Rasmus Malik Høegh Lindrup (@rasthh) 's Twitter Profile
Rasmus Malik Høegh Lindrup

@rasthh

PostDoc at UC Berkeley (BAIR), generative AI, variational inference
mastodon: @[email protected]
bluesky: @rmhl.bsky.social

ID: 2208715469

linkhttp://rasmusmhl.github.io calendar_today05-12-2013 12:10:41

32 Tweet

94 Followers

1,1K Following

Cognitive Systems (@cogsys) 's Twitter Profile Photo

Come work with us - exiting new position as associate/assistant professor in machine learning and signal processing. Apply before 30 April. #cogsys #DTU_Compute dtu.dk/english/about/…

Google DeepMind (@googledeepmind) 's Twitter Profile Photo

Our new paper, “Reinforcement Learning, Fast and Slow”, reviews recent techniques in deep RL that narrow the gap in learning speed between humans and agents, & demonstrate an interplay between fast and slow learning w/ parallels in animal/human cognition: cell.com/trends/cogniti…

Our new paper, “Reinforcement Learning, Fast and Slow”, reviews recent techniques in deep RL that narrow the gap in learning speed between humans and agents, & demonstrate an interplay between fast and slow learning w/ parallels in animal/human cognition:

cell.com/trends/cogniti…
Cognitive Systems (@cogsys) 's Twitter Profile Photo

Forskningens Døgn about the Sound of Denmark, for which #DTU_Compute and #CogSys has developed AI, got high schools all over the country (via livestream) to compete about sound and AI. compute.dtu.dk/nyheder/nyhed?…

David Beniaguev (@davidbeniaguev) 's Twitter Profile Photo

A story of a Cortical Neuron as a Deep Artificial Neural Net: 1) Neurons in the brain are bombarded with massive synaptic input distributed across a large tree like structure - its dendritic tree. During this bombardment, the tree goes wild preprint: biorxiv.org/content/10.110…

hardmaru (@hardmaru) 's Twitter Profile Photo

Weight Agnostic Neural Networks 🦎 Inspired by precocial species in biology, we set out to search for neural net architectures that can already (sort of) perform various tasks even when they use random weight values. Article: weightagnostic.github.io PDF: arxiv.org/abs/1906.04358

David Rolnick (@david_rolnick) 's Twitter Profile Photo

Want to help solve #ClimateChange? Here’s what #MachineLearning can do. Detailed recommendations for researchers, entrepreneurs, and public/private stakeholders. #ClimateChangeAI Full paper: arxiv.org/abs/1906.05433

Want to help solve #ClimateChange?  Here’s what #MachineLearning can do. Detailed recommendations for researchers, entrepreneurs, and public/private stakeholders. #ClimateChangeAI
Full paper: arxiv.org/abs/1906.05433
DTU Compute (@dtu_compute) 's Twitter Profile Photo

Thanks to DK Frie Forsk.fond for the impressive grants to DTU. Especially to #DTU_Compute professor Morten Mørup and his project ’Learning the Structure and Dynamics of Complex Networks’ that received 5,9 mio. DKK. #DFF #DTUtweet #complexnetworks compute.dtu.dk/nyheder/Nyhed?…

Laura Hannemose Rieger (@laura_rieger_de) 's Twitter Profile Photo

Excited to present "Client Adaptation improves Federated Learning with Simulated Non-IID Clients" at the Federated Learning workshop at #ICML2020 on Saturday 3:35 pm (CEST). Work together w/ Rasmus Malik Høegh Lindrup and Lars Kai Hansen arxiv.org/abs/2007.04806

Excited to present 
"Client Adaptation improves Federated Learning with Simulated Non-IID Clients"
at the Federated Learning workshop at #ICML2020 on Saturday 3:35 pm (CEST).
Work together w/ <a href="/rasthh/">Rasmus Malik Høegh Lindrup</a> and <a href="/tweetteresearch/">Lars Kai Hansen</a>
arxiv.org/abs/2007.04806
Rasmus Malik Høegh Lindrup (@rasthh) 's Twitter Profile Photo

3rd day and we've helped a bird escape OT, been overtaken by old man on mtn side, and taken down rain filled buckets from monsoon hit attic.