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 39 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, …
-
Architectural Support for Accelerating Machine Learning Inference
Machine learning has become ubiquitous over recent years, prompting many studies of architectures for accelerating these algorithms. At the same time, algorithms themselves are rapidly evolving, which means that any accelerators designed have to be efficient not just at the algorithms used today, …
-
LOCALITY DRIVEN OPTIMIZATION FOR RESOURCE-EFFICIENT MACHINE LEARNING INFERENCE
Machine learning (ML) inference spans platforms from high-performance servers to energy-constrained edge devices, each with distinct compute, memory, and energy constraints. Layered optimizations often miss the dynamic, cross-layer locality critical for efficient execution. This thesis develops …
-
Accelerating Electron Diffraction Analysis with Machine Learning Inference on FPGAs
Reflection High-Energy Electron Diffraction (RHEED) is used to study the crystal structure and growth of thin films in material science. The RHEED systems available today take several minutes to analyze the crystal’s structure from an image captured during the crystal's growth. This thesis captures …
-
RESOURCE-AWARE OPTIMIZATION TECHNIQUES FOR MACHINE LEARNING INFERENCE ON HETEROGENEOUS EMBEDDED SYSTEMS
… accelerators for energy-efficient DNN inference,(ii) the integration of formal properties in the systematic employment of approximate computing concepts, and (iii) resource management techniques on heterogeneous embedded systems.In summary, this dissertation provides a comprehensive …
-
FPGA-Accelerated Machine Learning Inference for Real-Time RHEED Analysis Towards Closed-Loop PLD
Real-time machine learning inference at high frame rates is challenging when target latencies fall in the millisecond range and host-side processing introduces transfer overhead. This thesis presents an FPGA-accelerated inference framework that performs end-to-end image analysis directly on a frame …
-
Neural Compression Inference Accelerator: a Cost and Energy-Effective Alternative to Conventional Machine Learning Inference Methods
Recent developments in machine learning and artificial intelligence have sparked an influx of workloads that require specialized computer hardware for cloud services. The hardware running machine learning models predominantly consists of graphics processing units (GPUs) and tensor processing units …
-
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 …
-
Optimization Techniques for Machine Learning Inference and Near Memory Image Processing in Hardware for Highly Constrained IoT Edge Nodes
… demand for fast, optimized, and energy-efficient machine learning inference engines as well as image processing in IoT edge applications. In this work, we address three challenging research problems and devise efficient solutions. Our investigation involved comprehensive exploration and analysis, …
-
EdgeEngine : a thermal-aware optimization framework for edge inference
… edge platforms enable the efficient execution of machine learning inference applications. These applications often have a critical constraint (such as meeting a deadline) and an optimization goal (such as minimizing energy consumption). To navigate this space, existing optimization frameworks …
-
Building and Accelerating a Declarative Platform for Machine Learning Model Serving
… technical advances in multiple areas including machine learning, databases and distributed systems. This work focuses on providing better big-data platforms for AI applications. One core challenge here is to map various machine learning and domain-specific algorithms onto the big-data platform. …
-
Essays on FinTech and Machine Learning in Finance
… treatment effect heterogeneity using generic machine learning inference to provide additional support of the trust channel and better understand the borrowers' heterogeneous responses to the Wells Fargo scandal. I exploit a generic machine learning inference approach proposed by Chernozhukov …
-
Optimizing Distributed Workloads with Infrastructure-managed Communication and Deployment
… tune, especially with new workloads like machine learning inference workflows and new infrastructure options like spot instances.</p><p>In this dissertation, I argue that decoupling the implementation of communication primitives and the control of deployment strategies from distributed …
-
ACCELERATION OF SPARSE MATRIX MULTIPLICATION USING BIT-SERIAL ARITHMETIC
Machine Learning inference requires the multiplication of large, sparse matrices. We argue that direct spatial implementation of these fixed matrices minimizes the work per- formed in the computation, and allows for significant reduction in latency and power through constant propagation and logic …
-
Benchmarking TenSEAL’s Homomorphic Encryption Through Predicting Encrypted RNA Sequencing Data
… understanding and improve diagnostics through machine learning models; however, adopting third-party cloud technologies increases the risks of data breaches and noncompliance with regulations such as the Health Insurance Portability and Accountability Act (HIPAA). To address these concerns, …
-
PAMBA: Partition-aware and Multi-SLO Batching for Serverless Inference on Heterogeneous Clouds
… offers elasticity and fine-grained billing for machine learning inference, but efficiently supporting large models under diverse latency service-level objectives (SLOs) remains challenging. In particular, existing approaches face a wide cost–performance gap between CPU and GPU execution, while …
-
Extending Randomized Smoothing to New Application Domains
Despite advances in recent years, machine learning models remain biased and susceptible to adversarial examples, which can drastically alter model outputs with minor input perturbations. Such adversarial examples and biases show that deployment in high-stakes domains requires guaranteed …
-
Progressive intelligence for low-power devices
… devices. Artificial intelligence, in particular machine learning, is one of these advancements which is progressing at an unprecedented rate. However, it is also becoming incredibly resource intensive to operate. Progressive intelligence is a solution to this issue, which approaches the machine …
-
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 …
Page 1 of 2