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 17 of 17 for “"Machine Learning Inference"”.
-
Rethinking Serverless for Machine Learning Inference
In the era of artificial intelligence and machine learning, AI/ML inference tasks have become exceedingly popular. However, executing these workloads on dedicated hardware may not be feasible for many users due to high maintenance costs, varying load patterns, and time to production. Furthermore, …
-
Continuous Learning for Lightweight Machine Learning Inference at the Edge
… network has been increasing exponentially. Machine Learning (ML) models, particularly Deep Neural Networks (DNNs), have the ability to process this data with remarkable accuracy. However, state-of-the-art ML models require substantial computational resources that edge devices typically lack, …
-
A Full System Co-Simulation Platform for Evaluating Edge Machine Learning Inference Using Compute-in-Memory
… co-simulation platform for evaluating embedded machine learning (ML) inference using compute-in-memory (CIM). CIM architectures aim to reduce data movement overhead by performing matrix operations in memory, but end-to-end benefits depend on system-level integration costs that are difficult to …
-
Scalable Embedded Tiny Machine Learning (SETML): A General Framework for Embedded Distributed Inference
The growth of machine learning applications has increased the necessity of lightweight, energyefficient solutions for resource-constrained devices such as the STM32C011F6 microcontroller. However, such devices struggle with supporting larger models even after miniaturization techniques such as …
-
Heterogeneous Hardware Support for Apiary
… for many typical compute-intensive tasks such as machine learning inference.
-
Using Machine Learning for Description and Inference of Cyber Threats, Vulnerabilities, and Mitigations
Machine learning and natural language processing (NLP) can help describe and make inferences on the vast amount of text data in cybersecurity. We use a graph database named BRON, which contains data from publicly available threat and vulnerability sources, for machine learning inference. Applying …
-
Mitigating Compute Congestion for Low Latency Datacenter RPCs
… recent datacenter workloads, such as interactive machine learning inference, high-frequency algorithm trading, cloud gaming, and interactive AR/VR applications impose stringent latency requirements. These applications heavily rely on low-latency RPCs as an essential building block, often executed …
-
Converting PyTorch Models to StreamIt Pipelines
… models, there have been efforts to optimize machine learning inference to support a large volume of queries. Currently, the two main ways to do this are running optimized kernels for computing the forward inference pass and distributing computation across multiple GPUs or different cores in a …
-
Enabling Efficient ML Inference in SigmaOS with Model-Aware Scheduling
Machine learning inference in multi-tenant cloud environments leads to significant challenges when it comes to minimizing latency and resource contention, especially as models grow in size and complexity. This thesis addresses the cold start overhead and scheduling inefficiencies of multi-tenant ML …
-
Flexible Energy-Aware Image and Transformer Processors for Edge Computing
Machine learning inference on edge devices for image and language processing has become increasingly common in recent years, but faces challenges associated with high memory and computation requirements, coupled with limited energy resources. This work applies different quantization schemes and …
-
Portable acquisition and interpretation of EEG for neonatal healthcare applications
… unit for on-board data processing and machine learning inference, is proposed. Novel signal processing and machine learning algorithms to support EEG data interpretation are optimised for use in resource-constrained applications and platforms. To date, minimal consideration is given to …
-
Acceleration of combustion computation fluid dynamics simulations through machine learning
… for chemical reactions with cost-effective machine learning inference. Moreover, the proposed framework offered a practical and scalable method for combustion CFD simulations. The trained DeepONet models are integrated into an open-source CFD framework, OpenFOAM, using LibTorch, replacing …
-
Delocalized Photonic Deep Learning on the Internet's Edge
Machine learning has become ubiquitous in our daily lives, providing unprecedented improvements in image recognition, autonomous driving and conversational AI. To enable this improvement the size of machine learning models has grown exponentially, requiring new hardware that scales accordingly. …
-
Digital Fibers: Materials, Processing, and Information
… to drug discovery and from communications to machine learning. While the capabilities of computing platforms have progressed dramatically, one can argue that materials have not been tailored or designed to capture the spectra of digital capabilities out there. In this thesis, I seek to …
-
MLPerf PowerPack: Defining MLPerf Inference Benchmark's Power Profile
… and limiting factor for the utility of machine learning applications, with each iteration consuming significantly more energy than the last. Understanding the distribution of energy consumption across different system components is crucial for enhancing the efficiency of systems that …
-
On the Distribution of Genetic Variation in Ecological Communities
… variables with community-scale genetic data in a machine learning framework to make predictions about the distribution of genetic variation across the landscape. First, I will present a modelling approach that involves merging Hubbell's neutral theory with neutral population genetic theory to …
-
Distributed Intelligence for Multi-Agent Systems in Search and Rescue
Unfavorable environmental and (or) human displacement may engender the need for Search and Rescue (SAR). Challenges such as inaccessibility, large search areas, and heavy reliance on available responder count, limited equipment and training makes SAR a challenging problem. Additionally, SAR …