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 68 for “"out-of-distribution"”.
-
Statistical Methods for Out-of-distribution Detection
For a network trained on in-distribution (ID) samples, test samples could be out-of-distribution (OOD) that are drawn from distributions different from that of ID samples. Accordingly, OOD detection aims to identify OOD samples in test phases. The main challenge lies in that a network could provide …
-
Out-of-distribution generalisation in machine learning
… applications in recent years. However, a lot of these success stories stem from evaluating the algorithms on data very similar to that they were trained on. When applied to a new data distribution, machine learning algorithms have been shown to fail. Given the non-stationary and heterogeneous …
-
Towards Out-of-distribution Problem for Reinforcement Learning
… high-quality models require a large amount of data, parameters as well as computation power. This originates from the curse of dimensionality and poor out-of-distribution generalization of current probabilistic models. Current machine learning models requires data points to be independently …
-
Machine Learning for Out of Distribution Database Workloads
… for predicting query latencies. With the rise of cloud first DBMS architectures, it is now possible to collect massive amounts of data on executed queries. This gives a way to improve the DBMS heuristics using models that utilize this execution history. In particular, such models can be …
-
Uncertainty-aware learning from sparse, unlabelled, and out-of-distribution time series
… learning is increasingly popular in the analysis of healthcare time series, as it can support improved diagnostics, personalised monitoring, and effective performance tracking. The ever-increasing availability of datasets from wearable sensors, mobile devices, and continuous monitoring …
-
Regularization, Uncertainty Estimation and Out of Distribution Detection in Convolutional Neural Networks
Classification is an important task in the field of machine learning and when classifiers are trained on images, a variety of problems can surface during inference. 1) Recent trends of using convolutional neural networks (CNNs) for various machine learning tasks has borne many successes and CNNs …
-
Improved Out-of-Distribution Detection Using Segmented Images and Prompt-Only Text Reasoning
The problem of Out-of-Distribution (OOD) detection has been thoroughly researched but continues to underperform in "near-OOD" settings, where OOD data may be very similar or inseparable from in-distribution (ID) data. The problem is that current state-of-the-art OOD detection methods fail to learn …
-
Weisfeiler-Leman graph kernels for the out-of-distribution characterization of graph structured data
This thesis presents a new metric named Graph Distributional Analytics (GDA). This approach uses Weisfeiler-Leman kernels, cosine similarity, and traditional statistical metrics to better characterize graph-structured data. It focuses on enhancing the analysis of graph-structured data and enhancing …
-
Last Layer Retraining of Selectively Sampled Wild Data Improves Performance
… in the wild where the data can lie in domains outside the training distribution. Out-of-distribution (OOD) generalization is difficult because these domains are underrepresented or non-existent in training data. The pursuit of a solution to bridging the performance gap between in-distribution …
-
SAFEGUARDING AI SYSTEMS AGAINST UNEXPECTED INPUTS
… achieved remarkable success across a broad range of applications. However, perturbations such as natural image corruptions or crafted malicious queries, can cause significant performance degradation. This poses severe risks in safety-critical applications, such as autonomous driving and clinical …
-
Adversarial Resilient and Privacy Preserving Deep learning
… the cloud and on edge devices for a wide range of domain-specific applications, ranging from healthcare, cyber-manufacturing, autonomic vehicles, to smart cities and smart planet initiatives. While deep learning creates new opportunities for business, engineering, and scientific discoveries, it …
-
Deep Transfer Learning for Macroscale Defect Detection in Semiconductor Manufacturing
… four axes at Texas Instruments. The major axis of improvement involves real-time machine learning recommendations regarding the presence of macroscale defects. In this work, a model for detecting central defects is described in detail, and a novel approach to overcoming data scarcity through the …
-
Towards Understanding Human-aligned Neural Representation in the Presence of Confounding Variables
Deep Neural Networks (DNNs) find one out of many possible solutions to a given task such as classification. This solution is more likely to pick up on spurious features and low-level statistical patterns in the train data rather than semantic features and highlevel abstractions, resulting in poor …
-
Generative models meet similarity search: efficient, heuristic-free and robust retrieval
The rapid growth of digital data, especially visual and textual contents, brings many challenges to the problem of finding similar data. Exact similarity search, which aims to exhaustively find all relevant items through a linear scan in a dataset, is impractical due to its high computational …
-
Epistemic deep learning : enabling machine learning models to ‘know when they do not know’
… and unreliable predictions when models encounter out-of-distribution data, adversarial perturbations, or naturally fluctuating environments. This thesis, titled Epistemic Deep Learning: Enabling Machine Learning Models to ‘Know When They Do Not Know’, addresses these critical challenges by …
-
Engineering-driven Machine Learning Methods for System Intelligence
… learning methods, and the industrial internet of things (IIoT). The development of sensing technology provides large amounts and various types of data (e.g., profile, image, point cloud, etc.) to describe each stage of a manufacturing process. The machine learning methods have the advantages of …
-
Open-Set Object Based Data Association
… object detectors trained on a specific set of objects, such as the YCB objects, are used to provide input to the data association problem, which limits the scope of the system to environments that it has been trained on. With advancements in foundational models, we can extend this …
-
Utilizing network features to detect erroneous inputs
Neural networks are vulnerable to a wide range of erroneous inputs such as corrupted, out-of-distribution, misclassified, and adversarial examples. Previously, separate solutions have been proposed for each of these faulty data types; however, in this work I show that the collective set of …
Page 1 of 4