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 11 of 11 for “"Invertible Neural Networks"”.
-
Accelerated Design of Structural Metamaterials with Invertible Neural Networks
… this capability through the novel usage of invertible neural networks (INN). We exploit an INN architecture that can be trained to perform forward prediction over a set of high-fidelity samples, and automatically learns the reverse mapping with guaranteed invertibility. We first apply this …
-
Applications of Invertible Neural Networks: From Outlier Detection to Solving Inverse Problems
… mapping can still limit their performance. Invertible Neural Networks (INNs) can address these shortcomings, thanks to their unique ability to maintain invertibility between input and output paradigms while estimating complex data distributions. This thesis investigates the application of …
-
Solving Forward and Inverse Problems for Seismic Imaging using Invertible Neural Networks
… and propose a novel approach based on Invertible Neural Networks. This type of neural network is designed to learn bijective mappings between the input and target distributions and hence they present a potential solution to solve forward and inverse problems jointly. In this thesis, we …
-
The Effect of Speaking Rate on Vowel Variability Based on the Uncontrolled Manifold Approach and Flow-Based Invertible Neural Network Modeling
… directly from speech data using the flow-based invertible neural networks framework. The application of the UCM analysis and FlowINN modeling method is discussed, particularly focusing on how the “good” part of variability in speech can be useful rather than being disregarded as noise.
-
Design Space Extrapolation and Inverse Design using Machine Learning
… frequency samples using specialized recurrent neural networks. (2) We propose Transposed Convolutional Networks to model spatial correlations in the design space. The design space comprises of all the geometrical and material parameters characterizing the response. The convolutional networks …
-
Towards Reliably Handling Inputs Not From the Training Distribution
… the input image contains a building. Bayesian neural networks are promising candidates to make deep classifiers better at detecting such unexpected inputs. The first part of the thesis presents a new variant of Bayesian neural networks that provides computational savings while performing well …
-
Expanding the capabilities of normalizing flows in deep generative models and variational inference
… Normalizing flows, sometimes also referred to as invertible neural networks, are one class of models providing this: they are formulated to be bijective and differentiable, and thus produce a tractable density model via the change-of-variable formula. Beyond just deep generative modelling and …
-
High-speed Channel Analysis and Design using Polynomial Chaos Theory and Machine Learning
… DC gain of CTLE. This approach is based on the invertible neural networks. Main advantage of this network is the possibility to provide multiple solutions for cases where the answer to the inverse problem is not unique. Numerical examples are provided to evaluate efficiency and accuracy of the …
-
A Hybrid Conceptual Design Methodology for Supersonic Aircraft using Morphing Technology
… design and inverse design through the use of Invertible Neural Networks (INN) is proposed to deal with the design challenges of morphing technology. With the addition of multiple morphing degrees of freedom as control variables in a trajectory optimization design approach, the trade-off …
-
Video Prediction with Invertible Linear Embeddings
Using recently popularized invertible neural network We predict future video frames from complex dynamic scenes. Our invertible linear embedding (ILE) demonstrates successful learning, prediction and latent state inference. In contrast to other approaches, ILE does not use any explicit …