Marcus Ghosh
@marcusghosh.bsky.social
Computational neuroscientist.
Research Fellow @imperialcollegeldn.bsky.social and @imperial-ix.bsky.social
Funded by @schmidtsciences.bsky.social
Research Fellow @imperialcollegeldn.bsky.social and @imperial-ix.bsky.social
Funded by @schmidtsciences.bsky.social
Pinned
Marcus Ghosh
@marcusghosh.bsky.social
· Aug 1
How does the structure of a neural circuit shape its function?
@neuralreckoning.bsky.social & I explore this in our new preprint:
doi.org/10.1101/2025...
🤖🧠🧪
🧵1/9
@neuralreckoning.bsky.social & I explore this in our new preprint:
doi.org/10.1101/2025...
🤖🧠🧪
🧵1/9
Interested in #neuroscience + #AI and looking for a PhD position?
I can support your application @imperialcollegeldn.bsky.social
✅ Check your eligibility (below)
✅ Contact me (DM or email)
UK nationals: www.imperial.ac.uk/life-science...
Otherwise: www.imperial.ac.uk/study/fees-a...
I can support your application @imperialcollegeldn.bsky.social
✅ Check your eligibility (below)
✅ Contact me (DM or email)
UK nationals: www.imperial.ac.uk/life-science...
Otherwise: www.imperial.ac.uk/study/fees-a...
November 4, 2025 at 9:47 AM
Interested in #neuroscience + #AI and looking for a PhD position?
I can support your application @imperialcollegeldn.bsky.social
✅ Check your eligibility (below)
✅ Contact me (DM or email)
UK nationals: www.imperial.ac.uk/life-science...
Otherwise: www.imperial.ac.uk/study/fees-a...
I can support your application @imperialcollegeldn.bsky.social
✅ Check your eligibility (below)
✅ Contact me (DM or email)
UK nationals: www.imperial.ac.uk/life-science...
Otherwise: www.imperial.ac.uk/study/fees-a...
Are #NeuroAI and #AINeuro equivalent?
@rdgao.bsky.social draws a nice distinction between the two.
And introduces Gao's second law:
“Any state-of-the-art algorithm for analyzing brain signals is, for some time, how the brain works.”
Part 1: www.rdgao.com/blog/2024/01...
@rdgao.bsky.social draws a nice distinction between the two.
And introduces Gao's second law:
“Any state-of-the-art algorithm for analyzing brain signals is, for some time, how the brain works.”
Part 1: www.rdgao.com/blog/2024/01...
September 25, 2025 at 12:19 PM
Are #NeuroAI and #AINeuro equivalent?
@rdgao.bsky.social draws a nice distinction between the two.
And introduces Gao's second law:
“Any state-of-the-art algorithm for analyzing brain signals is, for some time, how the brain works.”
Part 1: www.rdgao.com/blog/2024/01...
@rdgao.bsky.social draws a nice distinction between the two.
And introduces Gao's second law:
“Any state-of-the-art algorithm for analyzing brain signals is, for some time, how the brain works.”
Part 1: www.rdgao.com/blog/2024/01...
Reposted by Marcus Ghosh
New preprint! What happens if you add neuromodulation to spiking neural networks and let them go wild with it? TLDR: it can improve performance especially in challenging sensory processing tasks. Explainer thread below. 🤖🧠🧪 www.biorxiv.org/content/10.1...
Neuromodulation enhances dynamic sensory processing in spiking neural network models
Neuromodulators allow circuits to dynamically change their biophysical properties in a context-sensitive way. In addition to their role in learning, neuromodulators have been suggested to play a role ...
www.biorxiv.org
September 18, 2025 at 4:30 PM
New preprint! What happens if you add neuromodulation to spiking neural networks and let them go wild with it? TLDR: it can improve performance especially in challenging sensory processing tasks. Explainer thread below. 🤖🧠🧪 www.biorxiv.org/content/10.1...
Reposted by Marcus Ghosh
Truly honored (and a little overwhelmed) to see our work featured in The Transmitter's "This Paper Changed My Life." Huge thanks to @neural-reckoning.org for the kind words - and to our amazing community that keeps pushing spiking neural network research forward 🙏
In our latest “This paper changed my life,” @neural-reckoning.org explains how @fzenke.bsky.social's 2019 paper, and its related coding tutorial SpyTorch, made it possible to apply modern machine learning to spiking neural networks.
