خطة تعلم الذكاء الإصطناعي - الجزء الأول

Day 1

Linear Algebra (Vectors, Matrices, and Basic Operations)

Your task today is to understand the following basics:

• What are vectors and how are they mathematically represented.
• How to perform basic matrix operations (addition and multiplication).
• Practical examples of matrix-related operations.

Record a YouTube video that is public and accessible to everyone.

Explain what you learned today. Remember, teaching others helps you better understand the topic.

Don’t worry about mistakes; everyone learns from experience.

The goal is to provide the best explanation you can and improve day by day.

Write a daily report covering what you learned and the sources you used.

Attach the link to the video you recorded and send it via email to menna@gammal.tech.

Make sure the report includes the key points you explained in the video.

Day 2

Calculus (Derivatives, Gradients, and Partial Derivatives)

Your task today is to understand the following basics:

• What are derivatives and how they are used in AI.
• How to compute the gradient in multivariable functions.
• Understanding partial derivatives and how to calculate them.

Record a YouTube video that is public and accessible to everyone.

Explain what you learned today. Remember, teaching others helps you better understand the topic.

Don’t worry about mistakes; everyone learns from experience.

The goal is to provide the best explanation you can and improve day by day.

Write a daily report covering what you learned and the sources you used.

Attach the link to the video you recorded and send it via email to menna@gammal.tech.

Make sure the report includes the key points you explained in the video.

Day 3

Probability and Statistics (Distributions, Bayes' Theorem, and Variance)

Your task today is to understand the following basics:

• What are probability distributions and how they are used.
• Understanding Bayes' Theorem and its applications.
• Variance and how to calculate it in a dataset.

Record a YouTube video that is public and accessible to everyone.

Explain what you learned today. Remember, teaching others helps you better understand the topic.

Don’t worry about mistakes; everyone learns from experience.

The goal is to provide the best explanation you can and improve day by day.

Write a daily report covering what you learned and the sources you used.

Attach the link to the video you recorded and send it via email to menna@gammal.tech.

Make sure the report includes the key points you explained in the video.

Day 4

Python Programming (Basics and Essential Libraries)

Your task today is to understand the following basics:

• Introduction to Python and writing your first program.
• Understanding variables, conditionals, and loops.
• Getting familiar with essential libraries (e.g., NumPy and Pandas).

Record a YouTube video that is public and accessible to everyone.

Explain what you learned today. Remember, teaching others helps you better understand the topic.

Don’t worry about mistakes; everyone learns from experience.

The goal is to provide the best explanation you can and improve day by day.

Write a daily report covering what you learned and the sources you used.

Attach the link to the video you recorded and send it via email to menna@gammal.tech.

Make sure the report includes the key points you explained in the video.

Day 5

Python Programming (Data Handling with Pandas)

Your task today is to understand the following basics:

• How to create and manage DataFrames using the Pandas library.
• Performing simple statistical analysis on data.
• Cleaning data and handling missing values.

Record a YouTube video that is public and accessible to everyone.

Explain what you learned today. Remember, teaching others helps you better understand the topic.

Don’t worry about mistakes; everyone learns from experience.

The goal is to provide the best explanation you can and improve day by day.

Write a daily report covering what you learned and the sources you used.

Attach the link to the video you recorded and send it via email to menna@gammal.tech.

Make sure the report includes the key points you explained in the video.

Day 6

Python Libraries for Machine Learning (Introduction to Scikit-learn)

Your task today is to understand the following basics:

• Introduction to Scikit-learn and its role in machine learning.
• Understanding how to load and split data into training and test sets.
• Implementing a simple regression model using Scikit-learn.

Record a YouTube video that is public and accessible to everyone.

Explain what you learned today. Remember, teaching others helps you better understand the topic.

Don’t worry about mistakes; everyone learns from experience.

The goal is to provide the best explanation you can and improve day by day.

Write a daily report covering what you learned and the sources you used.

Attach the link to the video you recorded and send it via email to menna@gammal.tech.

Make sure the report includes the key points you explained in the video.

Day 7

Linear Regression Models Using Scikit-learn

Your task today is to understand the following basics:

• Introduction to linear regression models and their usage.
• Training a linear regression model using Scikit-learn.
• Understanding evaluation metrics for regression models such as R² and MSE.

Record a YouTube video that is public and accessible to everyone.

Explain what you learned today. Remember, teaching others helps you better understand the topic.

Don’t worry about mistakes; everyone learns from experience.

The goal is to provide the best explanation you can and improve day by day.

Write a daily report covering what you learned and the sources you used.

Attach the link to the video you recorded and send it via email to menna@gammal.tech.

Make sure the report includes the key points you explained in the video.

