scholarly journals Can Deep Learning Identify Tomato Leaf Disease?

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Keke Zhang ◽  
Qiufeng Wu ◽  
Anwang Liu ◽  
Xiangyan Meng
Keyword(s):  
Gradient Descent ◽  
Tomato Leaf ◽  
Plant Diseases ◽  
Fine Tuning ◽  
Stochastic Gradient Descent ◽  
Batch Size ◽  
Optimal Model ◽  
Combined Model ◽  
Leaf Disease ◽  
Fully Connected

This paper applies deep convolutional neural network (CNN) to identify tomato leaf disease by transfer learning. AlexNet, GoogLeNet, and ResNet were used as backbone of the CNN. The best combined model was utilized to change the structure, aiming at exploring the performance of full training and fine-tuning of CNN. The highest accuracy of 97.28% for identifying tomato leaf disease is achieved by the optimal model ResNet with stochastic gradient descent (SGD), the number of batch size of 16, the number of iterations of 4992, and the training layers from the 37 layer to the fully connected layer (denote as “fc”). The experimental results show that the proposed technique is effective in identifying tomato leaf disease and could be generalized to identify other plant diseases.

Challenging the Recognition of Facial Expression via Deep Learning

2014 ◽  
Vol 571-572 ◽  
pp. 717-720
Author(s):  
De Kun Hu ◽  
Yong Hong Liu ◽  
Li Zhang ◽  
Gui Duo Duan
Keyword(s):  
Neural Network ◽  
Facial Expression ◽  
Gradient Descent ◽  
Deep Neural Network ◽  
Back Propagation ◽  
Stochastic Gradient Descent ◽  
Excellent Performance ◽  
Proposed Model ◽  
Input Layer ◽  
Fully Connected

A deep Neural Network model was trained to classify the facial expression in unconstrained images, which comprises nine layers, including input layer, convolutional layer, pooling layer, fully connected layers and output layer. In order to optimize the model, rectified linear units for the nonlinear transformation, weights sharing for reducing the complexity, “mean” and “max” pooling for subsample, “dropout” for sparsity are applied in the forward processing. With large amounts of hard training faces, the model was trained via back propagation method with stochastic gradient descent. The results of shows the proposed model achieves excellent performance.

scholarly journals Computational Complexity of Gradient Descent Algorithm

2021 ◽  
Author(s):  
Nishchal J ◽  
neel bhandari
Keyword(s):  
Computational Complexity ◽  
Linear Regression ◽  
Gradient Descent ◽  
Stochastic Gradient Descent ◽  
Batch Size ◽  
Automated Learning ◽  
Gradient Descent Algorithm ◽  
The World ◽  
Different Types ◽  
Insight Into

Information is mounting exponentially, and the world is moving to hunt knowledge with the help of Big Data. The labelled data is used for automated learning and data analysis which is termed as Machine Learning. Linear Regression is a statistical method for predictive analysis. Gradient Descent is the process which uses cost function on gradients for minimizing the complexity in computing mean square error. This work presents an insight into the different types of Gradient descent algorithms namely, Batch Gradient Descent, Stochastic Gradient Descent and Mini-Batch Gradient Descent, which are implemented on a Linear regression dataset, and hence determine the computational complexity and other factors like learning rate, batch size and number of iterations which affect the efficiency of the algorithm.

scholarly journals Inefficiency of K-FAC for Large Batch Size Training

2020 ◽  
Vol 34 (04) ◽  
pp. 5053-5060
Author(s):  
Linjian Ma ◽  
Gabe Montague ◽  
Jiayu Ye ◽  
Zhewei Yao ◽  
Amir Gholami ◽  
...  
Keyword(s):  
Gradient Descent ◽  
Computational Cost ◽  
Parameter Tuning ◽  
Stochastic Gradient Descent ◽  
Batch Size ◽  
Common Belief ◽  
Record Times ◽  
Large Batch ◽  
Strong Scaling ◽  
Batch Sizes

