Karteikarten: Fundamentals of Artificial Intelligence and Machine Learning — 16 Karten

Artificial Intelligence — definition?

Simulation of human intelligence by machines.

AI history — starting point?

1956 Dartmouth Conference, McCarthy coined the term.

Narrow AI — role?

Performs specific tasks within limited domains.

General AI — capability?

Hypothetical AI with human-like cognitive abilities.

Machine Learning — definition?

Systems improving from data without explicit programming.

Difference: AI vs ML?

AI is broader; ML is a subset focused on learning from data.

Supervised Learning — data type?

Labeled data with input-output pairs.

Unsupervised Learning — goal?

Find patterns or structure in unlabeled data.

Deep Learning — key feature?

Uses multi-layer neural networks for complex pattern recognition.

Neural Network — element?

Interconnected neurons organized in layers.

Model evaluation — metric?

Accuracy measures correct predictions over total.

Overfitting — meaning?

Model learns noise, performs poorly on new data.

AI applications — example?

Healthcare, autonomous vehicles, NLP, finance.

Clustering — technique?

Groups data based on similarity without labels.

Activation function — purpose?

Introduces non-linearity into neural networks.

Model testing — purpose?

Assess performance on unseen data to ensure generalization.