ChatGPT for Deep Learning with Python Keras and Tensorflow

سرفصل های دوره

Master Image Recognition, Time Series Prediction, Regression and Classification with ChatGPT! A Project-based Course.

1. Introduction

1. Welcome and Introduction

2. Sneak Preview Deep Learning with ChatGPT

3. How to get the most out of this course

4. Course Overview

5.1 Course Materials.zip

5. Download Materials Downloads

2. ChatGPT Introduction

1. What is ChatGPT and how does it work

2. ChatGPT vs. Search Engines

3. Artificial Intelligence vs. Human Intelligence

4. Creating a ChatGPT account and getting started

5. Design Update November 2023

6. Features, Options and Products around GPT models

7. Navigating the OpenAI Website

8. What is a Token and how do Tokens work

9. Prompt Engineering Techniques (Part 1)

10. Prompt(s) used in previous Lecture.html

11. Prompt Engineering Techniques (Part 2)

12. Prompt(s) used in previous Lecture.html

13. Prompt Engineering Techniques (Part 3)

14. Prompt(s) used in previous Lecture.html

3. Python Installation

1. Download and Install Anaconda

2. How to open Jupyter Notebooks

3. How to work with Jupyter Notebooks

4. How to create a customized Environment for Deep Learning

4. Understanding Deep Learning and Neural Networks - with ChatGPT

1. Deep Learning vs. traditional Machine Learning

2. Prompt(s) used in previous Lecture.html

3. Neural Network Types - Overview

4. Prompt(s) used in previous Lecture.html

5. The Feedforward Neural Network (FNN) explained

6. Prompt(s) used in previous Lecture.html

7. Neural Network Types - CNN and RNN at a glance

8. Prompt(s) used in previous Lecture.html

9. Pre-trained GPT models vs. customized Neural Networks - What to use when

10. Prompt(s) used in previous Lecture.html

11. Test your Deep Learning Neural Networks Knowledge.html

5. Introduction Project Explore an unknown Dataset with ChatGPT and Pandas

1. Project Introduction

2. Project Assignment

3. Providing the Dataset to GPT3.5

4. Prompt(s) used in previous Lecture.html

5. Task 1 Inspecting the Dataset with GPT3.5

6. Prompt(s) used in previous Lecture.html

7. Task 2 Brainstorming with GPT3.5

8. Prompt(s) used in the previous Lecture.html

9. Task 3 Data Cleaning with GPT3.5

10. Prompt(s) used in previous Lecture.html

11. Task 4 Identifying and Creating new Features with GPT3.5

12. Prompt(s) used in previous Lecture.html

13. Task 5 Saving the cleaned Dataset

14. Prompt(s) used in previous Lecture.html

15. Loading the Dataset with GPT4

16. Prompt(s) used in previous Lecture.html

17. Initial Data Inspection and Brainstorming with GPT4

18. Prompt(s) used in previous Lecture.html

19. Data Cleaning with GPT4

20. Prompt(s) used in previous Lecture.html

21. Troubleshooting

22. Identifying and Creating new Features with GPT4

23. Prompt(s) used in previous Lecture.html

24. How to download and save the cleaned Dataset from GPT4

25. Prompt(s) used in previous Lecture.html

26. Conclusion, Final Remarks and Troubleshooting

6. Using ChatGPT for Explanatory Data Analysis (EDA)

1. Project Introduction

2. Project Assignment

3. Task 1 (Up-) Loading the Dataset and first Inspection

4. Prompt(s) used in the previous Lecture.html

5. Excursus Behind the Scenes

6. Task 2 Brainstorming Goals and Objectives of an EDA

7. Prompt(s) used in the previous Lecture.html

8. Task 3 Univariate Data Analysis

9. Prompt(s) used in the previous Lecture.html

10. Task 4 Multivariate Data Analysis Correlations

11. Prompt(s) used in the previous Lecture.html

12. Task 5 Exploring Factors influencing Income

13. Prompt(s) used in the previous Lecture.html

14. Task 6 Implications & Outlook

15. Prompt(s) used in the previous Lecture.html

16. The Code reviewed & Troubleshooting

7. Using ChatGPT for Binary Classification with Feedforward Neural Networks (FNN)

1. Project Introduction

2. Project Assignment

3. Task 1 (Up-) Loading the Dataset and first Inspection

4. Prompt(s) used in previous Lecture.html

5. Task 2 Brainstorming How to best tackle a FNN Classification Project

6. Prompt(s) used in previous Lecture.html

7. Task 3 Data Pre-processing and Feature Engineering (Theory)

8. Prompt(s) used in previous Lecture.html

9. Feature-specific questions and considerations

10. Prompt(s) used in previous Lecture.html

11. Actions derived from Brainstorming

12. Task 4 Data Pre-Processing and Feature Engineering (Code)

13. Prompt(s) used in previous Lecture.html

14. Task 5 Defining and Fitting an FNN Baseline Model

15. Prompt(s) used in previous Lecture.html

16. Task 6 Evaluation of Baseline Model on the Test Set

17. Prompt(s) used in previous Lecture.html

18. Task 7 Model Optimization - Theory

19. Prompt(s) used in previous Lecture.html

20. Task 7 Model Optimization - Code

21. Prompt(s) used in the previous Lecture.html

22. Performance Evaluation and Model Architecture

23. Prompt(s) used in the previous Lecture.html

24. Modifying the number of Hidden Layers

