scholarly journals A DEEP DIVE INTO THE BASICS OF DEEP LEARNING

2021 ◽  
Vol 65 (2) ◽  
Author(s):  
Ivan Wolansky ◽  
Keyword(s):  
Deep Learning ◽  
Linear Functions ◽  
Summary Statistics ◽  
Activation Functions ◽  
Medical Field ◽  
Deep Dive ◽  
Final Layer ◽  
Non Linear ◽  
Linear Problems ◽  
Better Than

Deep learning is a type of machine learning (ML) that is growing in importance in the medical field. It can often perform better than traditional ML models on different metrics, and it can handle non-linear problems due to activation functions. Activation functions are different non-linear functions that are used to restrict the values propagated to an interval. In deep learning, information propagates forward, passing through different layers of weights and activation functions, before reaching the final layer. Then a cost function is evaluated and propagated back through the network to adjust weights. A convolutional neural network (CNN) is a form of deep learning that is used primarily in imaging. CNNs perform significantly well with grid-like inputs because they learn shapes well. CNNs compute dot products between layers and kernels in a convolutional layer, prior to pooling, which outputs summary statistics. CNNs are better than trivial neural networks for imaging due to a number of reasons, like sparse interaction and equivariance of translation

The relationship between nitrogen supply and the nitrogen yield of cut grass swards

1977 ◽  
Vol 88 (2) ◽  
pp. 289-292 ◽  
Author(s):  
I. R. Richards ◽  
R. D. Hobson
Keyword(s):  
Nitrogen Supply ◽  
Linear Functions ◽  
Available Nitrogen ◽  
England And Wales ◽  
Nitrogen Yield ◽  
Non Linear ◽  
Using Data ◽  
The Relationship ◽  
Potential Maximum ◽  
Better Than

SUMMARYUsing data from 140 experiments conducted at sites throughout England and Wales, a relationship between nitrogen supply and the nitrogen yield of cut grass swards was sought. One linear and three non-linear functions were fitted to the data. The non-linear functions fitted the data slightly better than did the linear and, over the range in nitrogen supply normally found, provided consistent predictions of grass nitrogen yield. The recovery of available nitrogen in the herbage was found to decline with level of nitrogen supply from a potential maximum of 79%.

scholarly journals Helping the Visually Impaired See via Image Multi-labeling Based on SqueezeNet CNN

2019 ◽  
Vol 9 (21) ◽  
pp. 4656 ◽  
Author(s):  
Haikel Alhichri ◽  
Yakoub Bazi ◽  
Naif Alajlan ◽  
Bilel Bin Jdira
Keyword(s):  
Deep Learning ◽  
Visually Impaired ◽  
Indoor Environment ◽  
State Of The Art ◽  
Activation Function ◽  
Linear Functions ◽  
Indoor Environments ◽  
Scene Description ◽  
Deep Cnn ◽  
Better Than

This work presents a deep learning method for scene description. (1) Background: This method is part of a larger system, called BlindSys, that assists the visually impaired in an indoor environment. The method detects the presence of certain objects, regardless of their position in the scene. This problem is also known as image multi-labeling. (2) Methods: Our proposed deep learning solution is based on a light-weight pre-trained CNN called SqueezeNet. We improved the SqueezeNet architecture by resetting the last convolutional layer to free weights, replacing its activation function from a rectified linear unit (ReLU) to a LeakyReLU, and adding a BatchNormalization layer thereafter. We also replaced the activation functions at the output layer from softmax to linear functions. These adjustments make up the main contributions in this work. (3) Results: The proposed solution is tested on four image multi-labeling datasets representing different indoor environments. It has achieved results better than state-of-the-art solutions both in terms of accuracy and processing time. (4) Conclusions: The proposed deep CNN is an effective solution for predicting the presence of objects in a scene and can be successfully used as a module within BlindSys.

