[WIP] Create final exam Jupyter notebook for Deep Learning

[Copilot]

Plan: Create Deep Learning Final Exam Notebook

• Explore repository structure
• Review source notebook (NB-computer_vision_intro.ipynb)
• Understand content topics and structure
• Create dl-final_exam.ipynb with proper structure
• Add Part 1: Multiple Choice Questions (10 questions)
• Add Part 2: Short Answer Questions (10 questions)
• Add Part 3: Descriptive Questions (10 questions)
• Ensure all questions are based on source notebook topics
• Include answer keys and explanations
• Validate notebook format and structure

Original prompt

Create a new Jupyter notebook file named notebooks/dl-final_exam.ipynb in the codingalzi/dlp2 repository.

This notebook will serve as a final exam based on the content of notebooks/NB-computer_vision_intro.ipynb.
The structure of the notebook should include the following sections:

Deep Learning Final Exam

This exam covers the material from the "Introduction to Computer Vision" notebook (NB-computer_vision_intro.ipynb).

---

Part 1: Multiple Choice Questions (10 Questions)

Instructions: Choose the best answer for each question. (Concept-focused)

[Generate 10 multiple-choice questions with 5 options each. Include the question, options, correct answer, and a brief explanation for each.]

---

Part 2: Short Answer Questions (10 Questions)

Instructions: Provide a concise answer for each question. (Concept and code understanding)

[Generate 10 short-answer questions. Include the question, the expected answer, and a brief explanation/context.]

---

Part 3: Descriptive Questions (10 Questions)

Instructions: Explain the concepts or code logic in detail. (Concept and code understanding)

[Generate 10 descriptive/essay questions. Include the question and a sample model answer/explanation.]

---

Content Source:
The questions should be derived from the topics covered in notebooks/NB-computer_vision_intro.ipynb, which includes:

• Introduction to Convolutional Neural Networks (CNNs)
• Conv2D and MaxPooling2D layers
• Padding and Strides
• GlobalAveragePooling2D
• Training a CNN on MNIST
• The relevance of deep learning for small-data problems
• Data preprocessing (image_dataset_from_directory)
• TensorFlow Dataset objects
• Data augmentation

Formatting:

• Use Markdown cells for questions and text.
• You may use code cells if necessary to show code snippets for questions, but the primary format for the exam text should be Markdown.
• clearly label each section.
• Provide the "Answer Key" or "Solutions" within the same notebook, perhaps at the bottom or hidden in collapsible cells if possible, or just listed after each question block for study purposes (as requested: "Include correct answers and brief explanations").

Note: The user referenced a file dl-midterm_exam_final.ipynb for formatting style, but I do not have access to that specific file in the provided context. I will use a standard, clean, and well-structured Jupyter Notebook format that effectively presents the exam questions and answers.

This pull request was created as a result of the following prompt from Copilot chat.

Create a new Jupyter notebook file named notebooks/dl-final_exam.ipynb in the codingalzi/dlp2 repository.

This notebook will serve as a final exam based on the content of notebooks/NB-computer_vision_intro.ipynb.
The structure of the notebook should include the following sections:

Deep Learning Final Exam

This exam covers the material from the "Introduction to Computer Vision" notebook (NB-computer_vision_intro.ipynb).

---

Part 1: Multiple Choice Questions (10 Questions)

Instructions: Choose the best answer for each question. (Concept-focused)

[Generate 10 multiple-choice questions with 5 options each. Include the question, options, correct answer, and a brief explanation for each.]

---

Part 2: Short Answer Questions (10 Questions)

Instructions: Provide a concise answer for each question. (Concept and code understanding)

[Generate 10 short-answer questions. Include the question, the expected answer, and a brief explanation/context.]

---

Part 3: Descriptive Questions (10 Questions)

Instructions: Explain the concepts or code logic in detail. (Concept and code understanding)

[Generate 10 descriptive/essay questions. Include the question and a sample model answer/explanation.]

---

Content Source:
The questions should be derived from the topics covered in notebooks/NB-computer_vision_intro.ipynb, which includes:

• Introduction to Convolutional Neural Networks (CNNs)
• Conv2D and MaxPooling2D layers
• Padding and Strides
• GlobalAveragePooling2D
• Training a CNN on MNIST
• The relevance of deep learning for small-data problems
• Data preprocessing (image_dataset_from_directory)
• TensorFlow Dataset objects
• Data augmentation

Formatting:

• Use Markdown cells for questions and text.
• You may use code cells if necessary to show code snippets for questions, but the primary format for the exam text should be Markdown.
• clearly label each section.
• Provide the "Answer Key" or "Solutions" within the same notebook, perhaps at the bottom or hidden in collapsible cells if possible, or just listed after each question block for study purposes (as requested: "Include correct answers and brief explanations").

Note: The user referenced a file dl-midterm_exam_final.ipynb for formatting style, but I do not have access to that specific file in the provided context. I will use a standard, clean, and well-structured Jupyter Notebook format that effectively presents the exam questions and answers.

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.