Deep Neural Learning Adaptive Sequential Monte Carlo for Automatic Image and Speech Recognition

Kamsing, Patcharin; Torteeka, Peerapong; Boonpook, Wuttichai; Cao, Chunxiang

doi:10.1155/2020/8866259

Cited by 2 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The emergence of deep learning techniques has completely changed several research fields, such as image and speech recognition [18], video processing [25], natural language processing [54], medical imaging [21], and faul/t diagnosis [45]. In recent years, deep learning has been applied in scientific computing.…”

Section: Introductionmentioning

confidence: 99%

An Adaptive Physics-Informed Neural Network with Two-Stage Learning Strategy to Solve Partial Differential Equations

Shi¹,

Liu²,

null³

et al. 2023

NMTMA

View full text Add to dashboard Cite

Physics-Informed Neural Network (PINN) represents a new approach to solve Partial Differential Equations (PDEs). PINNs aim to solve PDEs by integrating governing equations and the initial/boundary conditions (I/BCs) into a loss function. However, the imbalance of the loss function caused by parameter settings usually makes it difficult for PINNs to converge, e.g. because they fall into local optima. In other words, the presence of balanced PDE loss, initial loss and boundary loss may be critical for the convergence. In addition, existing PINNs are not able to reveal the hidden errors caused by non-convergent boundaries and conduction errors caused by the PDE near the boundaries. Overall, these problems have made PINN-based methods of limited use on practical situations. In this paper, we propose a novel physics-informed neural network, i.e. an adaptive physics-informed neural network with a two-stage training process. Our algorithm adds spatio-temporal coefficient and PDE balance parameter to the loss function, and solve PDEs using a two-stage training process: pre-training and formal training. The pre-training step ensures the convergence of boundary loss, whereas the formal training process completes the solution of PDE by balancing various loss functions. In order to verify the performance of our method, we consider the imbalanced heat conduction and Helmholtz equations often appearing in practical situations. The Klein-Gordon equation, which is widely used to compare performance, reveals that our method is able to reduce the hidden errors. Experimental results confirm that our algorithm can effectively and accurately solve models with unbalanced loss function, hidden errors and conduction errors.

show abstract

Section: Introductionmentioning

confidence: 99%

An Adaptive Physics-Informed Neural Network with Two-Stage Learning Strategy to Solve Partial Differential Equations

Shi¹,

Liu²,

null³

et al. 2023

NMTMA

View full text Add to dashboard Cite

show abstract

“…Excellent results in image analysis are obtained using artificial intelligence (AI), in particular, convolutional neural networks (CNN) [22,23]. Modern deep learning networks [24,25] are used with great success to classify objects (images) and to predict specific values based on an image. It is only necessary to prepare a sufficiently large and representative data set for a given issue.…”

Section: Introductionmentioning

confidence: 99%

Estimating the distance to an object from grayscale stereo images using deep learning

Kulawik¹

2022

J. Appl. Math. Comput. Mech.

View full text Add to dashboard Cite

This article presents an innovative proposal for estimating the distance between an autonomous vehicle and an object in front of it. Such information can be used, for example, to support the process of controlling an autonomous vehicle. The primary source of information in research is monochrome stereo images. The images were made in compliance with the laws of the canonical order. The developed convolutional neural network model was used for the estimation. A proprietary dataset was developed for the experiments. The analysis was based on the phenomenon of disparity in stereo images. As a result of the research, a correctly trained model of the CNN network was obtained in six variants. High accuracy of distance estimation was achieved. This publication describes an original proposal for a hybrid blend of digital image analysis, stereo-vision, and deep learning for engineering applications.

show abstract

Deep Neural Learning Adaptive Sequential Monte Carlo for Automatic Image and Speech Recognition

Cited by 2 publications

References 35 publications

An Adaptive Physics-Informed Neural Network with Two-Stage Learning Strategy to Solve Partial Differential Equations

An Adaptive Physics-Informed Neural Network with Two-Stage Learning Strategy to Solve Partial Differential Equations

Estimating the distance to an object from grayscale stereo images using deep learning

Contact Info

Product

Resources

About