Using adversarial networks to extend brain computer interface decoding accuracy over time

eLife, Год журнала: 2023, Номер 12

Опубликована: Авг. 23, 2023

Existing intracortical brain computer interfaces (iBCIs) transform neural activity into control signals capable of restoring movement to persons with paralysis. However, the accuracy 'decoder' at heart iBCI typically degrades over time due turnover recorded neurons. To compensate, decoders can be recalibrated, but this requires user spend extra and effort provide necessary data, then learn new dynamics. As neurons change, one think underlying intent signal being expressed in changing coordinates. If a mapping computed between different coordinate systems, it may possible stabilize original decoder's from behavior without recalibration. We previously proposed method based on Generalized Adversarial Networks (GANs), called 'Adversarial Domain Adaptation Network' (ADAN), which aligns distributions latent within low-dimensional manifolds. we tested ADAN only very limited dataset. Here propose Cycle-Consistent (Cycle-GAN), full-dimensional recordings. both Cycle-GAN data multiple monkeys behaviors compared them third, quite Procrustes alignment axes provided by Factor Analysis. All three methods are unsupervised require little making practical real life. Overall, had best performance was easier train more robust than ADAN, ideal for stabilizing systems time.

Язык: Английский

---

Decoding motor plans using a closed-loop ultrasonic brain–machine interface

Nature Neuroscience, Год журнала: 2023, Номер 27(1), С. 196 - 207

Опубликована: Ноя. 30, 2023

Brain-machine interfaces (BMIs) enable people living with chronic paralysis to control computers, robots and more nothing but thought. Existing BMIs have trade-offs across invasiveness, performance, spatial coverage spatiotemporal resolution. Functional ultrasound (fUS) neuroimaging is an emerging technology that balances these attributes may complement existing BMI recording technologies. In this study, we use fUS demonstrate a successful implementation of closed-loop ultrasonic BMI. We streamed data from the posterior parietal cortex two rhesus macaque monkeys while they performed eye hand movements. After training, controlled up eight movement directions using also developed method for pretraining previous sessions. This enabled immediate on subsequent days, even those occurred months apart, without requiring extensive recalibration. These findings establish feasibility BMIs, paving way new class less-invasive (epidural) generalize extended time periods promise restore function neurological impairments.

Язык: Английский

---

Assistive sensory-motor perturbations influence learned neural representations

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Март 20, 2024

Task errors are used to learn and refine motor skills. We investigated how task assistance influences learned neural representations using Brain-Computer Interfaces (BCIs), which map activity into movement via a decoder. analyzed cortex as monkeys practiced BCI with decoder that adapted improve or maintain performance over days. The dimensionality of the population neurons controlling remained constant increased learning, counter expected trends from learning. Yet, time, information was contained in smaller subset modes. Moreover, ultimately stored modes occupied small fraction variance. An artificial network model suggests adaptive decoders contribute forming these compact representations. Our findings show assistive manipulate error for long-term learning computations, like credit assignment, informs our understanding has implications designing real-world BCIs.

Язык: Английский

---

Deep transfer learning-based decoder calibration for intracortical brain-machine interfaces

Computers in Biology and Medicine, Год журнала: 2025, Номер 192, С. 110231 - 110231

Опубликована: Апрель 21, 2025

Язык: Английский

---

Stabilizing brain-computer interfaces through alignment of latent dynamics

Nature Communications, Год журнала: 2025, Номер 16(1)

Опубликована: Май 19, 2025

Intracortical brain-computer interfaces (iBCIs) restore motor function to people with paralysis by translating brain activity into control signals for external devices. In current iBCIs, instabilities at the neural interface result in a degradation of decoding performance, which necessitates frequent supervised recalibration using new labeled data. One potential solution is use latent manifold structure that underlies population facilitate stable mapping between and behavior. Recent efforts unsupervised approaches have improved iBCI stability this principle; however, existing methods treat each time step as an independent sample do not account dynamics. Dynamics been used enable high-performance prediction movement intention, may also help improve stabilization. Here, we present platform Nonlinear Manifold Alignment (NoMAD), stabilizes recurrent network models NoMAD uses distribution alignment update nonstationary data consistent set dynamics, thereby providing input decoder. applications from monkey cortex collected during tasks, enables accurate behavioral unparalleled over weeks- months-long timescales without any recalibration.

