Skip to content

IEEE-FCIH-SB/Machine-Learning-Content-2025

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

logo ieee (1)

๐Ÿš€ Machine Learning Content 2025 | IEEE FCIH

Welcome to the Machine Learning Content 2025 repository! This repo contains structured machine learning sessions designed for IEEE FCIH SB members, covering foundational to advanced ML topics with slides, code, and tasks.

๐Ÿ“Œ Goal: Provide a hands-on learning experience for students and enthusiasts in AI & Machine Learning.


๐Ÿ“… Sessions Overview

๐Ÿ“Œ Session Title ๐Ÿท๏ธ Tags ๐Ÿ“œ Slides ๐Ÿ’ป Code ๐ŸŽฏ Task
Session 1: Introduction to ML Intro to Machine Learning,Intro to AI, Supervised Learning , AI market, Python Slides Code Task
Session 2: Linear Algebra for ML Vectors, Linear Combinations, Linear Transformations, matrix multiplication, Norms, Norms and distance, Dot product, cosine similarity, Determinants Slides Code Task
Session 3: Calculus for ML Limits, Continuity, Differentiation, Numerical differentiation, Partial derivative, Chain rule, Gradient, Jacobian, Optimization, Gradient Ascent, Gradient Descent, learning rate effect Slides
๐Ÿ“บVideo
โœจGD visualisationโœจ
Code Task
Session 4: Statistics and visualisation Sampling, Bootsrapping, Measures of location, Measures of variation, Degree of freedom (DoF), Measures of position, Percentiles, Quartiles, Box plot, Outlier, Standard Scores, Standardization, conditional probability, Bayes' Theorem, probability mass function, Mathmatical expectation, Bernoulli distribution, Binomial distribution, Poisson distribution , Normal distribution, central limit theorem (CLT), likelihood, Maximum likelihood estimation MLE Slides
๐Ÿ“บVideo
code
๐Ÿ“บVideo
๐ŸšซNo task
Session 5: Exploratory Data Analysis (EDA) missing data, data skewness, outliers, plotting ๐Ÿšซ Code
Dataset
๐Ÿ“บVideo
๐Ÿ”œ
Session 6: Linear Regression regression,Linear regression, Loss function, Cost function, Mean Absolute Error (MAE), Mean Squared Error (MSE), residuals, Normal equation, Gradient descent, Stochastic Gradient Descent, mini-batch Gradient Descent, Polynomial regressions, Piecewise Linear Regression Slides Code Task
Session 7: Logistic Regression Classification, logistic function, sigmoid functions, Odds, logits, log loss, log likelihood, negative likelihood, Cross entropy, Newton method, polynomial regression Slides Code Task
Session 8: Decision Tree Generalization, Decision Tree Classifier, Decision Tree regressior, Cross validation, Grid search, Tree pruning, Feature importance Slides Code Task
Session 9: Ensembel Bootsrapping, Bagging, Boosting, stacking, Random Forest, Gradient Boosting, Ada Boosting Slides Code โž•Extra code ๐ŸšซNo task
Session 10: Unsupervised Learning K-means, Segmentation, PCA, ICA, Audio data, gradio Slides Code
๐Ÿ“บVideo
๐ŸšซNo task
Session 11: Artificial Neural Networks (ANN) Perceptron, Simple NN, Activation functions, Logistic, SoftMax, ReLU, Leaky ReLU, Tanh, Loss functions, backpropagation Slides Code ๐ŸšซNo task
Session 12: Convolutional Neural Networks (CNN) Convolution layer, Pooling layer, Fully connected layer, Dialation, LeNET, AlexNET, VGG16, VGG19, Pretraind-models, fine-tuning, Data Augmentation Slides
๐Ÿ“บVideo
Code ๐ŸšซNo task
Session 13: Sequence Modeling Sequence data, RNN, LSTM, GRU, Text data Slides
๐Ÿ“บVideo
Code
๐Ÿ“บVideo
๐ŸšซNo task
Session 14: Transformers Sequence data, Encoder-Decoder, BERT, BART, GPT, LLM, Attention Slides Code ๐ŸšซNo task

Members projects

The project, by a team of 2-3 members, included well-documented code, a 20-30 slide presentation, and a 5-10 minute explanatory video. It was deployed with an interactive GUI using tools like Gradio or Streamlit, and promoted on LinkedIn, GitHub, YouTube, and Kaggle. Key technical elements involved PCA for feature reduction, image segmentation for feature extraction, and model evaluation using metrics like Accuracy and Precision. Hyperparameter tuning was done via k-fold cross-validation and grid search to optimize performance.

๐ŸŽฏ Featured Projects

๐Ÿ“น Video Coming Soon

๐ŸคŸ Arabic Sign Language Dataset 2022

GitHub

๐Ÿ’ณ Credit Card Fraud Detection

๐Ÿ’ณ Credit Card Fraud Detection

GitHub

Fashion-MNIST

๐Ÿ‘— Fashion-MNIST

GitHub

๐Ÿคฒ Sign Language MNIST

๐Ÿคฒ Sign Language MNIST

GitHub

๐Ÿ“น Video Coming Soon

๐Ÿฆ IEEE-CIS Fraud Detection

GitHub

House Prices Prediction

๐Ÿ  House Prices Prediction

GitHub

NYC Taxi Trip Duration

๐Ÿš• NYC Taxi Trip Duration

GitHub

NYC Taxi Trip Duration

๐ŸŒ… Day & Night Classification

GitHub


๐Ÿ‘จโ€๐Ÿ’ป Instructors

๐Ÿ‘จโ€๐Ÿ’ป Ziad Waleed - Vice Director

๐Ÿ‘จโ€๐Ÿ’ป Mario Mamdouh - Vice Director


๐ŸŒŽ Connect with IEEE FCIH SB

Stay updated with our latest events and activities!

๐Ÿ“Œ Join us and be part of an amazing learning experience! ๐Ÿš€
โœจ Enjoy Learning & Keep Exploring AI! โœจ