Fra Robin

Revisjon per 3. okt 2022 kl. 11:10 av Farzanmn (Diskusjon | bidrag)
Gå til: navigasjon, søk

Meeting structure

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

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

~12:20-12:35 Presentation on: Technology / Own Research / Journal review (see guidelines), time excludes discussion

Whatever content you present, remember that some of those attending have no advance knowledge about your project or work so introduce it in the beginning and stay focused on the main issues/challenges etc. Thus, make your presentation simple and understandable for as many as possible.

Dates and subjects - Autumn 2022 – Thursdays 12:00-12:45

5-20 min housekeeping/updates + 15 min talk

When What Who
25.08 Research work Renan Maffei, Bjørn Thor Jonsson [1],

Ivar-Kristian Waarum [2], Shin Watanabe [3]

01.09 Making Accelerators Smart: Applications of Deep Learning in High-Energy Physics Mateusz Wasiluk
08.09 Cubing Sound: Exploring Gestural-based New Musical Instrument in Head-mounted Augmented Reality Yichen Wang [4]
15.09 No presentation / Casual meeting └[∵┌]└[ ∵ ]┘[┐∵]┘
22.09 Planning for human robot interaction in the real world Shin Watanabe [5]
29.09 Guest lecture: Creative Computing on the BBC Microbit with Bare-Metal ARM Assembly Charles Martin (former ROBIN postdoc)
06.10 Julian?
13.10 Automatic/semiautomatic/interactive robotic dance choreography Mats Høvin
20.10 Marieke?
27.10 TBD Mojtaba
03.11 Visit by journalist from Titan.uio.no for mutual interaction Elina Melteig
10.11 TBD Farzan M. Noori
17.11 TBD Ulysse Côté-Allard
24.11 TBD Adel
01.12 A Unity ML Agents Simulation Journey Frank Veenstra
08.12 Kyrre?
15.12 Tom? or I:RIS master students

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
    • SLURM
    • R
    • Python as alternative to R, incl. matplotlib
    • ROS
    • Deep learning frameworks and practice
    • Unity ML agents
Personlige verktøy