using genetic network programming : a thesis presented in partial fulfilment of the requirements for the degree of Master of Information Science in Computer Science at Massey University, Albany, New Zealand
… model and subsequently transforming it into a computational graph, equivalent to a Genetic Network Program (GNP). Furthermore, we present a methodology for refining and reducing the size of the GNP solution. Lastly, we also test if we could utilize the black box system as a guide to the fitness …
-
Model Detection Based upon Amino Acid Properties
… structure prediction, phylogenetic analyses, and computational drug development. Currently discriminative methods for homology detection, which are not readily interpretable, are substantially more powerful than their more interpretable counterparts, particularly when sequence identity is very …
-
Interpretability of Feed Forward Neural Network from Activation Perspective
… the robustness of models by decomposing the computational graph of neural network using the proposed framework. In particular, it shows that the unsecured data can be categorized into Lipschitz vulnerability and float vulnerability according to the source of instability. Based on the insights …
-
Exploring Multi-Level Parallelism For Graph-Based Applications Via Algorithm And System Co-Design
Graph processing is at the heart of many modern applications where graphs are used as the basic data structure to represent the entities of interest and the relationships between them. Improving the performance of graph-based applications, especially using parallelism techniques, has drawn …
-
Novel Biomarkers within Extracellular Vesicles for the Identification of Traumatic Brain Injury
… approach with biostatistical analysis and computational Graph Neural Network (GNN)-based modeling to discover a panel of potential novel biomarkers for the detection and severity of TBI. Lastly, we confirmed the dynamic release of mtDNA and its fragments in EVs from neurons using an …
-
Deep learning algorithms and architectures for natural language processing
… exactly and very efficiently within any modern computational graph framework. We demonstrate the efficiency of the proposed algorithm in a variety of both NLP and computer vision tasks. In the latter case we explore a variety of external knowledge sources depending on the learning task at hand. …
-
On numerical methods in quantum spin systems
… to the quantum many body problem. I introduce Computational Graph States (CGS), a new class of variational wave functions based on the dataflow programming paradigm. The use of computational graphs makes composing new wave functions easy due to its modular structure. Automatic differentiation …
-
Deep Learning Approaches for Accelerated MRI Reconstruction
… and internally for DF, PG-DL leads to a deep computational graph that consumes considerable GPU memory during training. Consequently it is challenging to apply PG-DL with several acquisition types, include high-resolution, 3D/4D, and non-Cartesian MRI. Furthermore, for any DL-based approach, …
-
Συνελικτικά vευρωνικά δίκτυα σε υπολογιστικές διατάξεις τεχνολογίας IMC (In-Memory Computing)
… (CNNs) have led to a significant rise in computational and energy demands, particularly in edge systems with strict resource constraints. The efficient acceleration of the inference process in such environments requires architectures that drastically reduce the cost of accessing and …