Raeed H. Chowdhury

The paper shows that motor and sensory signals in somatosensory cortex are integrated through orthogonal population subspaces to enable accurate body state estimation and perturbation decoding.

The paper trains an autoregressive Transformer on neural spiking data to decode motor behavior, showing broad utility across tasks but highlighting limitations in scaling.

The paper shows that motor cortex maintains similar neural dynamics during motor execution and imagery by recreating missing components in a unique imagery subspace.

This paper infers control objectives from behavior in humans and monkeys using a generative model and behavioral signatures, validated through instructed tasks.

This paper introduces AutoLFADS, an automated framework for estimating neural population dynamics from neural data without supervisory information, validated on multiple datasets.

The paper uses a network model to show that small, correlated changes in synaptic connectivity can explain motor learning without disrupting neural covariance, aligning with experimental observations.

The paper examines the relationship between local field potentials (LFPs) and latent dynamics in primate sensorimotor cortex, finding frequency-dependent and region-specific correlations.

The paper investigates how area 2 of the primary somatosensory cortex encodes whole arm kinematics during reaching tasks, finding that neural activity reflects whole arm movement but varies between active and passive conditions.

The paper shows that latent neural dynamics in the cortex remain stable over two years, enabling consistent behavior decoding despite neuronal turnover.

This study compares GLMs to machine learning methods for predicting neural spikes and finds that modern methods like XGBoost and ensembles are more accurate and robust.