BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.25.0//EN
X-ORIGINAL-URL:https://kenya.ai/
X-WR-CALNAME:Ai Kenya
X-WR-CALDESC:Democratizing machine intelligence
X-WR-TIMEZONE:UTC
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20260605T112928
END:STANDARD
END:VTIMEZONE
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-c6447300d99fdbf4f3f7966295b8b5be@kenya.ai
DTSTART;TZID=UTC:20190903T000000
DTEND;TZID=UTC:20190904T000000
DTSTAMP:20190903T114908Z
CREATED:20190903
LAST-MODIFIED:20191015
PRIORITY:5
SEQUENCE:0
TRANSP:OPAQUE
SUMMARY:Depth  First Learning Fellowship on Normalizing Flows with Variational Inference
DESCRIPTION:Depth First Learning ( http://depthfirstlearning.com/ ) is an initiative aiming to develop curricula leading to mastery of specific important papers in machine learning.  These curricula are developed by running online study groups via videoconferencing on the following topics.\n– Variational Inference with Normalizing Flows\n– Spherical CNNs\n– Stein Variational Gradient Descent\n– Resurrecting the sigmoid in deep learning through dynamical isometry\nAbout the Fellow\nDr Steve Kroon obtained MCom (Computer Science) and PhD (Mathematical Statistics) degrees while studying at Stellenbosch University. He joined the Stellenbosch University Computer Science department in 2008. His PhD thesis considered aspects of statistical learning theory, and his subsequent research has focused on decision making in artificial intelligence, including machine learning, reinforcement learning, and search techniques. He has supervised and co-supervised 5 graduated and 3 current master’s students, and has published 3 journal articles and 8 peer-reviewed conference and conference workshop articles. He has served as a reviewer for the journals Algorithmica, the Journal of Universal Computer Science, and the South African Computer Journal, as well as on the programme committee for 2 conferences. He holds a Diploma in Actuarial Techniques, and is a member of the Centre for Artificial Intelligence Research, the Institute of Electrical and Electronics Engineers (IEEE) and the IEEE Computational Intelligence Society, the International Computer Games Association, the South African Statistical Association, and the South African Institute for Computer Scientists and Information Technologists.\nProgramme\nI’ll be running a  curriculum (for 6 weeks, starting later this month) on normalizing flows with variational inference.  We would like to include people from Africa (especially beyond South Africa) in the group, so please sign up (by clicking the register button) if you’re interested.\nTime\nThere will be weekly videoconferencing sessions of 1.5 hours, so\nyou’ll need a fairly good internet connection.  Possible times, not\nyet finalized (please let me know in your email which ones you are\navailable for):\n(a) Mon 12:30-14:00 South Africa Time\n(b) Wed 12:30-14:00 South Africa Time\n(c) Wed 15:00-16:30 South Africa Time\nYou would need to commit around 6 hours per week for prescribed\nreading and exercises.\nRough prerequisites for the course:\n\nProgramming in Python and NumPy.  (Experience in a framework such as\nPyTorch or TensorFlow recommended – you will likely need to edit or\nwrite code in these.)\nBasic computer science: order complexity, DAGs\nVector calculus: gradient, Jacobian, convexity, Jensen’s inequality\nLinear algebra: rank, determinant\nBasic statistics: understand probability densities, joint and\nconditional distributions, change of variable formula, some common\ndistributions (Bernoulli, Categorical/multinoulli, binomial,\n(multivariate) Gaussian, Beta), maximum likelihood estimation\nBasics of neural networks, e.g. multi-layer perceptron, activation\nfunctions (ReLU/tanh), loss functions (squared error/cross-entropy),\nstochastic gradient descent, learning rate\nFamiliarity with LaTeX (for scribing notes from sessions)\n\n
URL:https://kenya.ai/events/depth-first-learning-fellowship-on-normalizing-flows-with-variational-inference/
ATTACH;FMTTYPE=image/png:https://kenya.ai/wp-content/uploads/2019/09/kroon.png
END:VEVENT
END:VCALENDAR