Fundamentals of deep learning: a step-by-step guide

(Note: this manuscript summarizes part of my learning experience on machine learning in the past two years, and I hope it can benefit faculty, students or engineers who want to start a journey of “machine learning”. Comments or feedbacks can be sent to weidong.kuang@utrgv.edu. Your comments  and feedbacks are invaluable for me to improve it.)

Content

Preface (pdf) (pp.4) (updated on 2/23/2023)

Chapter 1      Introduction to deep learning (pdf) (pp.19) (19) (updated on 2/23/2023)

Chapter 2      A Brief Mathematical Review (pdf) (pp.51) (70) (updated on 2/23/2023)

Chapter 3      Linear Regression (pdf) (pp.23) (51)

Chapter 4      Logistic Regression (pdf) (pp.26) (77)

Chapter 5      Regularization (pdf) (pp.22) (99)

Chapter 6      Basics of Neural Networks (pdf) (pp.37) (136)

Chapter 7      Multiple-Layer Neural Networks (pdf) (pp.27) (163)

Chapter 8      Practical Considerations in Machine Learning (pdf) (pp.30) (193)

Chapter 9      A Comprehensive Example of Neural Networks (pdf) (pp.24) (217)

Chapter 10    An Introduction to PyTorch (pdf) (pp.35) (252)

Chapter 11    Convolutional Neural Networks (pdf) (pp.23) (275)

Chapter 12   Object Detection (pdf) (pp.26) (301)

Chapter 13   A Tutorial of Object Detection (pdf) (pp.31) (332)

Chapter 14   Generative Adversarial Nets (pdf) (pp.41) (373)

(more chapters are coming soon)

Appendix A   Jupyter Notebook and PyTorch Installation (doc)

 

Note: if you need the copies of python files in the manuscript, please send a request to

            weidong.kuang@utrgv.edu