There have been several recent work claiming record times for ImageNet training. This is achieved by using large batch sizes during training to leverage parallel resources to produce faster wall-clock training times per training epoch. However, often these solutions require massive hyper-parameter tuning, which is an important cost that is often ignored. In this work, we perform an extensive analysis of large batch size training for two popular methods that is Stochastic Gradient Descent (SGD) as well as Kronecker-Factored Approximate Curvature (K-FAC) method. We evaluate the performance of these methods in terms of both wall-clock time and aggregate computational cost, and study the hyper-parameter sensitivity by performing more than 512 experiments per batch size for each of these methods. We perform experiments on multiple different models on two datasets of CIFAR-10 and SVHN. The results show that beyond a critical batch size both K-FAC and SGD significantly deviate from ideal strong scaling behaviour, and that despite common belief K-FAC does not exhibit improved large-batch scalability behavior, as compared to SGD.

scholarly journals Analysis of Tomato Leaf Disease Identification Techniques

2021 ◽  
Vol 2 (2) ◽  
pp. 98-103
Author(s):  
Gaurav Chopra ◽  
Pawan Whig
Keyword(s):  
Learning Algorithm ◽  
State Of The Art ◽  
Tomato Leaf ◽  
Plant Diseases ◽  
Disease Classification ◽  
Identification System ◽  
Great Success ◽  
Tomato Crop ◽  
Leaf Disease ◽  
Comparable Accuracy

India loses thousands of metric tons of tomato crop every year due to pests and diseases. Tomato leaf disease is a major issue that causes significant losses to farmers and possess a threat to the agriculture sector. Understanding how does an algorithm learn to classify different types of tomato leaf disease will help scientist and engineers built accurate models for tomato leaf disease detection. Convolutional neural networks with backpropagation algorithms have achieved great success in diagnosing various plant diseases. However, human benchmarks in diagnosing plant disease have still not been displayed by any computer vision method. Under different conditions, the accuracy of the plant identification system is much lower than expected by algorithms. This study performs analysis on features learned by the backpropagation algorithm and studies the state-of-the-art results achieved by image-based classification methods. The analysis is shown through gradient-based visualization methods. In our analysis, the most descriptive approach to generated attention maps is Grad-CAM. Moreover, it is also shown that using a different learning algorithm than backpropagation is also possible to achieve comparable accuracy to that of deep learning models. Hence, state-of-the-art results might show that Convolutional Neural Network achieves human comparable accuracy in tomato leaf disease classification through supervised learning. But, both genetic algorithms and semi-supervised models hold the potential to built precise systems for tomato leaf detection.

scholarly journals Texture-Based Feature Extraction Using Gabor Filters to Detect Diseases of Tomato Leaves

2021 ◽  
Vol 35 (4) ◽  
pp. 331-339
Author(s):  
Wiharto ◽  
Fikri Hashfi Nashrullah ◽  
Esti Suryani ◽  
Umi Salamah ◽  
Nurcahya Pradana Taufik Prakisy ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Detection System ◽  
Gabor Filters ◽  
Tomato Leaf ◽  
Plant Diseases ◽  
Support Vector ◽  
Disease Detection ◽  
Final Decision ◽  
Early Detection Of Disease ◽  
Leaf Disease

The disease in tomato plants, especially on tomato leaves will have an impact on the quality and quantity of tomatoes produced. Handling disease on tomato leaves that must be done is to detect the type of disease as early as possible, then determine the treatment that must be done. Detection of its types of tomato plant diseases requires sufficient knowledge and experience. The problem is that many beginner farmers in growing tomatoes do not have much knowledge, so they have failed in growing tomatoes. Based on these cases, this study proposes a model for the early detection of disease in tomato leaves based on image processing. The research method used is divided into 5 stages, namely preprocessing, segmentation, feature extraction, classification, and performance evaluation. The feature extraction stage used is texture-based with Gabor filters and color-based filters. The final decision is determined by the Support Vector Machine (SVM) classification algorithm with the Radial Basis Function (RBF) kernel. The test results of the tomato leaf disease detection system produced an average performance parameter of 98.83% specificity, 90.37% sensitivity, 90.34% F1-score, 90.37% accuracy, and 94.60% area under the curve (AUC). Referring to the resulting of the AUC performance, the tomato leaf disease detection system is in the very good category.