25. Task 8 Decision Thresholds (Precision vs. Recall)

26. Prompt(s) used in the previous Lecture.html

27. The full project using GPT4 (Part 1)

28. The full project using GPT4 (Part 2)

29. Bonus Task Feature Importance and Outlook (Part 1)

30. Prompt(s) used in the previous Lecture.html

31. Bonus Task Feature Importance and Outlook (Part 2)

32. Prompt(s) used in the previous Lecture.html

8. Using ChatGPT for Image Recognition with Convolutional Neural Networks (CNN)

1. Project Introduction

2. Project Assignment

3. Task 1 Downloading the Dataset

4. Task 2 Loading the Dataset with Python and first Data Inspection

5. Prompt(s) used in the previous Lecture.html

6. Task 3 Displaying the images with Python

7. Prompt(s) used in the previous Lecture.html

8. Task 4 Loading, Merging, formatting and storing the full dataset

9. Prompt(s) used in the previous Lecture.html

10. Task 5 Data Preprocessing

11. Prompt(s) used in the previous Lecture.html

12. Task 6 Brainstorming

13. Prompt(s) used in the previous Lecture.html

14. Task 7 Creating and Training a Baseline CNN model

15. Prompt(s) used in the previous Lecture.html

16. Task 8 Evaluating the Baseline Model

17. Prompt(s) used in the previous Lecture.html

18. Task 9 Data Augmentation & Model Checkpointing

19. Prompt(s) used in the previous Lecture.html

20. Model Checkpointing

21. Advanced Data Augmentation & Fine Tuning

22. Prompt(s) used in the previous Lecture.html

23. Task 10 Increasing Model Architecture Complexity & Dropout

24. Prompt(s) used in the previous Lecture.html

25. Adding Dropout

26. Prompt(s) used in the previous Lecture.html

9. Using ChatGPT for Time Series Prediction with Recurrent Neural Networks (RNN)

1. Project Introduction

2. Project Assignment

3. Task 1 (Up-) Loading the Dataset and first Inspection

4. Prompt(s) used in the previous Lecture.html

5. Task 2 Explanatory Data Analysis (EDA)

6. Prompt(s) used in previous Lecture.html

7. Task 3 Brainstorming How to best tackle an RNN Time Series Project

8. Prompt(s) used in the previous Lecture.html

9. Task 4 Covariance Stationarity and other Time Series specific aspects

10. Prompt(s) used in the previous Lecture.html

11. Task 5 Feature Creation - adding temporal features

12. Prompt(s) used in the previous Lecture.html

13. Task 6 Creating and fitting a Baseline Model

14. Prompt(s) used in the previous Lecture.html

15. Performance Evaluation on the Test Set

16. Prompt(s) used in the previous Lecture.html

17. Finding the optimal look-back period (Lags)

18. Task 7 Adding more Features to the model (Part 1)

19. Prompt(s) used in the previous Lecture.html

20. Task 7 Adding more Features to the model (Part 2)

21. Task 8 Adding Temporal Features to the model

22. Prompt(s) used in the previous Lecture.html

23. Task 9 Increase the complexity of the LSTM Architecture

24. Prompt(s) used in the previous Lecture.html

25. Task 10 Adding Early Stopping, Validation & more

26. Final Assessment and potential Improvements

27. Prompt(s) used in the previous Lecture.html

10. Appendix Pandas Crash Course

1. Introduction

2. Intro to Tabular Data Pandas

3. Create your very first Pandas DataFrame (from csv)

4. Loading a CSV-file into Pandas.html

5. How to read CSV-files from other Locations

6. Pandas Display Options and the methods head() & tail()

7. First Data Inspection

8. Summary Statistics.html

9. Built-in Functions, Attributes and Methods with Pandas

10. Make it easy TAB Completion and Tooltip

11. Selecting Columns

12. Selecting one Column with the dot notation

13. Selecting Columns.html

14. Zero-based Indexing and Negative Indexing

15. Selecting Rows with iloc (position-based indexing)

16. Slicing Rows and Columns with iloc (position-based indexing)

17.1 pandas iloc.pdf

17. Position-based Indexing Cheat Sheets.html

18. Position-based Indexing 1.html

19. Position-based Indexing 2.html

20. Selecting Rows with loc (label-based indexing)

21. Slicing Rows and Columns with loc (label-based indexing)

22.1 Pandas loc.pdf

22. Label-based Indexing Cheat Sheets.html

23. Label-based Indexing 1.html

24. Label-based Indexing 2.html

25. First Steps with Pandas Series

26. Analyzing Numerical Series with unique(), nunique() and value counts()

27. Analyzing non-numerical Series with unique(), nunique(), value counts()

28. First Steps with Pandas Index Objects

29. Filtering DataFrames by one Condition

30. Filtering DataFrames by many Conditions

31. Sorting DataFrames with sort index() and sort values()

32. Visualizing Data with the plot() method

33. Creating Histograms

34. Creating Scatterplots

35. Understanding GroupBy objects

36. Splitting with many Keys

37. split-apply-combine explained

139,000 تومان

خرید اشتراک افزودن به سبد خرید

خرید دانلودی فوری

در این روش نیاز به افزودن محصول به سبد خرید و تکمیل اطلاعات نیست و شما پس از وارد کردن ایمیل خود و طی کردن مراحل پرداخت لینک های دریافت محصولات را در ایمیل خود دریافت خواهید کرد.

تولید کننده: Udemy