AdaGrad Gradient Descent Method for AI Image Management

Fong, Cher-Min; Yang, Peng; Hung, Chao-Kai; Lu, Wenlong; Chang, Chien-Wei

doi:10.1109/icce-taiwan49838.2020.9258085

Cited by 9 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The choice of the model optimizer holds significant importance, as it aims to minimize the loss function and bring it closer to the global minimum. 36 Out of the several available optimizers, three model optimizers including the stochastic gradient descent (SGD) optimizer, 37 adaptive moment estimation (Adam) optimizer, 38 and adaptive gradient (AdaGrad) optimizer 39 were selected. On the other hand, the learning rate is also an important hyperparameter that directly affects the training speed and model loss.…”

Section: Optimizers and Learning Ratementioning

confidence: 99%

Noninvasive Assessment of hiPSC Differentiation toward Cardiomyocytes Using Pretrained Convolutional Neural Networks and the Channel Pruning Algorithm

Duan,

He,

Lan

et al. 2024

ACS Biomater. Sci. Eng.

View full text Add to dashboard Cite

Human induced pluripotent stem cell (hiPSC)-derived cardiomyocytes (hiPSC-CMs) offer versatile applications in tissue engineering and drug screening. To facilitate the monitoring of hiPSC cardiac differentiation, a noninvasive approach using convolutional neural networks (CNNs) was explored. HiPSCs were differentiated into cardiomyocytes and analyzed using the quantitative real-time polymerase chain reaction (qRT-PCR). The bright-field images of the cells at different time points were captured to create the dataset. Six pretrained models (AlexNet, GoogleNet, ResNet 18, ResNet 50, DenseNet 121, VGG 19-BN) were employed to identify different stages in differentiation. VGG 19-BN outperformed the other five CNNs and exhibited remarkable performance with 99.2% accuracy, recall, precision, and F1 score and 99.8% specificity. The pruning process was then applied to the optimal model, resulting in a significant reduction of model parameters while maintaining high accuracy. Finally, an automation application using the pruned VGG 19-BN model was developed, facilitating users in assessing the cell status during the myocardial differentiation of hiPSCs.

show abstract

Section: Optimizers and Learning Ratementioning

confidence: 99%

Noninvasive Assessment of hiPSC Differentiation toward Cardiomyocytes Using Pretrained Convolutional Neural Networks and the Channel Pruning Algorithm

Duan,

He,

Lan

et al. 2024

ACS Biomater. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…As a result, the learning rate often becomes infinitesimally small before convergence. It was shown that AdaGrad can have fewer generalisation errors compared to the Adam optimiser [ 66 ].…”

Section: Trainingmentioning

confidence: 99%

Applications of Neural Networks in Biomedical Data Analysis

et al. 2022

View full text Add to dashboard Cite

Neural networks for deep-learning applications, also called artificial neural networks, are important tools in science and industry. While their widespread use was limited because of inadequate hardware in the past, their popularity increased dramatically starting in the early 2000s when it became possible to train increasingly large and complex networks. Today, deep learning is widely used in biomedicine from image analysis to diagnostics. This also includes special topics, such as forensics. In this review, we discuss the latest networks and how they work, with a focus on the analysis of biomedical data, particularly biomarkers in bioimage data. We provide a summary on numerous technical aspects, such as activation functions and frameworks. We also present a data analysis of publications about neural networks to provide a quantitative insight into the use of network types and the number of journals per year to determine the usage in different scientific fields.

show abstract

“…The evaluation is achieved in three main steps,  Load the data  Train both models for WN18 and FB15K  Evaluate both models. For evaluation, we used two different optimization techniques such as Adam optimizer [31] and AdaGrad optimizer [32]. These are the methods used to change the attributes such as weights and learning rate to reduce the losses of the neural network.…”

Section: Fine Tuning Of Parameters Valuesmentioning

confidence: 99%

“…Adaptive Gradient [32] Algorithm is an algorithm used for gradient-based optimization. It is used to perform smaller updates.…”

Section: Adagrad Optimizermentioning

confidence: 99%

See 1 more Smart Citation

Knowledge Graph Embedding for Link Prediction Models

Rehman¹,

Saeed²,

Minallah³

et al. 2022

Preprint

View full text Add to dashboard Cite

For disciplines like biological science, security, and the medical field, link prediction is a popular research area. To demonstrate the link prediction many methods have been proposed. Some of them that have been demonstrated through this review paper are TransE, Complex, DistMult, and DensE models. Each model defines link prediction with different perceptions. We argue that the practical performance potential of these methods, having similar parameter values, using the fine-tuning technique to evaluate their reliability and reproducibility of results. We describe those methods and experiments; provide theoretical proofs and experimental examples, demonstrating how current link prediction methods work in such settings. We use the standard evaluation metrics for testing the model's ability.

show abstract

AdaGrad Gradient Descent Method for AI Image Management

Cited by 9 publications

References 7 publications

Noninvasive Assessment of hiPSC Differentiation toward Cardiomyocytes Using Pretrained Convolutional Neural Networks and the Channel Pruning Algorithm

Noninvasive Assessment of hiPSC Differentiation toward Cardiomyocytes Using Pretrained Convolutional Neural Networks and the Channel Pruning Algorithm

Applications of Neural Networks in Biomedical Data Analysis

Knowledge Graph Embedding for Link Prediction Models

Contact Info

Product

Resources

About