Neural Networks

Uitgebreide vaknaam	Neural Networks
Leerdoelen	At the end of this course, the student: 1) is aware of the interdisciplinary diversity of neural network modeling approaches in the wider neural, cognitive and information processing sciences 2) can practically use feedforward neural networks in machine learning applications 3) understands elementary mathematical formalism to capture dynamical and stochastic phenomena in recurrent neural networks 4) has an orientation in the wider research landscape of NNs which enables him/her to approach research fields adjacent to AI / machine learning, in particular computational neuroscience, theoretical physics / complex systems and neuromorphic microchip technologies
Omschrijving	"Neural Networks" (NN) is an umbrella term for models of distributed, parallel information processing. In all NN models, a (large) number of "neurons" interact by spreading out activation patterns along "synaptic" connections which can be shaped by learning mechanisms. This general scheme has been worked out into an enormous variety of concrete models in a diversity of scientific disciplines and application scenarios. This course gives an introduction to a choice of NN specimen which together illustrate the powers of NN models as an integrative link between AI, machine learning, computational neuroscience, theoretical physics and – since a few years increasing in importance – microchip technologies and material science. Concretely, the following topics will be treated: • A very fast rehearsal of machine learning basics: overfitting, regularization, cross-validation • Classical perceptrons, multilayer perceptrons, and a glance at deep feedforward networks, including CNNs and autoencoders • An analysis of computational challenges inherent in the standard "backpropagation" algorithm • Since most NNs to be presented in this course are recurrent neural networks (RNNs), and RNNs are dynamical systems, a crash course on dynamical systems will be inserted • LSTM and other gated networks for "deep" learning of temporal data; backpropagation through time algorithm • Hopfield networks – the classical NN model of neural memory and pattern completion • Boltzmann machines and restricted Boltzmann machines – the most mathematically transparent model of universal learning algorithms, and the kickoff trigger for deep learning. This part of the course includes an introduction to sampling methods and simulated annealing. • Reservoir computing • An introduction to "neuromorphic computing", an emergent field between NNs, microchip fabrication and material science, of particular interest in Groningen because this is the core research theme of our CogniGron research center
Uren per week
Onderwijsvorm	Hoorcollege (LC), Opdracht (ASM), Practisch werk (PRC), Werkcollege (T)
Toetsvorm	Schriftelijk tentamen (WE), Verslag (R) (The final grade is based on the written exam (50%) and the project report (50%). The grade of the exam needs to be higher or equal to 5.0 in order to pass this course.)
Vaksoort	bachelor
Coördinator	Prof. Dr. H. Jaeger
Docent(en)	Prof. Dr. H. Jaeger
Verplichte literatuur	Titel Auteur ISBN Prijs Detailed 220 pp lecture notes, online via Nestor and public on homepage of 1rst instructor prof. dr. H. Jaeger
Entreevoorwaarden	Mandatory: Calculus for AI (WBAI048-05), Linear Algebra and Multivariable Calculus (WBAI050-05). If the mandatory requirements are not met, only the Board of Examiners of the AI BSc may grant an exemption. Exchange students are assumed to have gone through this through their Learning Agreement; pre-master's students through the Board of Admissions - other external students are judged case-by-case.
Opmerkingen	Artificial Intelligence (BSc) is a Fixed Quota (Numerus Fixus) programme. As a consequence, their courses (course code WBAI) are closed for students that are not registered under the AI BSc programme, unless the course is part of the mandatory curriculum of their programme. If you wish to take this course in your minor – or as part of a so-called ‘unofficial’ pre-master’s – please use the official procedure through the Board of Examiners form.
Opgenomen in	Opleiding Jaar Periode Type BSc Courses for Exchange Students: AI - Computing Science - Mathematics - semester II b BSc Kunstmatige Intelligentie 2 semester II b verplicht Pre-master/Fast-track for MSc AI - CCS – CS - Math  (Artificial Intelligence) - semester II b -