Large-scale learning with AdaGrad on Spark

Hadgu, Asmelash Teka; Nigam, Aastha; Diaz-Aviles, Ernesto

doi:10.1109/bigdata.2015.7364091

Cited by 46 publications

(16 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[31] showed that existing CNNs might be difficult to handle the image regression, and unsatisfied results were also The optimization algorithm utilized in the CIC is Adaptive Moment Estimation (Adam) [35] optimizer which is essentially Root Mean Square Prop (RMSProp) [36] with momentum factor. The Adam integrates the advantages of Adaptive Gradient (AdaGrad) [37] and RMSProp, and spends lower computational cost. Furthermore, it performs well for most nonconvex optimization, large data sets, and high-dimensional space.…”

Section: Image-based Reconstruction Of the Heat Transfer Problemmentioning

confidence: 99%

Image-based reconstruction for a 3D-PFHS heat transfer problem by ReConNN

Liu

Wang

Deng

2019

International Journal of Heat and Mass Transfer

View full text Add to dashboard Cite

The heat transfer performance of Plate Fin Heat Sink (PFHS) has been investigated experimentally and extensively. Commonly, the objective function of the PFHS design is based on the responses of simulations. Compared with existing studies, the purpose of this study is to transfer from analysis-based model to image-based one for heat sink designs. Compared with the popular objective function based on maximum, mean, variance values etc., more information should be involved in image-based and thus a more objective model should be constructed. It means that the sequential optimization should be based on images instead of responses and more reasonable solutions should be obtained. Therefore, an image-based reconstruction model of a heat transfer process for a 3D-PFHS is established. Unlike image recognition, such procedure cannot be implemented by existing recognition algorithms (e.g. Convolutional Neural Network) directly. Therefore, a Reconstructive Neural Network (ReConNN), integrated supervised learning and unsupervised learning techniques, is suggested and improved to achieve higher accuracy. According to the experimental results, the heat transfer process can be observed more detailed and clearly, and the reconstructed results are meaningful for the further optimizations. Nomenclature --variableL length of the heat sink r second moment estimation

show abstract

Section: Image-based Reconstruction Of the Heat Transfer Problemmentioning

confidence: 99%

Image-based reconstruction for a 3D-PFHS heat transfer problem by ReConNN

Liu

Wang

Deng

2019

International Journal of Heat and Mass Transfer

View full text Add to dashboard Cite

show abstract

“…The model with the least reconstruction error is selected to obtain sensor features. In order to minimize the reconstruction error, ADAGRAD is used as the optimization algorithm (Dean et al 2012;Hadgu, Nigam & Diaz-Aviles 2015). The architecture finalized using the cross-validation procedure is presented in Table 1.…”

Section: Denoising Autoencoder Architecture Developmentmentioning

confidence: 99%

Application of autoencoders in cyber-empathic design

2018

View full text Add to dashboard Cite

A critical task in product design is mapping information from the consumer space to the design space. This process is largely dependent on the designer to identify and relate psychological and consumer level factors to engineered product attributes. In this way, current methodologies lack provision to test a designer's cognitive reasoning and may introduce bias through the mapping process. Prior work on Cyber-Empathic Design (CED) supports this mapping by relating user-product interaction data from embedded sensors to psychological constructs. To understand consumer perceptions, a network of psychological constructs is developed using Structural Equation Modeling for parameter estimation and hypothesis testing, making the framework falsifiable in nature. The focus of this technical brief is toward automating CED through unsupervised deep learning to extract features from raw data. Additionally, Partial Least Square Structural Equation Modeling is used with extracted sensor features as inputs. To demonstrate the effectiveness of the approach a case study involving sensor-integrated shoes compares three models -a survey-only model (no sensor data), the existing CED approach with manually extracted sensor features, and the proposed deep learning based CED approach. The deep learning based approach results in improved model fit.

show abstract

“…The network is then trained using a gradient based optimization algorithm. There have been many gradient-based algorithms employed in machine learning including stochastic gradient descent [33][34][35], stochastic gradient descent with Nesterov Momentum [33][34][35][36], ADAGRAD [34,35,37], and ADAM [34,35,38]. Based on empirical findings, ADAGRAD and ADAM are widely used in practice because of their speed and accuracy [13,17,18,31], and because of this, ADA-GRAD has been implemented in this work.…”

Section: Proposed Architecturementioning

confidence: 99%

“…The feature-learning layer acts as an Transactions of the ASME input to a fully connected network, where for both models two hidden layers are used with 2048 hidden units in each layer. The output layer is modeled as a softmax layer [16,18,23,29,42,43] and the cross-entropy loss function [16,18,23,29,42,43] is minimized using the ADAGRAD [34,35,37] optimization algorithm with a learning rate of 0.005. These hyper-parameters were obtained using the training procedure shown in Fig.…”

Section: Accuracymentioning

confidence: 99%

Application of Feature-Learning Methods Toward Product Usage Context Identification and Comfort Prediction

Ghosh

Olewnik

Lewis

2017

Journal of Computing and Information Science in Engineering

View full text Add to dashboard Cite

Usage context is considered a critical driving factor for customers' product choices. In addition, physical use of a product (i.e., user-product interaction) dictates a number of customer perceptions (e.g., level of comfort). In the emerging internet of things (IoT), this work hypothesizes that it is possible to understand product usage and level of comfort while it is “in-use” by capturing the user-product interaction data. Mining this data to understand both the usage context and the comfort of the user adds new capabilities to product design. There has been tremendous progress in the field of data analytics, but the application in product design is still nascent. In this work, application of feature-learning methods for the identification of product usage context and level of comfort is demonstrated, where usage context is limited to the activity of the user. A novel generic architecture using foundations in convolutional neural network (CNN) is developed and applied to a walking activity classification using smartphone accelerometer data. Results are compared with feature-based machine learning algorithms (neural network and support vector machines (SVM)) and demonstrate the benefits of using the feature-learning methods over the feature-based machine-learning algorithms. To demonstrate the generic nature of the architecture, an application toward comfort level prediction is presented using force sensor data from a sensor-integrated shoe.

show abstract

Large-scale learning with AdaGrad on Spark

Cited by 46 publications

References 2 publications

Image-based reconstruction for a 3D-PFHS heat transfer problem by ReConNN

Image-based reconstruction for a 3D-PFHS heat transfer problem by ReConNN

Application of autoencoders in cyber-empathic design

Application of Feature-Learning Methods Toward Product Usage Context Identification and Comfort Prediction

Contact Info

Product

Resources

About