Mainak Deb

Unlike the brain, most ANNs lack any kind of organization of units🧠 In our paper (ICLR 2025) with @mayukh091 @apurvaratan, we present TopoLoss, a simple, scalable way to add brain-like topography to AI models with minimal performance loss🧵 toponets.github.io

Making apps I wish existed, episode 1 Bluetooth signal strength in real-time for iOS

no wrestling with obscure AWS cli commands, no massive figshare zip files, zero pain fMRI dataset that takes <5 min to get running pip install mosaic-dataset

Don't burn up your retina for science, mainakdeb.github.io/just-dark no bs dark-mode for papers, PDFs, and most websites. free, no install/download required :)

What if different parts of a neural network were forced to learn different aspects of the input? They start showing specialized regions like the brain Listen to @MainakDeb19 talk about an architecture that got him an ICLR 2024 spotlight! New talk from @lossfunk!

My work got featured in @TEDAIVienna👀 AtMan (NeurIPS 2023) explains LLM outputs, telling you which part of the context was critical. ted.com/talks/jonas_an… neurips.cc/virtual/2023/p…

@bryan_johnson no way

you up?

@wtergan @mayukh091 @apurvaratan thanks @wtergan you can check the openreview version for the appendix -> openreview.net/pdf?id=THqWPzL…

@MainakDeb19 @mayukh091 @apurvaratan Incredible work! I noticed the paper does not have Appendix section... will this be updated soon? Thanks for the share!

Unlike the brain, most ANNs lack any kind of organization of units🧠 In our paper (ICLR 2025) with @mayukh091 @apurvaratan, we present TopoLoss, a simple, scalable way to add brain-like topography to AI models with minimal performance loss🧵 toponets.github.io

@OpenNetBattle @mayukh091 @apurvaratan Thanks @OpenNetBattle🫡

@MainakDeb19 @mayukh091 @apurvaratan I believe there is a typo: "Brain-likeness in TopoNets manifests in two key ways: (1) an improved alignment with neural data from money and human brains compared to previous" money -> monkey

Checkpoints released on @huggingface🤗 check: github.com/toponets/topon…

🤠Thanks to @neuranna, @NeuroTaha, @alishdipani, and everyone at MurtyLab. murtylab.com

👀 Read the full paper here: openreview.net/forum?id=1g7HW…

👾Sparse model-to-brain mappings improve resistance to attacks.

Artificial neural networks can predict neural responses of the human brain (fMRI), however, they are vulnerable to small-scale adversarial attacks imperceptible to humans 🤖🧠 In our study with @nikolasmcneal @apurvaratan accepted at Neurips 2024 Unireps workshop, we find 👇

🚀At @NeurIPSConf tomorrow? Don't miss @nikolasmcneal and @MainakDeb19 's poster at the @unireps workshop on the adversarial sensitivity of vision encoding models of fMRI responses! A brief teaser about what they find.

I'll be joining @artflow_ai as an intern 🚀 @artflow_ai lets users generate visual content using #AI, exciting stuff! 🖌️🤖🎨 give it a try 👀 -> artflow.ai