#neuroskyence
www.thetransmitter.org/this-paper-c...
#neuroskyence
www.thetransmitter.org/this-paper-c...
This paper changed my life: Dan Goodman on a paper that reignited the field of spiking neural networks
Friedemann Zenke’s 2019 paper, and its related coding tutorial SpyTorch, made it possible to apply modern machine learning to spiking neural networks. The innovation reinvigorated the field.
www.thetransmitter.org
September 17, 2025 at 2:50 PM
Truly honored (and a little overwhelmed) to see our work featured in The Transmitter's "This Paper Changed My Life." Huge thanks to @neural-reckoning.org for the kind words - and to our amazing community that keeps pushing spiking neural network research forward 🙏
The misleading manifold?
The current debate (decoding vs causal relevance)
and a toy example I gave in the thread below
got me thinking about a related issue: how decoding may reflect structure more than function.
🧵 1/5
The current debate (decoding vs causal relevance)
and a toy example I gave in the thread below
got me thinking about a related issue: how decoding may reflect structure more than function.
🧵 1/5
These, and other, studies show that you can decode task-related signals from many brain areas.
But wouldn't we need causal manipulations to conclude that the brain "uses" them?
For example, maybe we can decode equally well from two areas. But, only one impacts behaviour when inactivated.
But wouldn't we need causal manipulations to conclude that the brain "uses" them?
For example, maybe we can decode equally well from two areas. But, only one impacts behaviour when inactivated.
September 8, 2025 at 1:44 PM
The misleading manifold?
The current debate (decoding vs causal relevance)
and a toy example I gave in the thread below
got me thinking about a related issue: how decoding may reflect structure more than function.
🧵 1/5
The current debate (decoding vs causal relevance)
and a toy example I gave in the thread below
got me thinking about a related issue: how decoding may reflect structure more than function.
🧵 1/5
Reposted by Marcus Ghosh
Proud to have been a part of this, a great example of distributed async science!
Huge thanks to @marcusghosh.bsky.social, @neuralreckoning.bsky.social, @tfiers.bsky.social, @krhab.bsky.social and others for putting in the bulk effort 🙌
Huge thanks to @marcusghosh.bsky.social, @neuralreckoning.bsky.social, @tfiers.bsky.social, @krhab.bsky.social and others for putting in the bulk effort 🙌
Is anarchist science possible? As an experiment, we got together a large group of computational neuroscientists from around the world to work on a single project without top down direction. Read on to find out what happened. 🤖🧠🧪
September 4, 2025 at 3:44 PM
Proud to have been a part of this, a great example of distributed async science!
Huge thanks to @marcusghosh.bsky.social, @neuralreckoning.bsky.social, @tfiers.bsky.social, @krhab.bsky.social and others for putting in the bulk effort 🙌
Huge thanks to @marcusghosh.bsky.social, @neuralreckoning.bsky.social, @tfiers.bsky.social, @krhab.bsky.social and others for putting in the bulk effort 🙌
Being part of this grassroots 🌱 neuroscience collaboration was a great experience!
Keep an eye out for our next collaborative effort
Keep an eye out for our next collaborative effort
September 4, 2025 at 3:17 PM
Being part of this grassroots 🌱 neuroscience collaboration was a great experience!
Keep an eye out for our next collaborative effort
Keep an eye out for our next collaborative effort
I'll be presenting this work at #CCN2025 tomorrow (A173).
Come and say hi or message me if you'd like to meet up!
Come and say hi or message me if you'd like to meet up!
How does the structure of a neural circuit shape its function?
@neuralreckoning.bsky.social & I explore this in our new preprint:
doi.org/10.1101/2025...
🤖🧠🧪
🧵1/9
@neuralreckoning.bsky.social & I explore this in our new preprint:
doi.org/10.1101/2025...
🤖🧠🧪
🧵1/9
August 11, 2025 at 3:33 PM
I'll be presenting this work at #CCN2025 tomorrow (A173).
Come and say hi or message me if you'd like to meet up!
Come and say hi or message me if you'd like to meet up!
How does the structure of a neural circuit shape its function?
@neuralreckoning.bsky.social & I explore this in our new preprint:
doi.org/10.1101/2025...
