دوره کاربردی مقدماتی هوش مصنوعی – (AI-ML)

Module 1: Data Preparation and Preprocessing

Data Cleaning and Exploration

Handling Missing Values

Exploratory Data Analysis

Data Transformation Techniques

Feature Engineering and Scaling

Encoding Categorical Variables

Feature Scaling and Normalization

Dimensionality Reduction Techniques (PCA, LDA)

Module 2: Supervised Learning Models

Regression Analysis

Linear Regression

Logistic Regression

Model Evaluation Metrics

Classification Algorithms

Decision Trees and Random Forests

Support Vector Machines (SVM)

K-Nearest Neighbors (KNN)

Performance Metrics (Confusion Matrix, ROC-AUC)

Module 3: Unsupervised Learning Models

Clustering Techniques

K-Means Clustering

Hierarchical Clustering

DBSCAN

Dimensionality Reduction

Principal Component Analysis (PCA)

t-SNE for Visualization

Feature Importance Analysis

Module 4: Model Selection and Hyperparameter Tuning

Model Selection Techniques

Cross-Validation

Bias-Variance Tradeoff

Learning and Validation Curves

Hyperparameter Tuning

Grid Search and Randomized Search

Successive Halving for Efficient Search

Evaluation Metrics and Model Comparison

Module 5: Ensemble Learning Methods

Introduction to Ensemble Learning

Bagging and Bootstrap Aggregating

Boosting (AdaBoost, Gradient Boosting)

Stacking and Voting Classifiers

Implementing Random Forests and XGBoost

Module 6: Deep Learning Basics with TensorFlow

Introduction to Deep Learning

Understanding Neural Networks

Backpropagation and Gradient Descent

Getting Started with PyTorch

Creating Tensors and Performing Operations

Building Simple Neural Networks

Training and Evaluating Models in TensorFlow

Module 7: Deep Learning Basics with PyTorch

Introduction to Deep Learning

Understanding Neural Networks

Backpropagation and Gradient Descent

Getting Started with PyTorch

Creating Tensors and Performing Operations

Building Simple Neural Networks

Training and Evaluating Models in PyTorch

Module 8: Convolutional Neural Networks (CNNs)

Building and Training CNNs

Layers in CNNs: Convolution, Pooling, and Fully Connected

Implementing CNNs for Image Classification

Data Augmentation and Regularization Techniques

Module 9: Recurrent Neural Networks (RNNs) and Sequential Data

Introduction to RNNs

Sequence Data and Time-Series Analysis

Implementing RNNs for Text and Sequence Data

Advanced Architectures: LSTMs and GRUs

Module 10: Advanced Deep Learning Architectures and Transfer Learning

Advanced Architectures

Transformers and Attention Mechanisms for NLP

GANs (Generative Adversarial Networks) for Data Generation

Transfer Learning

Fine-Tuning Pre-trained Models

Applications in Real-World Projects

Module 11: Real-World Applications and Case Studies

Applying Machine Learning to Real-World Problems

Sentiment Analysis (NLP)

Image Classification

Time Series Forecasting

Predictive Maintenance and Fraud Detection

Module 12: Project Development Workflow and Best Practices

End-to-End Machine Learning Projects

Problem Formulation and Data Collection

Model Selection and Training

Evaluation and Hyperparameter Tuning

Model Deployment and Monitoring

Module 13: Capstone Project

Project Proposal and Development

Students propose and implement a machine learning project of their choice.

Projects must include data preprocessing, model training, evaluation, and deployment.

Final Presentation and Evaluation