DEEP LEARNING FOR NONLINEAR REGRESSION

General Information:

Cover Page:

Outline:

CHAPTER I Background on deep learning
1.1 INTRODUCTION
ARTIFICIAL INTELLIGENCE
1.2.1 Analytical Al
1.2.2 Functional Al
1.2.3 Interactive Al.
1.2.4 Textual Al
1.2.5 Visual Al
1.2.6 Potential Al Techniques
A) Data mining, knowledge discovery and advanced analytics
B) Rule-Based modeling and decision-making.
C) Fuzzy Logic-Based approach
D) Knowledge representation, uncertainty reasoning and expert system modeling. Case-basedreasoning (CBR)
E) Text mining and Natural Language processing
F) Visual analytics, Computer vision and pattern recognition.
G) Hybridapproach, Searching and optimization
1.3 MACHINE LEARNING
1.3.1 Supervised learning.
1.3.2 Unsupervised learning
1.3.3 Semi-supervised learning
1.3.4 Reinforcement learning.
1.3.5 Machine Learning Tasks and Algorithms
1.3.6 Machine learning algorithms.
1.3.7 Dimensionality Reduction and Feature Learning
1.3.8 Real-World Applications of Al and ML
1.4 DEEP LEARNING
1.4.1 Various Forms of Data.
A) Sequential data
B) Image or 2D Data
C) Tabular Data.
1.4.2 DL Properties and Dependencies.
A) Data Dependencies.
B) Hardware Dependencies.
C) Feature Engineering Process.
D) Model Training and Execution time
1.4.3 Deep Learning Techniques and Applications
A) Deep Networks for supervised or discriminative Learning
Convolutional Neural Network (CNN or ConvNet).
Recurrent Neural Network (RNN) and its Variants
Long short-term memory (LSTM).
RNN/LSTM bidirectional.
Recurrent gated units (GRUS)
Bayesian Neural Network
B) Deep Networks for Generative or Unsupervised Learning.
Generative Adversarial Network (GAN).
Auto-Encoder (AE) and Its Variants
Kohonen Map or Self-Organizing Map (SOM)
Boltzmann Machine Restricted (RBM).
1.5 Deep Networks for Hybrid Learning and Other Approaches Hybrid Deep Neural Networks
Deep Transfer Learning (DTL)
Deep Reinforcement Learning (DRL).
1.4.4 Real-World Applications of DL
CONCLUSION.
2 CHAPTER II Nonlinear Regression
INTRODUCTION
REGRESSION ANALYSIS
2.2.1 Simple and multiple linear regression
2.2.2 Polynomial regression
2.2.3 LASSO and ridge regression
2.2.4 Logistic regression
2.2.5 Quantile regression.
2.2.6 Bayesian linear regression
2.2.7 Principal components regression
2.2.8 Partial least squares regression
2.2.9 Elastic Net regression.
2.3 LINEAR AND NON-LINEAR REGRESSION MODELS
2.3.1 Linear regression models.
2.3.2 Nonlinear regression models.
2.4 CONCLUSION
3 CHAPTER III Development of CNN model based on real dataset 57
INTRODUCTION
CASE OF STUDY
MATERIALS AND METHODS.
3.3.1 Materials
3.3.2 Dataset.
3.3.3 The Proposed model.
A) The CNN submodel
B) The SVM submodel.
3.4 RESULTS AND DISCUSSION
3.4.1 Comparison with MLP model
3.5 SOFTWARE
3.5.1 User interaction and design.
3.6 CONCLUSION

Download The Thesis:

📥 تحميل الملف

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