Interactive lessons to learn artificial intelligence step by step
What is AI? Types of AI (symbolic, machine learning, deep learning). Overview of ML lifecycle: data → model → evaluation → deployment.
The AI workflow. Data cleaning, preprocessing, and visualization. Basics of pandas, matplotlib, seaborn.
Supervised vs unsupervised learning. Regression and classification. Train/test split, cross-validation.
Perceptron, feedforward networks. Intro to PyTorch. Training loops, loss functions, optimizers.
From Bag-of-Words to embeddings. Word2Vec, GloVe, and modern embeddings. Tokenization, sequence modeling.
What are transformers? Attention mechanism explained simply. Evolution: from RNN → LSTM → Transformer → GPT.
Zero-shot, few-shot, and chain-of-thought prompting. Prompt engineering strategies. Fine-tuning vs. LoRA vs. adapters.
Bias, fairness, misinformation, and AI safety. Data privacy, copyright, and model misuse.
How Kaggle works: notebooks, datasets, leaderboards. Strategies for feature engineering and model improvement.
Work in groups on Kaggle competition entry or mini-LLM app (chatbot, summarizer, tutor bot).
Continue team projects. Build LLM-based applications or improve Kaggle competition entries.
Present Kaggle results and LLM applications. Explore careers in AI and continued learning paths.