Day 8

Classification Models Using Scikit-learn (Introduction)

Your task today is to understand the following basics:

• Introduction to classification models like K-Nearest Neighbors (KNN).
• How to load a dataset, split it, and train a classification model using Scikit-learn.
• Understanding how to evaluate classification models using accuracy.

Record a YouTube video that is public and accessible to everyone.

Explain what you learned today. Remember, teaching others helps you better understand the topic.

Don’t worry about mistakes; everyone learns from experience.

The goal is to provide the best explanation you can and improve day by day.

Write a daily report covering what you learned and the sources you used.

Attach the link to the video you recorded and send it via email to menna@gammal.tech.

Make sure the report includes the key points you explained in the video.

Day 9

Deep Dive into Classification Models (Decision Tree) Using Scikit-learn

Your task today is to understand the following basics:

• Understanding the Decision Tree and its use in classification.
• Training a Decision Tree model using Scikit-learn.
• Evaluating model performance using accuracy and confusion matrix.

Record a YouTube video that is public and accessible to everyone.

Explain what you learned today. Remember, teaching others helps you better understand the topic.

Don’t worry about mistakes; everyone learns from experience.

The goal is to provide the best explanation you can and improve day by day.

Write a daily report covering what you learned and the sources you used.

Attach the link to the video you recorded and send it via email to menna@gammal.tech.

Make sure the report includes the key points you explained in the video.

Day 10

Introduction to Neural Networks Using TensorFlow

Your task today is to understand the following basics:

• Introduction to neural networks and how they work.
• Understanding the different layers in a neural network.
• Building a simple neural network using the TensorFlow library.

Record a YouTube video that is public and accessible to everyone.

Explain what you learned today. Remember, teaching others helps you better understand the topic.

Don’t worry about mistakes; everyone learns from experience.

The goal is to provide the best explanation you can and improve day by day.

Write a daily report covering what you learned and the sources you used.

Attach the link to the video you recorded and send it via email to menna@gammal.tech.

Make sure the report includes the key points you explained in the video.

Day 11

Deep Dive into Neural Networks (Feedforward Networks) Using TensorFlow

Your task today is to understand the following basics:

• Understanding how feedforward networks work.
• Implementing a feedforward network model using TensorFlow.
• Evaluating neural network performance using metrics like loss and accuracy.

Record a YouTube video that is public and accessible to everyone.

Explain what you learned today. Remember, teaching others helps you better understand the topic.

Don’t worry about mistakes; everyone learns from experience.

The goal is to provide the best explanation you can and improve day by day.

Write a daily report covering what you learned and the sources you used.

Attach the link to the video you recorded and send it via email to menna@gammal.tech.

Make sure the report includes the key points you explained in the video.

Day 12

Introduction to Convolutional Neural Networks (CNNs) Using TensorFlow

Your task today is to understand the following basics:

• What are Convolutional Neural Networks (CNNs) and their role in image processing.
• Understanding convolutional layers and how they work.
• Implementing a simple CNN model using TensorFlow.

Record a YouTube video that is public and accessible to everyone.

Explain what you learned today. Remember, teaching others helps you better understand the topic.

Don’t worry about mistakes; everyone learns from experience.

The goal is to provide the best explanation you can and improve day by day.

Write a daily report covering what you learned and the sources you used.

Attach the link to the video you recorded and send it via email to menna@gammal.tech.

Make sure the report includes the key points you explained in the video.

Day 13

Deep Dive into Convolutional Neural Networks (CNNs) Using TensorFlow

Your task today is to understand the following basics:

• Understanding the role of pooling layers in CNNs.
• Implementing a more complex CNN model using TensorFlow.
• Understanding how to optimize the model using techniques like Dropout.

Record a YouTube video that is public and accessible to everyone.

Explain what you learned today. Remember, teaching others helps you better understand the topic.

Don’t worry about mistakes; everyone learns from experience.

The goal is to provide the best explanation you can and improve day by day.

Write a daily report covering what you learned and the sources you used.

Attach the link to the video you recorded and send it via email to menna@gammal.tech.

Make sure the report includes the key points you explained in the video.

Day 14

Introduction to Recurrent Neural Networks (RNNs) Using TensorFlow

Your task today is to understand the following basics:

• What are Recurrent Neural Networks (RNNs) and when to use them.
• Understanding how to process sequential data using RNNs.
• Implementing a simple RNN model using TensorFlow.

Record a YouTube video that is public and accessible to everyone.

Explain what you learned today. Remember, teaching others helps you better understand the topic.

Don’t worry about mistakes; everyone learns from experience.

The goal is to provide the best explanation you can and improve day by day.

Write a daily report covering what you learned and the sources you used.

Attach the link to the video you recorded and send it via email to menna@gammal.tech.

Make sure the report includes the key points you explained in the video.