scholarly journals Transfer learning-based Fashion Image Classification using Hybrid 2D-CNN and ImageNet Neural Network

2021 ◽  
Vol 9 (11) ◽  
pp. 1537-1545
Author(s):  
Sweety Duseja
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Image Classification ◽  
Transfer Learning ◽  
Learning Strategy ◽  
Learning Transfer ◽  
Learning Approach ◽  
Learning Method ◽  
Product Identification ◽  
Classification Product

Abstract: Many algorithms have been developed as a result of recent advances in machine learning to handle a variety of challenges. In recent years, the most popular transfer learning method has allowed researchers and engineers to run experiments with minimal computing and time resources. To tackle the challenges of classification, product identification, product suggestion, and picture-based search, this research proposed a transfer learning strategy for Fashion image classification based on hybrid 2D-CNN pretrained by VGG-16 and AlexNet. Pre-processing, feature extraction, and classification are the three parts of the proposed system's implementation. We used the Fashion MNIST dataset, which consists of 50,000 fashion photos that have been classified. Training and validation datasets have been separated. In comparison to other conventional methodologies, the suggested transfer learning approach has higher training and validation accuracy and reduced loss. Keywords: Machine Learning, Transfer Learning, Convolutional Neural Network, Image Classification, VGG16, AlexNet, 2D CNN.

scholarly journals Implementation of Transfer Learning in the Convolutional Neural Network Algorithm for Identification of Potato Leaf Disease

2021 ◽  
Vol 1 (1) ◽  
Author(s):  
Abdul Jalil Rozaqi ◽  
Muhammad Rudyanto Arief ◽  
Andi Sunyoto
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Transfer Learning ◽  
Method Development ◽  
Classification Model ◽  
Learning Method ◽  
Potato Leaf ◽  
Leaf Disease

Potatoes are a plant that has many benefits for human life. The potato plant has a problem, namely a disease that attacks the leaves. Disease on potato leaves that is often encountered is early blight and late blight. Image processing is a method that can be used to assist farmers in identifying potato leaf disease by utilizing leaf images. Image processing method development has been done a lot, one of which is by using the Convolutional Neural Network (CNN) algorithm. The CNN method is a good image classification algorithm because its layer architecture can extract leaf image features in depth, however, determining a good CNN architectural model requires a lot of data. CNN architecture will become overfitting if it uses less data, where the classification model has high accuracy on training data but the accuracy becomes poor on test data or new data. This research utilizes the Transfer Learning method to avoid an overfit model when the data used is not ideal or too little. Transfer Learning is a method that uses the CNN architecture that has been trained by other data previously which is then used for image classification on the new data. The purpose of this research was to use the Transfer Learning method on CNN architecture to classify potato leaf images in identifying potato leaf disease. This research compares the Transfer Learning method used to find the best method. The results of the experiments in this research indicate that the Transfer Learning VGG-16 method has the best classification performance results, this method produces the highest accuracy value of 95%.

scholarly journals Towards Image Classification with Machine Learning Methodologies for Smartphones

2019 ◽  
Vol 1 (4) ◽  
pp. 1039-1057 ◽  
Author(s):  
Lili Zhu ◽  
Petros Spachos
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Image Classification ◽  
Transfer Learning ◽  
Time Constraints ◽  
Learning Method ◽  
Android Application ◽  
Optimal Model ◽  
Recent Developments ◽  
Learning Architectures

Recent developments in machine learning engendered many algorithms designed to solve diverse problems. More complicated tasks can be solved since numerous features included in much larger datasets are extracted by deep learning architectures. The prevailing transfer learning method in recent years enables researchers and engineers to conduct experiments within limited computing and time constraints. In this paper, we evaluated traditional machine learning, deep learning and transfer learning methodologies to compare their characteristics by training and testing on a butterfly dataset, and determined the optimal model to deploy in an Android application. The application can detect the category of a butterfly by either capturing a real-time picture of a butterfly or choosing one picture from the mobile gallery.

scholarly journals Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping

2020 ◽  
Author(s):  
Joshua C.O KOh ◽  
German Spangenberg ◽  
Surya Kant
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Image Classification ◽  
Transfer Learning ◽  
High Performance ◽  
Plant Phenotyping ◽  
Network Architectures ◽  
Neural Architecture ◽  
Automated Machine Learning ◽  
Minimal Effort

