- About
-
The Global ETD Search service is a free service for researchers
to find electronic theses and dissertations. This service is
provided by the
Networked Digital Library of Theses and Dissertations.
Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
Search results
Showing 1 to 2 of 2 (0.033 seconds)Spelling suggestions: "subject:"vertex AI"" "subject:"certex AI""
| 1 |
The Allure of Automated Machine Learning Services : How SMEs and non-expert users can benefit from AutoML frameworksLux Dryselius, Felix January 2023 (has links)
This study investigates how small and medium sized enterprises (SMEs) and other resource-lacking organisations can utilise automated machine learning (AutoML) to lessen the development hurdles associated with machine learning model development. This is achieved by comparing the performance, cost of usage, as well as usability and documentation for machine learning models developed through two AutoML frameworks: Vertex AI on Google Cloud™ and the open-source library AutoGluon, developed by Amazon Web Services. The study also presents a roadmap and a time plan that can be utilised by resource-lacking enterprises to guide the development of machine learning solutions implemented through AutoML frameworks. The results of the study show that AutoML frameworks are easy to use and capable in generating machine learning models. However, performance is not guaranteed and machine learning projects utilising AutoML frameworks still necessitates substantial development effort. Furthermore, the limiting factor in model performance is often training data quality which AutoML frameworks do not address.
|
| 2 |
Analysis Of Fastlane For Digitalization Through Low-Code ML PlatformsRaghavendran, Krishnaraj January 2022 (has links)
Even a professional photographer sometimes uses automatic default settings that come up with the camera to take a photo. One can debate the quality of outcome from manual vs automatic mode. Until and unless we have a professional level of competence in taking a photo, updating our skills/knowledge as per the latest market trends and having enough time to try out different settings manually, it is worthwhile to use Auto-mode. As camera manufacturers, after several iterations of testing, comes up with the list of ideal parameter values, which is embedded as a factory default setting when we choose auto-mode. For non-professional photographers or amateurs recommend using the auto-mode that comes with the camera for not missing the moment. Similarly, in the context of developing machine learning models, until and unless we have the required data-engineering and ML development competence, time to train and test different ML models and tune different hyper parameter settings, it is worth to try out to Automatic Machine learning feature provided out-of-shelf by all the Cloud-based and Cloud-agnostic ML platforms. This thesis deep dives into evaluating possibility of generating automatic machine learning models with no-code/low-code experience provided by GCP, AWS, Azure and Databricks. We have made a comparison between different ML platforms on generating automatic ML model and presenting the results. It also covers the lessons learnt by developing automatic ML models from a sample dataset across all four ML platforms. Later, we have outlined machine learning subject matter expert’s viewpoints about using Automatic Machine learning models. From this research, we found automatic machine learning can come handy for many off-the-shelf analytical use-cases, this can be highly beneficial especially for time-constrained projects, when resource competence or staffing is a bottleneck and even when competent data scientists want a second-opinion or compare AutoML results with the custom ML model built.
|
Page generated in 0.0385 seconds