نحو جيل عربي من بناة التكنولوجيا

Lecture 1

• Terms, Features, Classes & Matrix Operations

Lecture 2

• Statistics and Probability for Machine Learning

Coding Exercise 1

• Introduction to Python for Machine and Deep Learning

Lecture 3

• Introduction to Python

Lecture 4

• Linear & Polynomial Regression and solving general problems

Lecture 5

• Gradient Descent variations & other optimizers (Momentum, RMS Prop & ADAM)

Coding Exercise 2

• NumPy, Vectorization, Data Visualization & OOP

Lecture 6

• Vectorization, Data Visualization and OOP Walkthrough

Lecture 7

• Perceptron and Adaline

Lecture 8

• Logistic Regression, Multilayer perceptron (MLP), Deep Nets

Coding Exercise 3

• Regression on real data (+20,000 houses info.) and Optimizers

Lecture 9

• Pre-processing (handling missing values, outliers, z-scoring) & Cross validation

Lecture 10

• Overfitting, Covariate shifts, Multicollinearity, Regularization, LR schedulers

Coding Exercise 4

• Classification with Perceptron, Adaline, logistic & DeepNNs on real data

Lecture 11

• Evaluation Metrics (MSE, Confusion matrix etc.) & Hypothesis Testing (ttest, etc.)

Lecture 12

• Dimensionality Reduction (PCA etc.), Feature Selection (SFS), Autoencoders

Coding Exercise 5

• Pre-processing, Multicollinearity, Cross-validation, Covariate shifts, LR schedulers

Lecture 13

• الخروج من الـ Notebooks واستخدام VS Code

Lecture 14

• Full Pipeline: من مشكلة واقعية في شركة إلى حل بإستخدام التعلم العميق

Lecture 15

• Probability, Bayesian thinking, the probabilistic approach to machine learning

Lecture 16

• Probabilistic Machine Learning, How to create cost functions, Entropy

Coding Exercise 6

• Probabilistic Machine Learning: Practice

Lecture 17

• Sequential Data, Recurrent Neural Networks (RNNs), Next Word Prediction

Lecture 18

• GRU, LSTM, Bidirectional RNN, Word Embedding

Lecture 19

• Learning Embeddings, Word2vec, Skip Gram, Negative Sampling, GloVe

Coding Exercise 7

• Sequence Models on text data: Spam Classification, NER (Vanilla RNN → GRU → LSTM → BiLSTM)

Lecture 20

• The Attention Mechanism, Transformers, BERT, GPT

Coding Exercise 8

• Attention, Transformers (News classification and Person NER, Many-to-One and Many-to-Many)

Lecture 21

• Diffusion Models

Lecture 22

• Research papers: DDPM, Improved DDPM, Stable Diffusion, Contrastive Learning

Coding Exercise 9

• Diffusion Models Projects (Super-resolution to enhance image quality, colouring black&white images)

Lecture 23

• Image Processing To CNNs: CNN Architectures (LeNet-5, AlexNet, VGG, Inception)

Lecture 24

• YOLO, Object Tracking, U-Net, ResNets, Augmentation

Coding Exercise 10

• CNNs, Transfer Learning, Augmentation, YOLO on custom data

Lecture 25

• Building And Serving Machine Learning Systems

Lecture 26

• AI-powered Chatbot Website And Mobile App on Custom Data, Part 1 (RAG)

Lecture 27

• AI-powered Chatbot Website And Mobile App on Custom Data, Part 2 (Fine-tuning)

Material

• Building and Deploying AI Projects (Slides)

Material

• Flask Code

Material

• AI Chatbot (Mobile App and Website) with Gemini API

Material

• Shawkat, Our AI Chatbot on custom data (Mobile App and Website)

Material

• Custom Phi3 Model on Custom data (people info extraction)

Material

• RAG Example and Our Custom Course Assistant Chatbot

Material

• Fine-Tuning with Our Custom Course Assistant Chatbot

Lecture 35

• Predicting Emotions During Sleep Using Brain Waves (Data and Theory), Kaggle

Lecture 36

• Full Analysis Pipeline Explanation, Starter Notebook for Competition

Material

• Link to Competition

Material

• Access to Our Exclusive Q&A and Discussion Group

Material

• Slides From All Lectures