Applied Machine Learning
Tillämpad Maskininlärning

EDAN95F, 7.5 högskolepoäng

Gäller från och med: Autumn 2018
Beslutad av: Professor Thomas Johansson
Datum för fastställande: 2018-10-15

Allmänna uppgifter

Avdelning: Computer Science (LTH)
Kurstyp: Gemensam kurs, avancerad nivå och forskarnivå
Kursen ges även på avancerad nivå med kurskoder: EDAN95, EDAN96
Undervisningsspråk: English

Syfte

To give an introduction to several subdomains of machine learning and to give an orientation about fundamental methods and algorithms within these domains. To convey knowledge about breadth and depth of the domain.

Mål

Kunskap och förståelse

För godkänd kurs skall doktoranden

• in an examination (oral or written) display basic knowledge concerning theories and methods related to the following subdomains:
• unsupervised and supervised learning, classification and regression
• neural networks, including convolutional neural networks, recurrent neural networks and deep learning
• bayesian learning
• reinforcement learning
• support vector machines, decision trees, random forests, ensemble methods

Färdighet och förmåga

För godkänd kurs skall doktoranden

• complete a number of assignments based on problems related to some of the previously mentioned subdomains and demonstrating the ability to:
• evaluate and prepare the data
• select and train a model
• evaluate the outcome and fine-tune the model

Värderingsförmåga och förhållningssätt

För godkänd kurs skall doktoranden

• * be able to judge suitability of a given machine learning method to a given problem,
• * understand limitations of applicability of machine learning methods

Kursinnehåll

* unsupervised and supervised learning, classification and regression * neural networks, including convolutional neural networks, recurrent neural networks and deep learning * bayesian learning * reinforcement learning * support vector machines, decision trees, random forests, ensemble methods * hardware and software architectures for machine learning, parallelisation, use of GPUs

Kurslitteratur

• Murphy, Kevin P.: Machine Learning, A Probabilistic Perspective.. ISBN 9780262018029.
• Goodfellow, I., Bengio, Y. & Courville, A.: Deep Learning. MIT Press, 2016. ISBN 9780262035613.
• Hands-On Machine Learning with Scikit-Learn and TensorFlow, Concepts, Tools, and Techniques to Build Intelligent Systems. ISBN 9781491962299.

Kursens undervisningsformer

Undervisningsformer: Föreläsningar, laborationer

Kursens examination

Examinationsform: Skriftlig tentamen. The written examination can be replaced by an oral exam given mutual agreement
Betygsskala: Underkänd, godkänd
Examinator: Senior lecturer Elin A. Topp

Antagningsuppgifter

Förutsatta förkunskaper: EDAA01 Programming - Second Course or similar

Kurstillfällesinformation

Startdatum: 2020-11-02
Slutdatum: 2020-12-31
Kursfart: Full time

Anmälningsinformation

contact the course responsible teacher (e-mail)

Kontaktinformation och övrigt

Kursansvarig: Elin A. Topp <elin_a.topp@cs.lth.se>
Hemsida: cs.lth.se/edan95
Övrig information: Procedures for handin-assignments and exercises for PhD students can be differing from those for undergraduate students and are subject to agreement with the course responsible teacher