Automated machine learning (AutoML) has been heralded as the next wave in artificial intelligence with its promise to deliver high performance end-to-end machine learning pipelines with minimal effort from the user. AutoML with neural architecture search which searches for the best neural network architectures in deep learning has delivered state-of-the-art performance in computer vision tasks such as image classification and object detection. Using wheat lodging assessment with UAV imagery as an example, we compared the performance of an open-source AutoML framework, AutoKeras in image classification and regression tasks to transfer learning using modern convolutional neural network (CNN) architectures pretrained on the ImageNet dataset. For image classification, transfer learning with Xception and DenseNet-201 achieved best classification accuracy of 93.2%, whereas Autokeras had 92.4% accuracy. For image regression, transfer learning with DenseNet-201 had the best performance (R2=0.8303, RMSE=9.55, MAE=7.03, MAPE=12.54%), followed closely by AutoKeras (R2=0.8273, RMSE=10.65, MAE=8.24, MAPE=13.87%). Interestingly, in both tasks, AutoKeras generated compact CNN models with up to 40-fold faster inference times compared to the pretrained CNNs. The merits and drawbacks of AutoML compared to transfer learning for image-based plant phenotyping are discussed.

scholarly journals Hierarchical Transfer Learning for Cycle Time Forecasting for Semiconductor Wafer Lot under Different Work in Process Levels

Mathematics ◽  
2021 ◽  
Vol 9 (17) ◽  
pp. 2039
Author(s):  
Junliang Wang ◽  
Pengjie Gao ◽  
Zhe Li ◽  
Wei Bai
Keyword(s):  
Neural Network ◽  
Transfer Learning ◽  
Cycle Time ◽  
Learning Strategy ◽  
System Level ◽  
Hierarchical Optimization ◽  
Learning Approach ◽  
Semiconductor Wafer ◽  
Work In Process ◽  
Optimization Transfer

The accurate cycle time (CT) prediction of the wafer fabrication remains a tough task, as the system level of work in process (WIP) is fluctuant. Aiming to construct one unified CT forecasting model under dynamic WIP levels, this paper proposes a transfer learning method for finetuning the predicted neural network hierarchically. First, a two-dimensional (2D) convolutional neural network was constructed to predict the CT under a primary WIP level with the input of spatial-temporal characteristics by reorganizing the input parameters. Then, to predict the CT under another WIP level, a hierarchical optimization transfer learning strategy was designed to finetune the prediction model so as to improve the accuracy of the CT forecasting. The experimental results demonstrated that the hierarchically transfer learning approach outperforms the compared methods in the CT forecasting with the fluctuation of WIP levels.

scholarly journals Discretization and machine learning approximation of BSDEs with a constraint on the Gains-process

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Idris Kharroubi ◽  
Thomas Lim ◽  
Xavier Warin
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Differential Equations ◽  
Numerical Experiments ◽  
Optimization Problem ◽  
Learning Approach ◽  
The Neural Network ◽  
Machine Learning Approach ◽  
Mesh Grid

AbstractWe study the approximation of backward stochastic differential equations (BSDEs for short) with a constraint on the gains process. We first discretize the constraint by applying a so-called facelift operator at times of a grid. We show that this discretely constrained BSDE converges to the continuously constrained one as the mesh grid converges to zero. We then focus on the approximation of the discretely constrained BSDE. For that we adopt a machine learning approach. We show that the facelift can be approximated by an optimization problem over a class of neural networks under constraints on the neural network and its derivative. We then derive an algorithm converging to the discretely constrained BSDE as the number of neurons goes to infinity. We end by numerical experiments.

Determination of thermodynamic state variables of liquids from its microscopic structure using an artificial neural network

Soft Matter ◽  
2020 ◽  
Author(s):  
Ulices Que-Salinas ◽  
Pedro Ezequiel Ramirez-Gonzalez ◽  
Alexis Torres-Carbajal
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Distribution Function ◽  
Microscopic Structure ◽  
Machine Learning Method ◽  
Learning Method ◽  
State Variables ◽  
Thermodynamic State

In this work we implement a machine learning method to predict the thermodynamic state of a liquid using only its microscopic structure provided by the radial distribution function (RDF). The...

Machine Learning as a Silent Observer of Advanced Geoscience Interpretation

2021 ◽  
Author(s):  
Muhammad Sajid
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Transfer Learning ◽  
Learning Performance ◽  
Learning Approach ◽  
Seismic Fault ◽  
Facies Classification ◽  
The World ◽  
Learning Machine ◽  
Fault Interpretation

Abstract Machine learning is proving its successes in all fields of life including medical, automotive, planning, engineering, etc. In the world of geoscience, ML showed impressive results in seismic fault interpretation, advance seismic attributes analysis, facies classification, and geobodies extraction such as channels, carbonates, and salt, etc. One of the challenges faced in geoscience is the availability of label data which is one of the most time-consuming requirements in supervised deep learning. In this paper, an advanced learning approach is proposed for geoscience where the machine observes the seismic interpretation activities and learns simultaneously as the interpretation progresses. Initial testing showed that through the proposed method along with transfer learning, machine learning performance is highly effective, and the machine accurately predicts features requiring minor post prediction filtering to be accepted as the optimal interpretation.

Sign in / Sign up

Export Citation Format

Share Document