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 18 of 18 for “"efficient neural networks"”.
-
Robust and efficient neural networks: Algorithms, architectures, and circuits
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms
-
Towards efficient deep neural networks with applications to visual recognition
… on the following two topics: designing energy-efficient neural networks and hashing approach to make deep learning more feasible to real applications; deep convolutional neural networks for visual recognition.
-
Johnson–Lindenstrauss Projections as Architectural Components in Deep Neural Networks
Modern deep neural networks are heavily overparameterized, with learned representations occupying lower-dimensional subspaces than their ambient dimensions suggest. This thesis investigates whether fixed random Johnson-Lindenstrauss (JL) projections can exploit this redundancy by functioning as …
-
Resource-aware and robust image processing for intelligent sensor systems
… IoT edge devices, the research proposes resource-efficient neural networks. The storage demand is reduced by compressing the neural network weights with an adaptive image encoding algorithm, and the computation demand is optimized by mapping the entire network parameters and operations into the …
-
Relationship Between Cognitive Reserve and Rate of Decline in Alzheimer’s Disease: A Population Study
… leisure activity) foster the development of more efficient neural networks and cognitive strategies, enabling individuals to cope more effectively with the pathology of dementia. Using extant data from a population-based study, we examined: (1) the effect of reserve accrued through middle life on …
-
Online Machine Learning for Wireless Communications: Channel Estimation, Receive Processing, and Resource Allocation
… applying ML schemes to wireless communication networks is not straightforward, there are several challenges need to addressed: 1). Training data in communication networks, especially in physical and MAC layer, are extremely limited; 2). The high-dynamic wireless environment and fast changing …
-
Domain wall based magnetic tunnel junction devices for neuromorphic computing
… rely on CMOS technology to simulate neural networks which is inefficient and requires immense power. Neuromorphic computing seeks to alleviate this bottleneck by shifting the computing paradigm from von Neumann architecture to brain-like computing to approach the extreme efficiency …
-
Towards science-guided knowledge distillation for multimodal learning under cross-domain distribution shift
… it into lightweight, domain-specific student networks that respect strict computational limits. Building upon this concept, this work introduces three complementary frameworks designed to handle severe domain mismatches. First, we develop strategies for heterogeneous domain-shift mitigation …
-
Sex and sex-specific factors influence brain health at middle age depending on APOEε4 genotype
… In males, hAPOEε4 genotype reduced both neural progenitor cell density and neurogenesis, which was correlated with increased microglia density. In contrast, in females, hAPOEε4 genotype did not alter neural progenitor cell density, yet increased neurogenesis, indicating sex-specific …
-
Workload Prediction for Efficient Performance Isolation and System Reliability
… allocation policies, in order to achieve efficient and in-time resource isolation among applications. For a multi-tier storage system, high-priority user work is often multiplexed with low-priority background work. This brings the challenge of how to strike a balance between maintaining …
-
Towards Human-Centered AI-Powered Assistants for the Visually Impaired
… understanding. Current state-of-the-art deep neural networks for the two tasks have been shown to achieve superior performance, but requires high computation and memory, making them cost prohibitive for on-device operation. On-device operation is necessary to address privacy concerns related …
-
Advancing Urban Accessibility through AI: Scalable Machine Learning Approaches to Pedestrian Path Network Mapping and Assessment
… transportation system. While automobile road networks have been extensively mapped, mapping the transportation network for the paths that serve pedestrians is inconsistent, incomplete, or missing. This fundamental lack of network information creates gaps in personal travel, accessible …
-
Unsupervised sound separation
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms
-
Efficient machine learning software stack from algorithms to compilation
… continuing challenge. Algorithm design proposes efficient model architectures and learning algorithms, while compilation design optimizes computation graphs and simplifies operations. However, there is still a gap between the demand for efficiency and the current solutions, driven by rapidly …
-
Practical Neural Architecture Search: Efficient Methods and Evaluation
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Efficient Deep Learning for Visual and Textual Data
Efficient hardware, increased computational power, and smart sensors, are powering deep learning, and moving intelligence from the cloud to edge devices (e.g., smartphones, smart cameras, and wearables). However, deep neural networks are computationally expensive and are difficult to deploy on edge …
-
Resource optimization methods for Machine Learning model execution on resource constrained embedded systems
… evolution of embedded intelligence, the logic of neural networks and fields of optimization such as quantization-aware training and post-training pruning. Chapter 3 presents an extensive experimental evaluation of these techniques across various microcontroller architectures, using rigorous power …