Appropriate mathematical models for describing the complete lactation of dairy sheep

2000 ◽  
Vol 71 (2) ◽  
pp. 197-207 ◽  
Author(s):  
G. E. Pollott ◽  
E. Gootwine
Keyword(s):  
Milk Yield ◽  
Linear Functions ◽  
Dairy Sheep ◽  
Mathematical Functions ◽  
Lactation Curve ◽  
Non Linear ◽  
Birth Records ◽  
Daily Milk Yield ◽  
Parameter Function ◽  
Better Than

AbstractDespite milk being an important product from sheep, there are very few reports of milk production from the complete lactation of dairy sheep. The Improved Awassi in Israel is kept under an intensive system of management with lambs being weaned soon after birth. Records from one such flock were analysed to investigate the suitability of various mathematical functions for describing milk yield from the complete lactations of dairy sheep. This included a consideration of whether the functions could cope with short lactations, a characteristic of dairy sheep, and a limited number of test-day records per lactation.Four non-linear mathematical functions were investigated (Wood, Morant, Grossman and Pollott), two of which could also be fitted in a linear and a linear weighted form (Wood and Morant). These functions were fitted to weekly data from a ‘typical Awassi lactation curve’, represented by least squares means of daily milk yield from each week of a 40-week lactation derived from an analysis of 25605 test day records. Characteristics of the lactation were calculated from the functions, such as total milk yield, day and level of peak yield and persistency. These functions were also fitted to 1416 individual lactation records of up to 10 test-day records per lactation. The value of the functions was investigated using the residual mean square (RMS) of the fitted curve as an indicator of how well each function described the lactation. Forms of these functions with a reduced number of parameters were also investigated.The non-linear functions always fitted the data with a lower RMS than their linear equivalent and the weighted form of the linear functions always had a lower RMS than the unweighted form. Of the linear functions, Morant fitted better than Wood. Of the non-linear functions Grossman, Morant and Pollott (additive and multiplicative) fitted the data equally as well but better than Wood. The various functions predicted characteristics of the lactation curve differently; the Wood functions tended to overestimate yield in early lactation and the Morant functions underestimated peak yield.No function was better suited to short lactations than another. However the three-parameter function of Morant, Pollott multiplicative and Pollott additive were considered to be the most suitable for describing the complete lactation of dairy sheep.

scholarly journals Deep learning from phylogenies to uncover the transmission dynamics of epidemics

2021 ◽  
Author(s):  
J Voznica ◽  
A Zhukova ◽  
V Boskova ◽  
E Saulnier ◽  
F Lemoine ◽  
...  
Keyword(s):  
Deep Learning ◽  
Simulated Data ◽  
Large Set ◽  
Summary Statistics ◽  
Bayesian Approaches ◽  
Simulation Based ◽  
Dataset Size ◽  
Sex With Men ◽  
Inference Methods ◽  
Better Than

ABSTRACTWidely applicable, accurate and fast inference methods in phylodynamics are needed to fully profit from the richness of genetic data in uncovering the dynamics of epidemics. Standard methods, including maximum-likelihood and Bayesian approaches, which are both model specific, often rely on complex mathematical formulae and approximations, and do not scale well with dataset size. We develop a likelihood-free, simulation-based approach, which combines deep learning with (1) a large set of summary statistics measured on phylogenies or (2) a complete and compact vectorial representation of trees, which avoids potential limitations of summary statistics and applies to any phylodynamic model. Our method enables both model selection and estimation of epidemiological parameters. We demonstrate its speed and accuracy on simulated data, where it performs better than the state-of-the-art methods. To illustrate its applicability, we assess the dynamics induced by superspreading individuals in an HIV dataset of men- having-sex-with-men in Zurich.

scholarly journals Pathological Analysis of Blood Cells Using Deep Learning Techniques

2020 ◽  
Vol 13 ◽  
Author(s):  
Virender Ranga ◽  
Shivam Gupta ◽  
Priyansh Agrawal ◽  
Jyoti Meena
Keyword(s):  
Deep Learning ◽  
Blood Cells ◽  
Well Being ◽  
Input Image ◽  
Medical Sciences ◽  
Human Errors ◽  
Deep Dive ◽  
Proposed Model ◽  
Better Than