🤖🧠🧪
🧵1/9
@neuralreckoning.bsky.social & I explore this in our new preprint:
doi.org/10.1101/2025...
🤖🧠🧪
🧵1/9
August 1, 2025 at 8:27 AM
How does the structure of a neural circuit shape its function?
@neuralreckoning.bsky.social & I explore this in our new preprint:
doi.org/10.1101/2025...
🤖🧠🧪
🧵1/9
@neuralreckoning.bsky.social & I explore this in our new preprint:
doi.org/10.1101/2025...
🤖🧠🧪
🧵1/9
Reposted by Marcus Ghosh
Preprint update: The new version of #SPARKS🎇 is out!
Everything's in here: sparks.crick.ac.uk
A thread on what changed 🧵👇
@flor-iacaruso.bsky.social @sdrsd.bsky.social @alexegeaweiss.bsky.social
#neuroskyence #NeuroAI #ML #BioInspiredAI
Everything's in here: sparks.crick.ac.uk
A thread on what changed 🧵👇
@flor-iacaruso.bsky.social @sdrsd.bsky.social @alexegeaweiss.bsky.social
#neuroskyence #NeuroAI #ML #BioInspiredAI
July 31, 2025 at 10:33 AM
Preprint update: The new version of #SPARKS🎇 is out!
Everything's in here: sparks.crick.ac.uk
A thread on what changed 🧵👇
@flor-iacaruso.bsky.social @sdrsd.bsky.social @alexegeaweiss.bsky.social
#neuroskyence #NeuroAI #ML #BioInspiredAI
Everything's in here: sparks.crick.ac.uk
A thread on what changed 🧵👇
@flor-iacaruso.bsky.social @sdrsd.bsky.social @alexegeaweiss.bsky.social
#neuroskyence #NeuroAI #ML #BioInspiredAI
Reposted by Marcus Ghosh
Hiring a post-doc at Imperial in EEE. Broad in scope + flexible on topics: neural networks & new AI accelerators from a HW/SW co-design perspective!
w/ @neuralreckoning.bsky.social @achterbrain.bsky.social in Intelligent Systems and Networks group.
Plz share! 🚀: www.imperial.ac.uk/jobs/search-...
w/ @neuralreckoning.bsky.social @achterbrain.bsky.social in Intelligent Systems and Networks group.
Plz share! 🚀: www.imperial.ac.uk/jobs/search-...
Description
Please note that job descriptions are not exhaustive, and you may be asked to take on additional duties that align with the key responsibilities ment...
www.imperial.ac.uk
July 25, 2025 at 1:27 PM
Hiring a post-doc at Imperial in EEE. Broad in scope + flexible on topics: neural networks & new AI accelerators from a HW/SW co-design perspective!
w/ @neuralreckoning.bsky.social @achterbrain.bsky.social in Intelligent Systems and Networks group.
Plz share! 🚀: www.imperial.ac.uk/jobs/search-...
w/ @neuralreckoning.bsky.social @achterbrain.bsky.social in Intelligent Systems and Networks group.
Plz share! 🚀: www.imperial.ac.uk/jobs/search-...
How can we best use AI in science?
Myself and 9 other research fellows from @imperial-ix.bsky.social use AI methods in domains from plant biology (🌱) to neuroscience (🧠) and particle physics (🎇).
Together we suggest 10 simple rules @plos.org 🧵
doi.org/10.1371/jour...
Myself and 9 other research fellows from @imperial-ix.bsky.social use AI methods in domains from plant biology (🌱) to neuroscience (🧠) and particle physics (🎇).
Together we suggest 10 simple rules @plos.org 🧵
doi.org/10.1371/jour...
July 25, 2025 at 10:58 AM
How can we best use AI in science?
Myself and 9 other research fellows from @imperial-ix.bsky.social use AI methods in domains from plant biology (🌱) to neuroscience (🧠) and particle physics (🎇).
Together we suggest 10 simple rules @plos.org 🧵
doi.org/10.1371/jour...
Myself and 9 other research fellows from @imperial-ix.bsky.social use AI methods in domains from plant biology (🌱) to neuroscience (🧠) and particle physics (🎇).
Together we suggest 10 simple rules @plos.org 🧵
doi.org/10.1371/jour...