scholarly journals Computational Complexity of Gradient Descent Algorithm

2021 ◽  
Author(s):  
Nishchal J ◽  
neel bhandari
Keyword(s):  
Computational Complexity ◽  
Linear Regression ◽  
Gradient Descent ◽  
Stochastic Gradient Descent ◽  
Batch Size ◽  
Automated Learning ◽  
Gradient Descent Algorithm ◽  
The World ◽  
Different Types ◽  
Insight Into

Information is mounting exponentially, and the world is moving to hunt knowledge with the help of Big Data. The labelled data is used for automated learning and data analysis which is termed as Machine Learning. Linear Regression is a statistical method for predictive analysis. Gradient Descent is the process which uses cost function on gradients for minimizing the complexity in computing mean square error. This work presents an insight into the different types of Gradient descent algorithms namely, Batch Gradient Descent, Stochastic Gradient Descent and Mini-Batch Gradient Descent, which are implemented on a Linear regression dataset, and hence determine the computational complexity and other factors like learning rate, batch size and number of iterations which affect the efficiency of the algorithm.

scholarly journals Taming the Noisy Gradient: Train Deep Neural Networks with Small Batch Sizes

2019 ◽  
Author(s):  
Yikai Zhang ◽  
Hui Qu ◽  
Chao Chen ◽  
Dimitris Metaxas
Keyword(s):  
Neural Networks ◽  
Gradient Descent ◽  
Deep Neural Networks ◽  
Stochastic Gradient Descent ◽  
Batch Size ◽  
Training Performance ◽  
Strongly Convex ◽  
Batch Sizes ◽  
Learning Architectures ◽  
New Framework

Deep learning architectures are usually proposed with millions of parameters, resulting in a memory issue when training deep neural networks with stochastic gradient descent type methods using large batch sizes. However, training with small batch sizes tends to produce low quality solution due to the large variance of stochastic gradients. In this paper, we tackle this problem by proposing a new framework for training deep neural network with small batches/noisy gradient. During optimization, our method iteratively applies a proximal type regularizer to make loss function strongly convex. Such regularizer stablizes the gradient, leading to better training performance. We prove that our algorithm achieves comparable convergence rate as vanilla SGD even with small batch size. Our framework is simple to implement and can be potentially combined with many existing optimization algorithms. Empirical results show that our method outperforms SGD and Adam when batch size is small. Our implementation is available at https://github.com/huiqu18/TRAlgorithm.

scholarly journals Exchangeability and Kernel Invariance in Trained MLPs

2019 ◽  
Author(s):  
Russell Tsuchida ◽  
Fred Roosta ◽  
Marcus Gallagher
Keyword(s):  
Machine Learning ◽  
Gradient Descent ◽  
Stochastic Gradient ◽  
Stochastic Gradient Descent ◽  
Learning Models ◽  
Fully Connected ◽  
Shed Light ◽  
Machine Learning Models

In the analysis of machine learning models, it is often convenient to assume that the parameters are IID. This assumption is not satisfied when the parameters are updated through training processes such as Stochastic Gradient Descent. A relaxation of the IID condition is a probabilistic symmetry known as exchangeability. We show the sense in which the weights in MLPs are exchangeable. This yields the result that in certain instances, the layer-wise kernel of fully-connected layers remains approximately constant during training. Our results shed light on such kernel properties throughout training while limiting the use of unrealistic assumptions.

Sign in / Sign up

Export Citation Format

Share Document