home.social

#learns — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #learns, aggregated by home.social.

fetched live
  1. RE: zpravobot.news/@Rainmaker1973/

    Great #video about #learningbehavior in #hymenopterans, so it's about clever insects. #Intelligence isn't limited to specific animal groups. The kind of intelligence that provides an #evolutionaryadvantage can occur in a wide variety of taxa, for example, in #bumblebees. Using a species of the genus #Bombus (apparently B. hypnorum), the video illustrates the speed of learning in the #queen, who #learns to operate an artificial, flap-like #closure at her #nestentrance.
    © this text #StefanFWirth

  2. There’s more to #development than #money…Think of how a #child develops. #Learns to walk, talk. Grows up. Gets a bit smarter every day.
    That’s development too. It’s time for Kinton Bay to grow up. Get smarter and acknowledge its #violent beginnings.

    Petronella McGovern, The Liars

    #quote #quotes

  3. 'Generalization on the Unseen, Logic Reasoning and Degree Curriculum', by Emmanuel Abbe, Samy Bengio, Aryo Lotfi, Kevin Rizk.

    jmlr.org/papers/v25/24-0220.ht

    #sparse #learns #generalization

  4. 'Value-Distributional Model-Based Reinforcement Learning', by Carlos E. Luis, Alessandro G. Bottero, Julia Vinogradska, Felix Berkenkamp, Jan Peters.

    jmlr.org/papers/v25/23-0913.ht

    #reinforcement #quantile #learns

  5. 'Decomposed Linear Dynamical Systems (dLDS) for learning the latent components of neural dynamics', by Noga Mudrik, Yenho Chen, Eva Yezerets, Christopher J. Rozell, Adam S. Charles.

    jmlr.org/papers/v25/23-0777.ht

    #dynamical #dynamics #learns

  6. Representations and Computations in Transformers that Support Generalization on Structured Tasks

    Yuxuan Li, James McClelland

    Action editor: Stefan Lee.

    openreview.net/forum?id=oFC2LA

    #attention #learns #representations

  7. FairGrad: Fairness Aware Gradient Descent

    Gaurav Maheshwari, Michaël Perrot

    Action editor: Novi Quadrianto.

    openreview.net/forum?id=0f8tU3

    #fairness #fairgrad #learns

  8. #AI Is a Lot of Work. As the technology becomes #ubiquitous, a vast #tasker #underclass is emerging and not going anywhere. #AI #learns by finding #patterns in enormous quantities of #data, but first that data has to be sorted, #tagged by people, a vast #workforce mostly hidden behind machines. It’s difficult and #repetitive work. A several-second blip of footage took eight hours to annotate, for which a college graduate in #Nairobi was paid about $10. theverge.com/features/23764584

  9. Reinforcement Teaching

    Calarina Muslimani, Alex Lewandowski, Dale Schuurmans, Matthew E. Taylor, Jun Luo

    Action editor: Marcello Restelli.

    openreview.net/forum?id=G2GKii

    #learns #reinforcement #learnable

  10. Lightweight Learner for Shared Knowledge Lifelong Learning

    Yunhao Ge, Yuecheng Li, Di Wu et al.

    Action editor: Edward Grefenstette.

    openreview.net/forum?id=Jjl2c8

    #learns #agents #agent

  11. Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?

    Tian Yun, Usha Bhalla, Ellie Pavlick, Chen Sun

    Action editor: Zhe Gan.

    openreview.net/forum?id=YwNrPL

    #concepts #learns #recognition

  12. Recurrent networks, hidden states and beliefs in partially observable environments

    Gaspard Lambrechts, Adrien Bolland, Damien Ernst

    openreview.net/forum?id=dkHfV3

    #reinforcement #learns #recurrent

  13. No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL

    Han Wang, Archit Sakhadeo, Adam M White et al.

    openreview.net/forum?id=AiOUi3

    #hyperparameters #hyperparameter #learns