Introduction: The major area of work of pathologists is concerned with detecting the diseases and helping the patients in their healthcare and well-being. The present method used by pathologists for this purpose is manually viewing the slides using a microscope and other instruments. But this method suffers from a lot of problems, like there is no standard way of diagnosing, human errors and it puts a heavy load on the laboratory men to diagnose such a large number of slides daily. Method: The slide viewing method is widely used and converted into digital form to produce high resolution images. This enables the area of deep learning and machine learning to deep dive into this field of medical sciences. In the present study, a neural based network has been proposed for classification of blood cells images into various categories. When input image is passed through the proposed architecture and all the hyper parameters and dropout ratio values are used in accordance with proposed algorithm, then model classifies the blood images with an accuracy of 95.24%. Result: After training the models on 20 epochs. The plots of training accuracy, testing accuracy and corresponding training loss, testing loss for proposed model is plotted using matplotlib and trends. Discussion: The performance of proposed model is better than existing standard architectures and other work done by various researchers. Thus, the proposed model enables the development of pathological system which will reduce human errors and daily load on laboratory men. This can also in turn help pathologists in carrying out their work more efficiently and effectively. Conclusion: In the present study, a neural based network has been proposed for classification of blood cells images into various categories. These categories have significance in the medical sciences. When input image is passed through the proposed architecture and all the hyper parameters and dropout ratio values are used in accordance with proposed algorithm, then model classifies the images with an accuracy of 95.24%. This accuracy is better than standard architectures.. Further it can be seen that the proposed neural network performs better than present related works carried by various researchers.

Comparison of various Activation Functions A Deep Learning Approach

2018 ◽  
Vol 6 (3) ◽  
pp. 122-126
Author(s):  
Mohammed Ibrahim Khan ◽  
◽  
Akansha Singh ◽  
Anand Handa ◽  
◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning Approach ◽  
Activation Functions

Analysis of Non-Linear Activation Functions for Classification Tasks Using Convolutional Neural Networks

2019 ◽  
Vol 12 (3) ◽  
pp. 156-161 ◽  
Author(s):  
Aman Dureja ◽  
Payal Pahwa
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Activation Function ◽  
Primary Objective ◽  
Experimental Comparison ◽  
Activation Functions ◽  
Practical Applications ◽  
Network Activation ◽  
Non Linear ◽  
Hidden Layer

Background: In making the deep neural network, activation functions play an important role. But the choice of activation functions also affects the network in term of optimization and to retrieve the better results. Several activation functions have been introduced in machine learning for many practical applications. But which activation function should use at hidden layer of deep neural networks was not identified. Objective: The primary objective of this analysis was to describe which activation function must be used at hidden layers for deep neural networks to solve complex non-linear problems. Methods: The configuration for this comparative model was used by using the datasets of 2 classes (Cat/Dog). The number of Convolutional layer used in this network was 3 and the pooling layer was also introduced after each layer of CNN layer. The total of the dataset was divided into the two parts. The first 8000 images were mainly used for training the network and the next 2000 images were used for testing the network. Results: The experimental comparison was done by analyzing the network by taking different activation functions on each layer of CNN network. The validation error and accuracy on Cat/Dog dataset were analyzed using activation functions (ReLU, Tanh, Selu, PRelu, Elu) at number of hidden layers. Overall the Relu gave best performance with the validation loss at 25th Epoch 0.3912 and validation accuracy at 25th Epoch 0.8320. Conclusion: It is found that a CNN model with ReLU hidden layers (3 hidden layers here) gives best results and improve overall performance better in term of accuracy and speed. These advantages of ReLU in CNN at number of hidden layers are helpful to effectively and fast retrieval of images from the databases.

scholarly journals Deep learning for intelligent diagnosis in thyroid scintigraphy

2021 ◽  
Vol 49 (1) ◽  
pp. 030006052098284
Author(s):  
Tingting Qiao ◽  
Simin Liu ◽  
Zhijun Cui ◽  
Xiaqing Yu ◽  
Haidong Cai ◽  
...  
Keyword(s):  
Deep Learning ◽  
Disease Diagnosis ◽  
Kappa Coefficient ◽  
Diagnostic Assessment ◽  
First Year ◽  
Thyroid Scintigraphy ◽  
Diagnostic Ability ◽  
The Third ◽  
Classification Time ◽  
Better Than

