An official website of the United States government
Abstract Resource management in engineering design seeks to optimally allocate while maximizing the performance metrics of the final design. Bayesian optimization (BO) is an efficient design framework that judiciously allocates resources through heuristic-based searches, aiming to identify the optimal design region with minimal experiments. Upon recommending a series of experiments or tasks, the framework anticipates their completion to augment its knowledge repository, subsequently guiding its decisions toward the most favorable next steps. However, when confronted with time constraints or other resource challenges, bottlenecks can hinder the traditional BO’s ability to assimilate knowledge and allocate resources with efficiency. In this work, we introduce an asynchronous learning framework designed to utilize idle periods between experiments. This model adeptly allocates resources, capitalizing on lower fidelity experiments to gather comprehensive insights about the target objective function. Such an approach ensures that the system progresses uninhibited by the outcomes of prior experiments, as it provisionally relies on anticipated results as stand-ins for actual outcomes. We initiate our exploration by addressing a basic problem, contrasting the efficacy of asynchronous learning against traditional synchronous multi-fidelity BO. We then employ this method to a practical challenge: optimizing a specific mechanical characteristic of a dual-phase steel.
more »
« less
Efficient End-to-End Asynchronous Time-Series Modeling With Deep Learning to Predict Customer Attrition
Modeling time-series data with asynchronous, multi-cardinal, and uneven patterns presents several unique challenges that may impede convergence of supervised machine learning algorithms, or significantly increase resource requirements, thus rendering modeling efforts infeasible in resource-constrained environments. The authors propose two approaches to multi-class classification of asynchronous time-series data. In the first approach, they create a baseline by reducing the time-series data using a statistical approach and training a model based on gradient boosted trees. In the second approach, they implement a fully convolutional network (FCN) and train it on asynchronous data without any special feature engineering. Evaluation of results shows that FCN performs as well as the gradient boosting based on mean F1-score without computationally complex time-series feature engineering. This work has been applied in the prediction of customer attrition at a large retail automotive finance company.
more »
« less
- Award ID(s):
- 1920182
- PAR ID:
- 10356999
- Date Published:
- Journal Name:
- Handbook of Research on Methodologies and Applications of Supercomputing
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Synchronizing decisions across multiple agents in realistic settings is problematic since it requires agents to wait for other agents to terminate and communicate about termination reliably. Ideally, agents should learn and execute asynchronously instead. Such asynchronous methods also allow temporally extended actions that can take different amounts of time based on the situation and action executed. Unfortunately, current policy gradient methods are not applicable in asynchronous settings, as they assume that agents synchronously reason about action selection at every time step. To allow asynchronous learning and decision-making, we formulate a set of asynchronous multi-agent actor-critic methods that allow agents to directly optimize asynchronous policies in three standard training paradigms: decentralized learning, centralized learning, and centralized training for decentralized execution. Empirical results (in simulation and hardware) in a variety of realistic domains demonstrate the superiority of our approaches in large multi-agent problems and validate the effectiveness of our algorithms for learning high-quality and asynchronous solutions.more » « less
-
Flooding is one of the leading threats of natural disasters to human life and property, especially in densely populated urban areas. Rapid and precise extraction of the flooded areas is key to supporting emergency-response planning and providing damage assessment in both spatial and temporal measurements. Unmanned Aerial Vehicles (UAV) technology has recently been recognized as an efficient photogrammetry data acquisition platform to quickly deliver high-resolution imagery because of its cost-effectiveness, ability to fly at lower altitudes, and ability to enter a hazardous area. Different image classification methods including SVM (Support Vector Machine) have been used for flood extent mapping. In recent years, there has been a significant improvement in remote sensing image classification using Convolutional Neural Networks (CNNs). CNNs have demonstrated excellent performance on various tasks including image classification, feature extraction, and segmentation. CNNs can learn features automatically from large datasets through the organization of multi-layers of neurons and have the ability to implement nonlinear decision functions. This study investigates the potential of CNN approaches to extract flooded areas from UAV imagery. A VGG-based fully convolutional network (FCN-16s) was used in this research. The model was fine-tuned and a k-fold cross-validation was applied to estimate the performance of the model on the new UAV imagery dataset. This approach allowed FCN-16s to be trained on the datasets that contained only one hundred training samples, and resulted in a highly accurate classification. Confusion matrix was calculated to estimate the accuracy of the proposed method. The image segmentation results obtained from FCN-16s were compared from the results obtained from FCN-8s, FCN-32s and SVMs. Experimental results showed that the FCNs could extract flooded areas precisely from UAV images compared to the traditional classifiers such as SVMs. The classification accuracy achieved by FCN-16s, FCN-8s, FCN-32s, and SVM for the water class was 97.52%, 97.8%, 94.20% and 89%, respectively.more » « less
-
Emotions are an integral part of human nature. Emotion awareness is critical to any form of interpersonal communication and collaboration, including these in the software development process. Recently, the SE community starts having growing interests in emotion awareness in software development. While researchers have accomplished many valuable results, most extant research ignores the dynamic nature of emotion. To investigate the emotion dynamics, SE community needs an effective approach to capture and model emotion dynamics rather than focuses on extracting isolated emotion states. In this paper, we proposed such an approach–EmoD. EmoD is able to automatically collect project teams' communication records, identify the emotions and their intensities in them, model the emotion dynamics into time series, and provide efficient data management. We developed a prototype tool that instantiates the EmoD approach by assembling state-of-the-art NLP, SE, and time series techniques. We demonstrate the utility of the tool using the IPython's project data on GitHub and a visualization solution built on EmoD. Thus, we demonstrate that EmoD can provide end-to-end support for various emotion awareness research and practices through automated data collection, modeling, storage, analysis, and presentation.more » « less
-
Abstract The Ice-sheet and Sea-level System Model (ISSM) provides numerical solutions for ice sheet dynamics using finite element and fine mesh adaption. However, considering ISSM is compatible only with central processing units (CPUs), it has limitations in economizing computational time to explore the linkage between climate forcings and ice dynamics. Although several deep learning emulators using graphic processing units (GPUs) have been proposed to accelerate ice sheet modeling, most of them rely on convolutional neural networks (CNNs) designed for regular grids. Since they are not appropriate for the irregular meshes of ISSM, we use a graph convolutional network (GCN) to replicate the adapted mesh structures of the ISSM. When applied to transient simulations of the Pine Island Glacier (PIG), Antarctica, the GCN successfully reproduces ice thickness and velocity with a correlation coefficient of approximately 0.997, outperforming non-graph models, including fully convolutional network (FCN) and multi-layer perceptron (MLP). Compared to the fixed-resolution approach of the FCN, the flexible-resolution structure of the GCN accurately captures detailed ice dynamics in fast-ice regions. By leveraging 60–100 times faster computational time of the GPU-based GCN emulator, we efficiently examine the impacts of basal melting rates on the ice sheet dynamics in the PIG.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.4018/978-1-7998-7156-9.ch016
