Foram Bharat Kamdar

Stanford University
Country flagUnited States

Research Interests

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Explore related searches

Articles (7)

Intracortical brain-computer interfaces (BCIs) that decode complex movements, such as handwriting and speech, can require substantial training data to achieve high performance. We investigated whether leveraging the neural activity recordings of previous users could reduce this initial data collection burden for new BCI users (an approach we call “cross-brain transfer”). Using intracortical recordings from five BrainGate2 clinical trial participants, we tested cross-brain transfer for both speech and handwriting neural decoders trained and evaluated on general, unconstrained corpora of spoken and written English. We found that cross-brain transfer improved decoding performance when training data from the target user was limited (< 200 sentences), and that dataset-specific input layers to the decoder were critical for combining data across users. Without trainable input layers, transfer failed and performed worse than training from scratch on target user data only. Finally, we measured the effectiveness of cross-brain transfer relative to training with (1) more data from the same user and (2) more electrode-permuted data from the same user, which simulates sampling from another brain with identical neural latent structure. In some cases (T16 speech, T12 handwriting), cross-brain transfer appeared as effective as additional permuted data from the same user, while in others (T12 speech, T15 speech) electrode-permuted data was more beneficial. Our results successfully demonstrate and characterize cross-brain transfer learning between multiple intracortical BCI users, for both speech and handwriting, using a general open-ended dataset not restricted to small sets of words or phrases. This work highlights a promising path towards addressing a key barrier to the clinical translation of BCIs, while clarifying when cross-brain transfer may be most beneficial and the decoder design choices needed to realize those gains.

Year:

2026

People with paralysis express unmet needs for peer support, leisure activities and sporting activities. Many within the general population rely on social media and massively multiplayer video games to address these needs. We developed a high-performance, finger-based brain–computer-interface system allowing continuous control of three independent finger groups, of which the thumb can be controlled in two dimensions, yielding a total of four degrees of freedom. The system was tested in a human research participant with tetraplegia due to spinal cord injury over sequential trials requiring fingers to reach and hold on targets, with an average acquisition rate of 76 targets per minute and completion time of 1.58 ± 0.06 seconds—comparing favorably to prior animal studies despite a twofold increase in the decoded degrees of freedom. More importantly, finger positions were then used to control a virtual quadcopter—the number-one restorative priority for the participant—using a brain-to-finger-to-computer interface to allow dexterous navigation around fixed- and random-ringed obstacle courses. The participant expressed or demonstrated a sense of enablement, recreation and social connectedness that addresses many of the unmet needs of people with paralysis.

Year:

2025

Intracortical brain–computer interfaces (iBCIs) require frequent recalibration to maintain robust performance due to changes in neural activity that accumulate over time, which result in periods when users cannot use their device. Here we introduce a hidden Markov model to infer which targets users are moving towards during iBCI use and we retrain the system using these inferred targets, enabling unsupervised adaptation to changing neural activity. Our approach outperforms distribution alignment methods in large-scale, closed-loop simulations over two months, as well as in a closed loop with a human iBCI user over one month. Leveraging an offline dataset spanning five years of iBCI recordings, we show how target inference recalibration methods appear capable of long-term unsupervised recalibration, whereas recently proposed data-distribution-matching approaches appear to accumulate compounding errors over time. We show offline that our approach performs well on freeform datasets of a person using a home computer with an iBCI. Our results demonstrate the use of task structure to bootstrap a noisy decoder into a highly performant one, thereby overcoming one of the major barriers to clinically translating BCIs.

Year:

2025

Year:

2025

The computation-through-dynamics perspective argues that biological neural circuits process information via the continuous evolution of their internal states. Inspired by this perspective, Latent Factor Activity using Dynamical systems (LFADS, [1]) identifies a generative model consistent with the neural activity recordings. LFADS models neural dynamics with a recurrent neural network (RNN) generator, which results in excellent fit to the data. However, it has been difficult to understand the dynamics of the LFADS generator. In this work, we show that this poor interpretability arises in part because the generator implements complex, multi-stable dynamics. We introduce a simple modification to LFADS that ameliorates issues with interpretability by providing an inferred per-trial bias (modeled as a constant input) to the RNN generator, enabling it to contextually adapt a simpler dynamical system to individual trials. In both simulated neural recordings from pendulum oscillations and real recordings during arm movements in nonhuman primates, we observed that the standard LFADS learned complex, multi-stable dynamics, whereas the modified LFADS learned easier-to-understand contextual dynamics. This enabled direct analysis of the generator, which reproduced at a single-trial level previous results shown only through more complex analyses at the trial average. Finally, we applied the per-trial inferred bias LFADS model to human intracortical brain computer interface recordings during attempted finger movements and speech. We show that modifying neural dynamics using linear operations of the per-trial bias addresses non-stationarity and identifies the extent of behavioral variability, problems known to plague BCI. We call our modification to LFADS as “contextual LFADS”.

Year:

2025

Understanding the cortical activity patterns driving dexterous upper limb motion has the potential to benefit a broad clinical population living with limited mobility through the development of novel brain-computer interface (BCI) technology. The present study examines the activity of ensembles of motor cortical neurons recorded using microelectrode arrays in the dominant hemisphere of two BrainGate clinical trial participants with cervical spinal cord injury as they attempted to perform a set of 48 different hand gestures. Although each participant displayed a unique organization of their respective neural latent spaces, it was possible to achieve classification accuracies of ~70% for all 48 gestures (and ~90% for sets of 10). Our results show that single unit ensemble activity recorded in a single hemisphere of human precentral gyrus has the potential to generate a wide range of gesture-related signals across both hands, providing an intuitive and diverse set of potential command signals for intracortical BCI use.

Year:

2024

Year:

2023

Collaborators (9)

Jaimie Henderson

Professor

Stanford University School of Medicine

UNITED STATES
View details

Nicholas Au Yong

Emory University School of Medicine

UNITED STATES
View details

Leigh Hochberg

Neurologist

Massachusetts General Hospital

UNITED STATES
View details

Chethan Pandarinath

Assistant Professor

Emory University

UNITED STATES
View details

Carrina Iacobacci

University of California, Davis

UNITED STATES
View details

Nishal Pradeepbhai Shah

Assistant Professor

Rice University

UNITED STATES
View details

Sergey Stavisky

Assistant Professor

University of California, Davis

UNITED STATES
View details

Scott Linderman

Assistant Professor

Stanford University

UNITED STATES
View details

David Brandman

Associate Professor

University of California, Davis

UNITED STATES
View details