Teknologiseminar

From Robin

Revision as of 10:10, 17 April 2020 (view source) Frankvee (Talk | contribs) (→Dates and subjects - Spring 2020 – Thursdays 12:00-12:30/13:00) ← Older edit		Revision as of 09:12, 3 June 2020 (view source) Frankvee (Talk | contribs) (→Dates and subjects - Spring 2020 – Thursdays 12:00-12:30/13:00) Newer edit →
Line 27:		Line 27:
	|-		|-
	|  07.05    || Round table ||		|  07.05    || Round table ||
		+	|-
		+	|  21.05    || Fabio Massimo Zennaro || Information Bottleneck
		+	|-
		+	|  28.05    || Round table ||
		+	|-
		+	|  04.06    || Round table ||
		+	|-
		+	|  11.06    || Anders Elovsson || Introduction to own research
		+	|-
		+	|  18.06    || Jendrik || Modeling models with model-based models
	|-		|-
	|}		|}

---

Revision as of 09:12, 3 June 2020

Meeting structure

Place: ROBIN pause area, 4th floor Ole-Johan Dahls hus

12:00-12:15 Brief exchange of recent news, plans etc.

12:15-13:00 Technology / Own Research / Journal review (see guidelines), including discussion

Dates and subjects - Spring 2020 – Thursdays 12:00-12:30/13:00

5-10 min housekeeping updates + talks/roundtable

When	Who	Content (title and type (tech/res/review)
24.01	Jendrik Seipp	Introduction and own research
14.02	Chloe Barnes	Introduction and own research
21.02 28.02	Seyed Mojtaba Karbasi	Introduction and own research
20.03	Tønnes Nygaard	Bias and discrimination in machine learning
03.04	Vegard Søyseth	Robin's laboratories
23.04	Ulysse Côté-Allard	Introduction and own research
30.04	Hoang Minh Pham	Introduction and own research
07.05	Round table
21.05	Fabio Massimo Zennaro	Information Bottleneck
28.05	Round table
04.06	Round table
11.06	Anders Elovsson	Introduction to own research
18.06	Jendrik	Modeling models with model-based models

Overview of earlier seminars

Examples of interesting topics for technology introduction

Feel free to add topics to the wishlist!

• Robotics
  • Reinforcement learning for robotics
  • SLAM
  • embodied cognition
  • Swarm

• Neural networks
  • Recursive NNs and LSTMs
  • NEAT / HyperNEAT
  • Deep NNs

• Evolutionary algorithms and other types of optimization
  • Performance comparison of EAs (statistical tests)
  • Differential evolution
  • Diversity preservation methods
  • Novelty search, MAP-Elites and variants
  • Bayesian optimization

• Tools
  • R
  • Python as alternative to R, incl. matplotlib
  • ROS
  • Deep learning frameworks and practice