Explainable convolutional networks for covid-19

General Information:

Cover Page:

Outline:

GENERAL INTRODUCTION
CHAPTRE I IMAGE CLASSIFICATION
I.1 Introduction
I.2 Computer vision
I.3 Applications of computer vision
I.4 Image classification
I.4.1 Types of image classification
I.4.2 Datasets for image classification
I.4.3 Confusion matrix
I.4.4 Image Classification Metrics
I.5 Conclusion
CHAPTRE II DEEP LEARNING
II.1 Introduction
II.2 What is deep learning
II.3 Deep learning applications
II.4 A brief History of Deep Learning
II.5 Artificial Neural Networks
II.5.1 Biological neurons
II.5.2 The Perceptron
II.5.3 The multilayer perceptron
II.5.4 Activation function
II.5.5 Loss function
II.5.6 Gradient descent
II.5.7 Variants of gradient Descent
II.5.8 Adaptive Learning Rate Optimization techniques for Gradient Descent
II.5.9 Backpropagation
II.6 Deep neural network
II.7 Convolutional Neural Networks
II.7.1 Convolutional layers
II.7.2 Pooling layers
II.7.3 Fully connected layers
II.7.4 History of CNNs
II.7.5 The famous state-of-the-art CNNs
II.8 Transfer Learning
II.9 Explainability in convolutional neural networks
II.9.1 Importance of explainability in a CNN model
II.9.2 Preliminary Methods
II.9.3 Activation based methods
II.9.4 Gradient based methods
II.10 Conclusion
CHAPTRE III MODEL DESIGN AND IMPLEMENTATION
III.1 Introduction
III.2 Related works
III.3 Dataset used in this work
III.4 Development tools
III.5 Implementation workflow
III.6 Conclusion
GENERAL CONCLUSION
REFERENCES AND BIBLIOGRAPHY

Download The Thesis:

📥 تحميل الملف

For more
academic sources and references,
including theses and dissertations from Algerian universities,
, visit our main website.