Erik Hermansen (@erik_hermansen1) 's Twitter Profile
Erik Hermansen

@erik_hermansen1

Postdoc Mathematical Sciences/Neural Data Science, NTNU

ID: 1364967922205098000

linkhttps://www.ntnu.no/ansatte/erik.hermansen calendar_today25-02-2021 15:58:17

36 Tweet

210 Followers

154 Following

David Klindt (@klindt_david) 's Twitter Profile Photo

1/n Tweeprint 📢📢📢 on neuro-symbolic AI: tinyurl.com/bdjrfsyv Are basic neural networks (2-layer MLP) able to learn simple algorithms (addition of real numbers)? Prior theory says they should be and yet, during training, we see a highly complex error surface evolving

Benjamin Dunn (@adric_dunn) 's Twitter Profile Photo

Math in comp neuro summer camp!! Apply now!!! 10-28/July in lovely Norway (amazing/middle of nowhere). No tuition and room/board/food(good) is covered. Great experience/speakers/students/activities!!!! “fire together, wire together” Do it! compneuronrsn.org

Math in comp neuro summer camp!!
Apply now!!!
10-28/July in lovely Norway (amazing/middle of nowhere). No tuition and room/board/food(good) is covered. Great experience/speakers/students/activities!!!!
“fire together, wire together” 
Do it!

compneuronrsn.org
David Klindt (@klindt_david) 's Twitter Profile Photo

Preprint alert: Superposition in CNNs and Brains Context: Recent work on LLMs showed how sparse coding can recover interpretable representations in transformers Anthropic TL;DR: Concurrently, we have been doing similar analyses in vision models and brains.

Preprint alert: Superposition in CNNs and Brains

Context: Recent work on LLMs showed how sparse coding can recover interpretable representations in transformers <a href="/AnthropicAI/">Anthropic</a> 

TL;DR: Concurrently, we have been doing similar analyses in vision models and brains.
Matteo Guardamagna (@matguardamagna) 's Twitter Profile Photo

Next week at SfN (14th) I will present my first postdoctoral work in the Moser Lab. Kavli Neuroscience Stop by if you are interested in the development of mEC networks (P10-P21), the onset and maturation of toroidal manifolds & individual grid cells, cute rat pups and more!🐀 #SfN2023

Jo Carpenter (@jcarpenter___) 's Twitter Profile Photo

TLDR; We only found *two* neurons in our CA1 dataset that are egocentric-modulated 👀 My first bioRxiv (and the first part of my PhD work) is live! #tweeprint

TLDR; We only found *two* neurons in our CA1 dataset that are egocentric-modulated 👀

My first <a href="/biorxivpreprint/">bioRxiv</a> (and the first part of my PhD work) is live!

#tweeprint
Matteo Guardamagna (@matguardamagna) 's Twitter Profile Photo

Tomorrow at FENS, I'll be sharing my postdoc work on the development of brain networks involved in navigation! Come see me if you're interested in the emergence of toroidal and ring manifolds! New results on the origin of grid modularity, ring-tori relationships & more

Tomorrow at <a href="/FENSorg/">FENS</a>, I'll be sharing my postdoc work on the development of brain networks involved in navigation! 

Come see me if you're interested in the emergence of toroidal and ring manifolds! New results on the origin of grid modularity, ring-tori relationships &amp; more
Erik Hermansen (@erik_hermansen1) 's Twitter Profile Photo

Excited to share paper out in Nature Communications with David Klindt Benjamin Dunn! Uncovering 2D toroidal representations in grid cell ensemble activity during 1D behavior Presented some of this at Neuromonster (thanks Ruairidh Battleday et al): youtube.com/watch?v=0eW4w3… nature.com/articles/s4146…

Matteo Guardamagna (@matguardamagna) 's Twitter Profile Photo

At Society for Neuroscience (SfN) this morning? 🧠 Stop by at PSTR190.07, board V17! I will be presenting my postdoc work on the development of toroidal and ring attractors in MEC/paraSub, with brand new results on the network changes that lead to their organization

David Klindt (@klindt_david) 's Twitter Profile Photo

🧵 New paper! We explore sparse coding, superposition, and the Linear Representation Hypothesis (LRH) through identifiability theory, compressed sensing, and interpretability research. If neural representations intrigue you, read on! 🤓 arxiv.org/abs/2503.01824