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 154 for “"deep learning systems"”.
-
Adaptive on-device deep learning systems
"Mobile systems such as smartphones, drones, and augmented-reality headsets are revolutionizing our lives. On-device deep learning is regarded as the key enabling technology for realizing their full potential. This is because communication with cloud adds additional latency or cost, or the …
-
Error Resilient and Adaptive Deep Learning Systems
As deep learning systems become integral to a wide array of applications, including autonomous systems, healthcare, and finance, their complexity and deployment in hardware bring new challenges. In particular, the susceptibility of deep learning systems to hardware-induced errors, manufacturing …
-
Certifiably trustworthy deep learning systems at scale
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-03-01 without embargo terms
-
COLLABORATIVE DISTRIBUTED DEEP LEARNING SYSTEMS ON THE EDGES
Deep learning has revolutionized a wide range of fields. In spite of its success, most deep learning systems are proposed in the cloud, where data are processed in a centralized manner with abundant compute and network resources. This raises a problem when deep learning is deployed on the edge …
-
Characterising Algorithm Debt in Machine and Deep Learning Systems
The integration of Machine and Deep Learning (ML/DL) into modern software systems has transformed application domains such as finance, healthcare, and autonomous technologies. However, the complexity of ML/DL algorithms, the unique development pipeline, and the stochastic training process introduce …
-
Tensor signal modeling for high-dimensional deep learning systems
… applications of signal processing and machine learning. Towards that end, in the first part of this dissertation we initially consider the fundamental concepts of modeling and processing high-dimensional data, namely tensors and their decompositions. These higher-order processing workhorses, …
-
Efficient Architecture and Data Manipulation for Deep Learning Systems
Thesis (Ph.D.)--Michigan State University. Electrical Engineering - Doctor of Philosophy, 2024
-
Deep learning systems and methodologies for Spitz melanocytic tumour analysis
… de metodologías como el multiple instance learning, active learning, self-training y federated learning para mitigar los desafíos inherentes al campo de la patología digital, manteniendo un enfoque práctico hacia la integración clínica. Este trabajo, posicionado en la intersección entre la …
-
Deep Learning Systems with Linguistic Interpretability in Manufacturing Image Classifications
Machine learning has received considerable attention in recent decades in data-driven modelling systems and methods. Machine Learning focuses on applied maths and computing algorithms for creating ‘computational machines’ that can learn to imitate system behaviours automatically. Unlike traditional …
-
OPTIMIZING PARALLELISM AND COMMUNICATION FOR LARGE-SCALE GENERATIVE DEEP LEARNING SYSTEMS
Since 2014, deep learning has shifted from discriminative to generative models capable of producing text, images, videos, and scientific insights. However, scaling models to hundreds of billions of parameters introduces compute, memory, communication, power, and development walls. This paper …
-
An Empirical Study of Logging Practice in CUDA-based Deep Learning Systems
… extensively explored in conventional software systems, there remains a lack of understanding of how logging is applied in CUDA-based deep learning (DL) systems, despite their growing adoption in practice. In this paper, we conduct an empirical study to examine the characteristics and rationales …
-
Building Secure and Reliable Deep Learning Systems from a Systems Security Perspective
As deep learning (DL) is becoming a key component in many business and safety-critical systems, such as self-driving cars or AI-assisted robotic surgery, adversaries have started placing them on their radar. To understand their potential threats, recent work studied the worst-case behaviors of deep …
-
Towards Trust and Transparency in Deep Learning Systems through Behavior Introspection & Online Competency Prediction
Deep neural networks are naturally “black boxes”, offering little insight into how or why they make decisions. These limitations diminish the adoption likelihood of such systems for important tasks and as trusted teammates. We employ introspective techniques to abstract machine activation patterns …
-
Efficient Design of Neural Network Hardware Accelerator for Enhanced Performance in Deep Learning Systems
… speed while retaining low cost and high learning performance. The main challenge is to design complex machine learning models on hardware with high performance. In this thesis, the aim is to develop the hardware implementation of perceptron within a neural network. Innovative …
-
Reducing the Cost of Test Data Labelling for Deep-Learning Systems: An Empirical Study
Deep learning (DL) systems have achieved remarkable success across various domains, including healthcare, autonomous driving, and facial recognition. However, ensuring the reliability of these systems requires comprehensive testing with accurately labeled datasets, which is a resource-intensive and …
-
IMPROVING INFORMATION EXTRACTION WITH WEIGHTED MULTI-TASK LEARNING
… from unstructured text. Traditional machine learning techniques for information extraction require task-specific training data and manually engineered features, many of which require a pipeline of external sub-systems to extract named entities, etc. On the other hand, deep learning systems do …
-
Incorporating Large Language Models for Spurious Features Testing in Deep Learning System
In the realm of Deep Neural Networks (DNNs), the identification and management of spurious features significantly influence the performance and generalisation of these systems. This thesis delves into the intricate domain of testing deep learning systems, with a specific focus on the identification …
-
Analysis of Data Security Vulnerabilities in Deep Learning
As deep learning systems become more integrated into important application areas, the security of such systems becomes a paramount concern. Specifically, as modern networks require an increasing amount of data on which to train, the security of data that is collected for these models cannot be …
-
Data-Efficient, Context-Aware, and Generalizable Deep Learning for Prostate Cancer Detection from Micro-Ultrasound
Deep learning offers a powerful tool for medical image analysis, but conventional learning algorithms are often poorly matched to the constraints imposed by real-world clinical applications. These challenges are especially evident in prostate cancer diagnosis. Deep learning-enabled prostate cancer …
-
A Double-Edged Sword: The Role of Noise in Trustworthy Deep Learning
Deep learning systems are widely used in everyday technologies such as facial recognition, image analysis, and 3D scene reconstruction. However, these systems often face an important challenge: noise. Noise can come from imperfect data, human labeling errors, or low-quality sensors, and it can …
Page 1 of 8