Learned Spectrum - Teddy Warner

Towards temporal understanding in AI through fMRI learning stage classification.

This research presents a novel approach to understanding temporal cognition through the application of Vision Transformers to functional Magnetic Resonance Imaging (fMRI) data analysis. While current artificial intelligence approaches to world modeling rely heavily on absolute temporal markers and timestamps, human perception of time operates as a fundamentally subjective experience that adapts with cognitive state and learning progress. We demonstrate that neural activation patterns captured during learning through fMRI contain rich temporal information that can inform more nuanced…

saved by

• SUJASH AGRAWAL

related reading

• AI to Interpret Your Mindjonathanxu.com
• Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priorsmedarc-ai.github.io
• [2305.18274] Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priorsarxiv.org
• MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Datamedarc-ai.github.io
• Toward accessible, real-time brain decoding: Introducing ENIGMA | Alljoined Blogalljoined.com
• Dimensionality reduction in neural data analysisxcorr.net
• Arousal as a universal embedding for spatiotemporal brain dynamicsnature.com
• Towards a “universal translator” for neural dynamics at single-cell, single-spike resolutionarxiv.org
• [2501.00663] Titans: Learning to Memorize at Test Timearxiv.org
• Retrieving and reconstructing conceptually similar images from fMRI with latent diffusion models and a neuro-inspired brain decoding model - IOPscienceiopscience.iop.org
• [2409.06843] Universal scale-free representations in human visual cortexarxiv.org
• Spatially embedded recurrent neural networks reveal widespread links between structural and functional neuroscience findingsnature.com