Reposted by Marcus Ghosh
New preprint for #neuromorphic and #SpikingNeuralNetwork folk (with @pengfei-sun.bsky.social).
arxiv.org/abs/2507.16043
Surrogate gradients are popular for training SNNs, but some worry whether they really learn complex temporal spike codes. TLDR: we tested this, and yes they can! 🧵👇
🤖🧠🧪
arxiv.org/abs/2507.16043
Surrogate gradients are popular for training SNNs, but some worry whether they really learn complex temporal spike codes. TLDR: we tested this, and yes they can! 🧵👇
🤖🧠🧪
Beyond Rate Coding: Surrogate Gradients Enable Spike Timing Learning in Spiking Neural Networks
We investigate the extent to which Spiking Neural Networks (SNNs) trained with Surrogate Gradient Descent (Surrogate GD), with and without delay learning, can learn from precise spike timing beyond fi...
arxiv.org
July 24, 2025 at 5:03 PM
New preprint for #neuromorphic and #SpikingNeuralNetwork folk (with @pengfei-sun.bsky.social).
arxiv.org/abs/2507.16043
Surrogate gradients are popular for training SNNs, but some worry whether they really learn complex temporal spike codes. TLDR: we tested this, and yes they can! 🧵👇
🤖🧠🧪
arxiv.org/abs/2507.16043
Surrogate gradients are popular for training SNNs, but some worry whether they really learn complex temporal spike codes. TLDR: we tested this, and yes they can! 🧵👇
🤖🧠🧪
Had a great time discussing multisensory integration @imrf.bsky.social!
And really enjoyed sharing our new work too
And really enjoyed sharing our new work too
July 21, 2025 at 8:14 AM
Had a great time discussing multisensory integration @imrf.bsky.social!
And really enjoyed sharing our new work too
And really enjoyed sharing our new work too
Reposted by Marcus Ghosh
It’s been a minute (11 years) since my last @imrf.bsky.social
I’m excited to seeing all the great research.
And I’m delighted to give a talk on Friday about Rebecca Brady’s PhD new modelling studies in collab w @bizleylab.bsky.social and @jennycampos.bsky.social
1/2
www.biorxiv.org/content/10.1...
I’m excited to seeing all the great research.
And I’m delighted to give a talk on Friday about Rebecca Brady’s PhD new modelling studies in collab w @bizleylab.bsky.social and @jennycampos.bsky.social
1/2
www.biorxiv.org/content/10.1...
Modelling Audio-Visual Reaction Time with Recurrent Mean-Field Networks
Understanding how the brain integrates multisensory information during detection and decision-making remains an active area of research. While many inferences have been drawn about behavioural outcome...
www.biorxiv.org
July 15, 2025 at 10:34 AM
It’s been a minute (11 years) since my last @imrf.bsky.social
I’m excited to seeing all the great research.
And I’m delighted to give a talk on Friday about Rebecca Brady’s PhD new modelling studies in collab w @bizleylab.bsky.social and @jennycampos.bsky.social
1/2
www.biorxiv.org/content/10.1...
I’m excited to seeing all the great research.
And I’m delighted to give a talk on Friday about Rebecca Brady’s PhD new modelling studies in collab w @bizleylab.bsky.social and @jennycampos.bsky.social
1/2
www.biorxiv.org/content/10.1...
Off to my first @imrf.bsky.social conference!
I'll be giving a talk on Friday (talk session 9) on multisensory network architectures - new work from me & @neuralreckoning.bsky.social.
But say hello or DM me before then!
I'll be giving a talk on Friday (talk session 9) on multisensory network architectures - new work from me & @neuralreckoning.bsky.social.
But say hello or DM me before then!
July 15, 2025 at 9:22 AM
Off to my first @imrf.bsky.social conference!
I'll be giving a talk on Friday (talk session 9) on multisensory network architectures - new work from me & @neuralreckoning.bsky.social.
But say hello or DM me before then!
I'll be giving a talk on Friday (talk session 9) on multisensory network architectures - new work from me & @neuralreckoning.bsky.social.
But say hello or DM me before then!
Had a great time teaching on the @trendcamina.bsky.social summer school in Zambia!