Objective To construct deep learning (DL) models to improve the accuracy and efficiency of thyroid disease diagnosis by thyroid scintigraphy. Methods We constructed DL models with AlexNet, VGGNet, and ResNet. The models were trained separately with transfer learning. We measured each model’s performance with six indicators: recall, precision, negative predictive value (NPV), specificity, accuracy, and F1-score. We also compared the diagnostic performances of first- and third-year nuclear medicine (NM) residents with assistance from the best-performing DL-based model. The Kappa coefficient and average classification time of each model were compared with those of two NM residents. Results The recall, precision, NPV, specificity, accuracy, and F1-score of the three models ranged from 73.33% to 97.00%. The Kappa coefficient of all three models was >0.710. All models performed better than the first-year NM resident but not as well as the third-year NM resident in terms of diagnostic ability. However, the ResNet model provided “diagnostic assistance” to the NM residents. The models provided results at speeds 400 to 600 times faster than the NM residents. Conclusion DL-based models perform well in diagnostic assessment by thyroid scintigraphy. These models may serve as tools for NM residents in the diagnosis of Graves’ disease and subacute thyroiditis.

scholarly journals Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Christian Crouzet ◽  
Gwangjin Jeong ◽  
Rachel H. Chae ◽  
Krystal T. LoPresti ◽  
Cody E. Dunn ◽  
...  
Keyword(s):  
Deep Learning ◽  
Prussian Blue ◽  
Processing Speed ◽  
Digital Pathology ◽  
Ground Truth ◽  
Individual Variability ◽  
Rgb Images ◽  
Cerebral Microhemorrhages ◽  
Phasor Analysis ◽  
Better Than

AbstractCerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5–40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian blue-stained regions of interest, which is prone to inter-individual variability and can lead to significant delays in data analysis. To improve this labor-intensive process, we developed and compared three digital pathology approaches to identify and quantify CMHs from Prussian blue-stained brain sections: (1) ratiometric analysis of RGB pixel values, (2) phasor analysis of RGB images, and (3) deep learning using a mask region-based convolutional neural network. We applied these approaches to a preclinical mouse model of inflammation-induced CMHs. One-hundred CMHs were imaged using a 20 × objective and RGB color camera. To determine the ground truth, four users independently annotated Prussian blue-labeled CMHs. The deep learning and ratiometric approaches performed better than the phasor analysis approach compared to the ground truth. The deep learning approach had the most precision of the three methods. The ratiometric approach has the most versatility and maintained accuracy, albeit with less precision. Our data suggest that implementing these methods to analyze CMH images can drastically increase the processing speed while maintaining precision and accuracy.

scholarly journals Collocation Methods for High-Order Well-Balanced Methods for Systems of Balance Laws

Mathematics ◽  
2021 ◽  
Vol 9 (15) ◽  
pp. 1799
Author(s):  
Irene Gómez-Bueno ◽  
Manuel Jesús Castro Díaz ◽  
Carlos Parés ◽  
Giovanni Russo
Keyword(s):  
High Order ◽  
Collocation Methods ◽  
Quadrature Formulas ◽  
Balance Laws ◽  
Source Terms ◽  
Time Step ◽  
Systems Of Balance Laws ◽  
Reconstruction Operator ◽  
Non Linear ◽  
Linear Problems

In some previous works, two of the authors introduced a technique to design high-order numerical methods for one-dimensional balance laws that preserve all their stationary solutions. The basis of these methods is a well-balanced reconstruction operator. Moreover, they introduced a procedure to modify any standard reconstruction operator, like MUSCL, ENO, CWENO, etc., in order to be well-balanced. This strategy involves a non-linear problem at every cell at every time step that consists in finding the stationary solution whose average is the given cell value. In a recent paper, a fully well-balanced method is presented where the non-linear problems to be solved in the reconstruction procedure are interpreted as control problems. The goal of this paper is to introduce a new technique to solve these local non-linear problems based on the application of the collocation RK methods. Special care is put to analyze the effects of computing the averages and the source terms using quadrature formulas. A general technique which allows us to deal with resonant problems is also introduced. To check the efficiency of the methods and their well-balance property, they have been applied to a number of tests, ranging from easy academic systems of balance laws consisting of Burgers equation with some non-linear source terms to the shallow water equations—without and with Manning friction—or Euler equations of gas dynamics with gravity effects.

Sign in / Sign up

Export Citation Format

Share Document