Язык: Английский

---

Neural Data Transformer 2: Multi-context Pretraining for Neural Spiking Activity

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2023, Номер unknown

Опубликована: Сен. 22, 2023

Abstract The neural population spiking activity recorded by intracortical brain-computer interfaces (iBCIs) contain rich structure. Current models of such are largely prepared for individual experimental contexts, restricting data volume to that collectable within a single session and limiting the effectiveness deep networks (DNNs). purported challenge in aggregating is pervasiveness context-dependent shifts distributions. However, large scale unsupervised pretraining nature spans heterogeneous data, has proven be fundamental recipe successful representation learning across learning. We thus develop Neural Data Transformer 2 (NDT2), spatiotemporal activity, demonstrate can leverage motor BCI datasets span sessions, subjects, tasks. NDT2 enables rapid adaptation novel contexts downstream decoding tasks opens path deployment pretrained DNNs iBCI control. Code: https://github.com/joel99/context_general_bci

Язык: Английский

---

Brain–Computer Interfaces with Intracortical Implants for Motor and Communication Functions Compensation: Review of Recent Developments

Sovremennye tehnologii v medicine, Год журнала: 2024, Номер 16(1), С. 78 - 78

Опубликована: Фев. 28, 2024

Brain-computer interfaces allow the exchange of data between brain and an external device, bypassing muscular system. Clinical studies invasive brain-computer interface technologies have been conducted for over 20 years. During this time, there has a continuous improvement approaches to neuronal signal processing in order improve quality control devices. Currently, with intracortical implants completely paralyzed patients robotic limbs self-service, use computer or tablet, type text, reproduce speech at optimal speed. Studies regularly provide new fundamental on functioning central nervous In recent years, breakthrough discoveries achievements annually made sphere. This review analyzes results clinical experiments implants, provides information stages technology development, its main achievements.

Язык: Английский

---

A new approach for neural decoding by inspiring of hyperdimensional computing for implantable intra-cortical BMIs

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Окт. 7, 2024

In the field of Brain Machine Interface (BMI), process translating motor intention into a machine command is denoted as decoding. However, despite recent advancements, decoding remains formidable challenge within BMI. The utilization current algorithms in BMI often involves computational complexity and requires use computers. This primarily due to reliance on mathematical models address issue perform subsequent output calculations. Unfortunately, computers are not feasible for implantable systems their size power consumption. To this predicament, study proposes pioneering approach inspired by hyperdimensional computing. first identifying pattern each stimulus considering normal firing rate distribution neuron. Subsequently, newly observed input compared with patterns detected at moment algorithm, which shares similarities computing, identifies most similar final output. reduces dependence models. efficacy method assessed through an authentic dataset acquired from Frontal Eye Field (FEF) two male rhesus monkeys. space encompasses eight possible angles. results demonstrate accuracy 51.5% while exhibiting significantly low complexity, involving mere 2050 adder operators. Furthermore, proposed algorithm implemented field-programmable gate array (FPGA) ASIC designe standard CMOS 180 nm technology, underscoring its suitability real-time applications. implementation required only 2.3 Kbytes RAM, occupied area 2.2 mm

Язык: Английский

---

Measuring instability in chronic human intracortical neural recordings towards stable, long-term brain-computer interfaces

Communications Biology, Год журнала: 2024, Номер 7(1)

Опубликована: Окт. 21, 2024

Язык: Английский

---

From monkeys to humans: observation-based EMG brain–computer interface decoders for humans with paralysis

Journal of Neural Engineering, Год журнала: 2023, Номер 20(5), С. 056040 - 056040

Опубликована: Окт. 1, 2023

. Intracortical brain-computer interfaces (iBCIs) aim to enable individuals with paralysis control the movement of virtual limbs and robotic arms. Because patients' prevents training a direct neural activity limb decoder, most iBCIs rely on 'observation-based' decoding in which patient watches moving cursor while mentally envisioning making movement. However, this reliance observed target motion for decoder development precludes its application prediction unobservable motor output like muscle activity. Here, we ask whether recordings from surrogate individual performing same as iBCI can be used an decoder.

Язык: Английский

---