Awesome students and super TAs:
@akoumoundourou.bsky.social, @tomnotgeorge.bsky.social, @jsoldadomagraner.bsky.social, @ashvparker.bsky.social, @pollytur.bsky.social, @skuechenhoff.bsky.social
Awesome students and super TAs:
@akoumoundourou.bsky.social, @tomnotgeorge.bsky.social, @jsoldadomagraner.bsky.social, @ashvparker.bsky.social, @pollytur.bsky.social, @skuechenhoff.bsky.social
July 14, 2025 at 2:44 PM
Had a great time teaching on the @trendcamina.bsky.social summer school in Zambia!
Awesome students and super TAs:
@akoumoundourou.bsky.social, @tomnotgeorge.bsky.social, @jsoldadomagraner.bsky.social, @ashvparker.bsky.social, @pollytur.bsky.social, @skuechenhoff.bsky.social
Awesome students and super TAs:
@akoumoundourou.bsky.social, @tomnotgeorge.bsky.social, @jsoldadomagraner.bsky.social, @ashvparker.bsky.social, @pollytur.bsky.social, @skuechenhoff.bsky.social
Reposted by Marcus Ghosh
Thrilled to see our TinyRNN paper in @nature! We show how tiny RNNs predict choices of individual subjects accurately while staying fully interpretable. This approach can transform how we model cognitive processes in both healthy and disordered decisions. doi.org/10.1038/s415...
Discovering cognitive strategies with tiny recurrent neural networks - Nature
Modelling biological decision-making with tiny recurrent neural networks enables more accurate predictions of animal choices than classical cognitive models and offers insights into the underlying cog...
doi.org
July 2, 2025 at 7:03 PM
Thrilled to see our TinyRNN paper in @nature! We show how tiny RNNs predict choices of individual subjects accurately while staying fully interpretable. This approach can transform how we model cognitive processes in both healthy and disordered decisions. doi.org/10.1038/s415...
Reposted by Marcus Ghosh
(1/7) New preprint from Rajan lab! 🧠🤖
@ryanpaulbadman1.bsky.social & Riley Simmons-Edler show–through cog sci, neuro & ethology–how an AI agent with fewer ‘neurons’ than an insect can forage, find safety & dodge predators in a virtual world. Here's what we built
Preprint: arxiv.org/pdf/2506.06981
@ryanpaulbadman1.bsky.social & Riley Simmons-Edler show–through cog sci, neuro & ethology–how an AI agent with fewer ‘neurons’ than an insect can forage, find safety & dodge predators in a virtual world. Here's what we built
Preprint: arxiv.org/pdf/2506.06981
July 2, 2025 at 6:34 PM
(1/7) New preprint from Rajan lab! 🧠🤖
@ryanpaulbadman1.bsky.social & Riley Simmons-Edler show–through cog sci, neuro & ethology–how an AI agent with fewer ‘neurons’ than an insect can forage, find safety & dodge predators in a virtual world. Here's what we built
Preprint: arxiv.org/pdf/2506.06981
@ryanpaulbadman1.bsky.social & Riley Simmons-Edler show–through cog sci, neuro & ethology–how an AI agent with fewer ‘neurons’ than an insect can forage, find safety & dodge predators in a virtual world. Here's what we built
Preprint: arxiv.org/pdf/2506.06981
The Centauromachy begins
Binz et al. (in press, Nature) developed an LLM called Centaur that better predicts human responses in 159 of 160 behavioural experiments compared to existing cognitive models. See: arxiv.org/abs/2410.20268
June 27, 2025 at 9:19 AM
The Centauromachy begins
Reposted by Marcus Ghosh
🚨Preprint Alert: Who Does What in Deep Learning? Multidimensional Contribution of Neural Units using Game Theory: arxiv.org/abs/2506.19732
The result of my MSc thesis is out with @kayson.bsky.social @fatemehhadaeghi.bsky.social @patrickmineault.bsky.social @kordinglab.bsky.social, Claus C. Hilgetag
The result of my MSc thesis is out with @kayson.bsky.social @fatemehhadaeghi.bsky.social @patrickmineault.bsky.social @kordinglab.bsky.social, Claus C. Hilgetag
Who Does What in Deep Learning? Multidimensional Game-Theoretic Attribution of Function of Neural Units
Neural networks now generate text, images, and speech with billions of parameters, producing a need to know how each neural unit contributes to these high-dimensional outputs. Existing explainable-AI ...
arxiv.org
June 25, 2025 at 9:18 AM
🚨Preprint Alert: Who Does What in Deep Learning? Multidimensional Contribution of Neural Units using Game Theory: arxiv.org/abs/2506.19732
The result of my MSc thesis is out with @kayson.bsky.social @fatemehhadaeghi.bsky.social @patrickmineault.bsky.social @kordinglab.bsky.social, Claus C. Hilgetag
The result of my MSc thesis is out with @kayson.bsky.social @fatemehhadaeghi.bsky.social @patrickmineault.bsky.social @kordinglab.bsky.social, Claus C. Hilgetag
How should #multisensory signals be combined when they are structured in time?
