Artificial Intelligence Methods - Study Materials

This folder contains materials for studying Artificial Intelligence Methods at UAM. It includes tasks related to data preprocessing, various machine learning algorithms, and exercises.

Table of Contents

machine_learning_on_dataset - Final Project

• Data Preprocessing
• k-Nearest Neighbors (kNN)
• Support Vector Classification (SVC)
• Neural Network
• Random Forest Classifier
• Model Evaluation Metrics

Labs

lab 1 - Data Preprocessing & Intro to Charts

• Basics of data preprocessing
• Introduction to data visualization

lab 2 - Introduction to Scikit-Learn

• SVM Classifier
• Model evaluation metrics: Precision, Recall, AUC, Accuracy
• Standardization & Normalization
• Overfitting & Underfitting

lab 3 - Naïve Bayes & Regression

• Naïve Bayes Classifier
• Linear Regression
• Mean Squared Error (MSE) & Mean Absolute Error (MAE)

lab 4 - Clustering & Encoding

• k-Means Clustering
• One-Hot Encoding
• Agglomerative Clustering

lab 5 - Principal Component Analysis & TensorFlow

• Principal Component Analysis (PCA)
• Introduction to Keras & TensorFlow

lab 6 - Neural Networks & MNIST Dataset

• Working with the MNIST dataset
• Implementing Neural Networks

lab 7 - Training Optimization Techniques

• Training in batches
• Dropout & Regularization

lab 8 - Convolutional Neural Networks (CNN)

• MNIST dataset
• Layers: Dense, Dropout, Conv2D, MaxPooling2D, Flatten
• Data Augmentation

lab 9 - Model Training & Pretrained Models

• Data Augmentation
• ModelCheckpoint
• Reloading models
• Using pretrained models

lab 10 - Advanced Neural Networks

• Learning Rate Optimization
• Recurrent Neural Networks (RNN)
• Gated Recurrent Unit (GRU) & Long Short-Term Memory (LSTM)
• Reuters Newswire Dataset

---

This repository serves as a comprehensive resource for learning various AI and machine learning techniques through practical implementation.