1. Supervised vs Unsupervised Learning - The model is trained on labeled data. It learns to map inputs to known outputs. Predicting house prices based on features like size and location. The model works on unlabeled data, finding patterns or clusters.
2. Neural Networks & Deep Learning - Algorithms inspired by the human brain, composed of layers of nodes (neurons) that process data. Neural networks with many layers capable of learning complex patterns. Image recognition, natural language processing, speech recognition.
3. Overfitting & Underfitting - Model performs well on training data but poorly on unseen data. It has “memorized” the data. Model is too simple and fails to capture underlying patterns in the data. Achieve a balance for good generalization.
4. Feature Engineering - The process of selecting, creating, and transforming variables (features) to improve model performance. Good features can drastically improve results, sometimes more than complex models. Converting timestamps into day-of-week or hour-of-day features for better predictions.
5. Reinforcement Learning - A learning approach where an agent learns by interacting with an environment and receiving rewards or penalties. Training an AI to play chess or optimize robotic movements. Focuses on decision-making over time rather than predicting outputs directly.
Phone - +65 66018888
Email - [email protected]
Address - Block AS8, 10 Kent Ridge Crescent, #03-01 Singapore 119260
Visit - https://scale.nus.edu.sg/pr ...