Krishnaswamy Lab open-sources Neurospectrum, a geometric-topological DL framework for neural trajectories
Pseudomanifold · x · 2026-11-09
Krishnaswamy Lab released Neurospectrum on GitHub (Bhaskar, Zhang, Moore et al.): a geometric and topological deep learning framework that models neural activity as a time-varying signal on a graph, encodes spatial patterns with multiscale diffusion wavelets plus learnable attention, and compresses them via a T-PHATE-regularized autoencoder into low-dimensional latent trajectories. Code, notebooks and configs are public; validated on mouse calcium imaging and human fMRI.
More from Research
- Researchers question AI capability acceleration: shift to RL may be the confounder — DavidSKrueger · 2026-11-09
- Neural network output layers explained: classification vs regression — HarperSCarroll · 2026-11-09
- Ropedia W0 trains robot world models on 10,000 hours of human video, lifting LIBERO-Plus by 6.76 points — jiqizhixin · 2026-11-09
- Mathematician rebuts AI proof critics: demanding Lean verification is a double standard — AlexKontorovich · 2026-11-09
- RobPicker in Nature Methods: meta-learning fixes noisy labels, protein detection 0.24 to 0.47 — bravo_abad · 2026-11-09
- Google's ScientistTwo AI writes expert-level papers end-to-end and self-reviews — 2C_ornot2C · 2026-11-09