[f(k)] Fw: Tommi Kärkkäinen: About machine learning methods: A quest for simplicity and transparency, in the physics colloquium on Friday

[Antero Voutilainen]

Perjantaina taas kollokviopuhe!

~ Antero Voutilainen

------ Forwarded Message --------
From: Tero Tapio Heikkilä <tero.t.heikkila at jyu.fi>
Date: 11.3.2024 8.33.36
Subject: Tommi Kärkkäinen: About machine learning methods: A quest for simplicity and transparency, in the physics colloquium on FridayWelcome to the University of Jyväskylä physics colloquium. 

On Friday 15th March at 10 am in FYS1 and Zoom [https://jyufi.zoom.us/j/66703175507] (passcode 890524):
Tommi Kärkkäinen, University of Jyväskylä
About machine learning methods: A quest for simplicity and transparency
Types of data-driven machine learning consist of supervised, unsupervised, and reinforcement learning methods. Here, I will discuss unsupervised and supervised methods, which have provided excellent results in various applications. The amazing results, however, might be difficult to reproduce. In fact, there are many aspects in relation to especially currently popular deep learning techniques which makes their use complicated and nontransparent. Surprisingly, by imitating classical linear regression, simple but yet powerful machine learning approaches can be derived. In this presentation, I will present and exemplify these techniques and some of their background in the context of monolayer-protected clusters.
Welcome!
Coffee will be served in the lobby. Although on-site attendance is the preferred option, you can also join via Zoom. Please do not send chat messages in Zoom during the talk, except if you need to tell about a muted speaker.

Confirmed colloquium talks in the Spring 2024 (you are welcome to suggest more - there are still open slots):
5.4. Heikki Mäntysaari (JYU): TBA
12.4. Sebastian Bergeret (San Sebastian): Superconducting spintronics
Tero & Iain

-- Tero Heikkilä Professor, Department of Physics University of Jyväskylä
[65301ef2-cf3a-47fb-b75e-6fa13d159792]
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.jyu.fi/pipermail/fyysikkokerho/attachments/20240312/031dd9e2/attachment.html>