Artificial Intelligence

Supervised Learning: regression, classification, decision trees, random forests, SVM

Unsupervised Learning: clustering (K-Means, hierarchical), dimensionality reduction (PCA)

Model evaluation: accuracy, precision, recall, F1 score, confusion matrix

Bias & variance, overfitting vs underfitting

Feature engineering and data preprocessing

Neural Network Basics: perceptron, activation functions, backpropagation

Multi-Layer Perceptrons (MLP)

Convolutional Neural Networks (CNN) for image tasks

Recurrent Neural Networks (RNN), LSTM for sequential data

Regularization: dropout, batch normalization

Computer Vision: image classification, object detection (YOLO basics), image segmentation

Natural Language Processing (NLP): text preprocessing, sentiment analysis, word embeddings, introduction to transformers

Generative AI: GANs basics, introduction to diffusion models

Reinforcement Learning (Intro): agents, environment, reward system.

Model deployment with Flask / FastAPI

APIs for AI integration

Basics of Docker and containerization for AI models

Cloud deployment (AWS SageMaker, GCP AI Platform, Azure ML)

Edge AI basics (AI on mobile & IoT devices)

AI Ethics: bias, fairness, privacy, transparency

Responsible AI practices in engineering projects

Large Language Models (LLMs) & Prompt Engineering

AI in Robotics & IoT

Research directions: self-supervised learning, graph neural networks, quantum AI (intro)