Master programming syntax, solve interactive challenges & run live code in Syntaxis Explore Arena →

menu_book Course Curriculum (Artificial Intelligence Fundamentals) expand_more

AI Concepts

Artificial intelligence definition Narrow AI General AI concept Machine learning relationship Deep learning relationship Symbolic AI Expert systems Search and planning Knowledge representation Probabilistic reasoning

Data & Features

Training data Validation data Test data Features Labels Feature engineering Normalization Standardization Categorical encoding Missing data

Learning Types

Supervised learning Unsupervised learning Semi-supervised learning Self-supervised learning Reinforcement learning Classification Regression Clustering Dimensionality reduction Anomaly detection

Model Training

Objective function Loss function Gradient descent Learning rate Epochs Batch size Overfitting Underfitting Regularization Early stopping

Evaluation

Accuracy Precision Recall F1 score Confusion matrix ROC AUC Mean absolute error Mean squared error Cross-validation Baseline model

Neural Networks

Neuron model Activation functions Hidden layers Forward propagation Backpropagation Weight initialization Dropout Convolutional networks Recurrent networks Transformers

Responsible AI

Bias in data Fairness metrics Privacy Explainability Transparency Human oversight Robustness Adversarial examples Data leakage Model cards

Applied AI

Recommendation systems Natural language processing Computer vision Speech recognition Time-series forecasting Generative models Embeddings Vector search Retrieval augmented generation AI system monitoring

Artificial Intelligence Fundamentals / Learning Types

Reinforcement learning

Learn Reinforcement learning in AI Fundamentals with a dedicated explanation, topic-specific example, edge guidance, and mastery check.

12 min read • Beginner

ai-fundamentals-025.py

py

q[state, action] += alpha * (reward + gamma * max_q(next_state) - q[state, action])

What to watch

Content source & attribution

Original Syntaxis Content · Original Syntaxis Content

Lesson quizzes

Reinforcement learning Mastery Check →

Self-supervised learning