SwathiAnil

73 posts

SwathiAnil

SwathiAnil

@Swathi_Anil_

PhD candidate @VlachosLab & @BernsteinNeuro Freiburg, Visiting PhD @NeuralReckoning Weakness:Kittens.Austen.Parton

London, England Katılım Ekim 2020
283 Takip Edilen91 Takipçiler
SwathiAnil retweetledi
Allen Institute
Allen Institute@AllenInstitute·
How does the brain work? Scientists are closer to the answer with the largest wiring diagram and functional map of a mammalian brain to date. 🧵
English
44
503
1.7K
191K
SwathiAnil retweetledi
Dan Goodman
Dan Goodman@neuralreckoning·
PhD position openings in my group! Check out topics and how to apply below. At the moment, I'm particularly interested in the topic of modularity in both biological and artificial networks, and how it can be used to scale up intelligent processes. neural-reckoning.org/openings.html
English
1
77
231
34.5K
SwathiAnil retweetledi
Dan Goodman
Dan Goodman@neuralreckoning·
IV 55 - @Swathi_Anil_ has been following up on our earlier multimodal paper (👇), and looks at how different recurrent and feedforward architectures can cope with multimodal signals with complex temporal structure. x.com/MarcusGhosh/st…
Marcus Ghosh@MarcusGhosh

How should animals combine information across their senses? Prior work suggests linear fusion (sight+sound). However, we show that this would be sub-optimal for many multisensory tasks, and instead, propose a nonlinear function f(sight, sound). doi.org/10.1371/journa…

English
1
1
1
642
SwathiAnil retweetledi
Dan Goodman
Dan Goodman@neuralreckoning·
IV 47 - @MarcusGhosh has been evolving neural networks on multisensory predator/prey and foraging tasks and finding how the need for different architectural features like recurrency emerge as task complexity increases.
Dan Goodman tweet media
English
1
1
2
80
SwathiAnil retweetledi
Dan Goodman
Dan Goodman@neuralreckoning·
IV 38 - PhD student Yang Chu will show you not just one but several learning algorithms that could explain how blind people can localise sounds without visual feedback using innate circuits and a tiny amount of external non-visual feedback.
Dan Goodman tweet media
English
1
1
2
66
SwathiAnil retweetledi
Dan Goodman
Dan Goodman@neuralreckoning·
III 52 - PhD student Greta Horvathova will be talking about her work designing an information bottleneck inspired network that retains object label relevant information while discarding irrelevant information by using "adversarial autoencoders".
English
1
1
3
59
SwathiAnil retweetledi
Dan Goodman
Dan Goodman@neuralreckoning·
II 66 - PhD student @GabrielBna1 will be presenting his work on the relationship between structural modularity and functional specialisation in neural networks, which will be published soon and you can read the preprint and thread below. x.com/neuralreckonin…
Dan Goodman@neuralreckoning

#preprint! Defining neural modularity is hard: much history. We used toy ANNs to show structural and functional definitions not tightly related, resource constraints important, and we need to start thinking about temporal dynamics. 🧵 with @GabrielBna1 arxiv.org/abs/2106.02626

English
1
1
2
96
SwathiAnil
SwathiAnil@Swathi_Anil_·
Looking forward to having a great time at #BernsteinConference 2024! 🧠 Come say hi to everyone at the @neuralreckoning lab ✨ Drop by my poster (IV 55) for our latest work on temporal multisensory processing! @MarcusGhosh 💫 @BernsteinNeuro
Dan Goodman@neuralreckoning

Come and meet the Neural Reckoners at @BernsteinNeuro with posters from: ⭐️@GabrielBna1: specialization/modularity ⭐️@MarcusGhosh @Swathi_Anil_: multisensory processing ⭐️Yang Chu: bootstrapping auditory learning with an innate circuit ⭐️Greta Horvathova: adversarial autoencoders

English
0
0
7
161
SwathiAnil retweetledi
Dan Goodman
Dan Goodman@neuralreckoning·
I'm on the latest episode of Brain Inspired talking about spiking neurons, ML and metascience! Thanks @pgmid for the invite and the extremely fun conversation. Links in the following tweet and for the explanation of why this picture you'll have to listen to the episode. 😉
Dan Goodman tweet media
English
1
11
49
10K
Tim Vogels
Tim Vogels@TPVogels·
Question of the day: If one wanted to build a recurrent spiking net to investigate wider effects of, eg, a dysfunctional K+ channel, are there published precedents that do NOT use Hodgkin-Huxley at the cell level? Do u know of (papers w/) [LIF/AdEx+channel] nets for inspiration?
English
5
3
18
4.5K
SwathiAnil retweetledi
Tim Vogels
Tim Vogels@TPVogels·
Over the years my lab has been working on #meta_learning #plasticity rules in #spiking networks. Here's progress report on how far we can get using a twist on simulation based inference (fSBI), presented at @NeurIPSConf (#405) w/ @basile_cfx, @pramesh95 @ppjgoncalves & @jakhmack.
Tim Vogels@TPVogels

@patrickmineault Tx Patrick, great community service! We got something on #meta_learning ensembles of (EE, EI, II & IE) #plasticity rules in large #spiking networks using simulation based #inference with @jakhmack @basile_cfx @pramesh95 & @ppjgoncalves. Tweeprint coming. openreview.net/forum?id=FLFas…

English
1
23
75
22.3K
SwathiAnil
SwathiAnil@Swathi_Anil_·
Happy to share our latest and my first first author(yay!) paper in @PLOSCompBiol, a close look at rTMS-induced remodeling in large scale spiking networks with homeostatic structural plasticity! Thanks to everyone @VlachosLab & @BernsteinNeuro for everything! 🥂🧠✨ #plasticity
Andreas Vlachos@VlachosLab

🚨 Paper Alert 🧠: Our latest study @PLOSCompBiol uses computational modeling to explore homeostatic structural plasticity as a mechanism in neuronal rewiring via rTMS. Advancing our understanding of brain stimulation. Great job @Swathi_Anil_🚨#Brainstim journals.plos.org/ploscompbiol/a…

English
1
4
16
1.6K