To explore this, we:
* Introduce a new multisensory task
* Compare several models
TLDR:
* Prior models perform suboptimally
* Our new model performs ≈ an RNN, while using less than 1/10th the number of parameters.
To explore this, we:
* Introduce a new multisensory task
* Compare several models
TLDR:
* Prior models perform suboptimally
* Our new model performs ≈ an RNN, while using less than 1/10th the number of parameters.
Fusing multisensory signals across channels and time.
Now published at PLOS Comp Biol! 🎉 With @swathianil.bsky.social and @marcusghosh.bsky.social.
journals.plos.org/ploscompbiol...
TLDR, when multisensory signals vary over time, neural architecture becomes important. Biggest not always best.
Now published at PLOS Comp Biol! 🎉 With @swathianil.bsky.social and @marcusghosh.bsky.social.
journals.plos.org/ploscompbiol...
TLDR, when multisensory signals vary over time, neural architecture becomes important. Biggest not always best.
June 11, 2025 at 8:10 AM
How should #multisensory signals be combined when they are structured in time?
To explore this, we:
* Introduce a new multisensory task
* Compare several models
TLDR:
* Prior models perform suboptimally
* Our new model performs ≈ an RNN, while using less than 1/10th the number of parameters.
To explore this, we:
* Introduce a new multisensory task
* Compare several models
TLDR:
* Prior models perform suboptimally
* Our new model performs ≈ an RNN, while using less than 1/10th the number of parameters.
New pre-print with Rebecca Brady on mathematical models to simulate audio-visual reaction time tasks.
This debutant paper has three main goals:
1. To simulate different mechanisms of multisensory integration and compare with the behavioural findings 1/8
This debutant paper has three main goals:
1. To simulate different mechanisms of multisensory integration and compare with the behavioural findings 1/8
June 6, 2025 at 12:43 PM
Really interesting work from @solarpunkgabs.bsky.social & @neuralreckoning.bsky.social!
New #Preprint Alert!! 🤖 🧠 🧪
What if we could train neural cellular automata to develop continuous universal computation through gradient descent ?! We have started to chart a path toward this goal in our new preprint:
arXiv: arxiv.org/abs/2505.13058
Blog: gabrielbena.github.io/blog/2025/be...
🧵⬇️
What if we could train neural cellular automata to develop continuous universal computation through gradient descent ?! We have started to chart a path toward this goal in our new preprint:
arXiv: arxiv.org/abs/2505.13058
Blog: gabrielbena.github.io/blog/2025/be...
🧵⬇️
A Path to Universal Neural Cellular Automata | Gabriel Béna
Exploring how neural cellular automata can develop continuous universal computation through training by gradient descent
gabrielbena.github.io
June 5, 2025 at 7:46 AM
Really interesting work from @solarpunkgabs.bsky.social & @neuralreckoning.bsky.social!
Fellows from @imperial-ix.bsky.social, including myself, recently visited AIMS Cape Town!
We ran tutorials to show the students how we apply methods from AI to different scientific domains; from particle physics to public health (@ojwatson.bsky.social) and #neuroscience.
We ran tutorials to show the students how we apply methods from AI to different scientific domains; from particle physics to public health (@ojwatson.bsky.social) and #neuroscience.
May 7, 2025 at 12:39 PM
Fellows from @imperial-ix.bsky.social, including myself, recently visited AIMS Cape Town!
We ran tutorials to show the students how we apply methods from AI to different scientific domains; from particle physics to public health (@ojwatson.bsky.social) and #neuroscience.
We ran tutorials to show the students how we apply methods from AI to different scientific domains; from particle physics to public health (@ojwatson.bsky.social) and #neuroscience.