Beskrivelse
Grunnleggende om maskinlæring; multilags perceptron, universal approximation theorem, back‑propagation; konvolusjonsnettverk, rekurrente nevrale nettverk, variational auto‑encoder, generative adversarial networks; komponenter og teknikker i dyp læring; Markov Decision Process; Bellman‑likningen, policy iteration, value iteration, Monte‑Carlo‑læring, temporal difference‑metoder, Q‑learning, SARSA, anvendelser.
Referansetekst i originalspråket
Fundamentals of machine learning; multi-layer perceptron, universal approximation theorem, back-propagation; convolutional networks, recurrent neural networks, variational auto-encoder, generative adversarial networks; components and techniques in deep learning; Markov Decision Process; Bellman equation, policy iteration, value iteration, Monte-Carlo learning, temporal difference methods, Q learning, SARSA, applications.
Kilder og referanser
Datoer og kilder beholdes for å hjelpe deg å verifisere opplysningene. Oversettelsene tilbys for å lette lesing; den offisielle kilden er referansen for krav og betingelser.
Kildereferanse : https://calendar.carleton.ca/grad/courses/COMP/