Latent Factors and Dynamics in Motor Cortex and Their Application to Brain–Machine Interfaces

Pandarinath, Chethan; Ames, K. Cora; Russo, Abigail A.; Farshchiansadegh, Ali; Miller, Lee E.; Dyer, Eva L.; Kao, Jennifer L.

doi:10.1523/jneurosci.1669-18.2018

Cited by 92 publications

(45 citation statements)

References 113 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The patterns of the attention weights suggested that the previous neural activity is essential for neural decoding during the preparatory period and execution of the movement, whereas the most recent neural activity is essential during the release phase. This finding is consistent with observations made in [ 5 , 36 , 37 , 38 ], where preparatory neural activity served as an initial condition for subsequent activity patterns. For the instructed delayed reach-to-grasp task, all findings from the three RNN-based neural decoders suggest that the preparatory neural activity is essential during the preparatory period and the execution of the movement, whereas the most recent neural activity is essential during the release phase.…”

Section: Discussionsupporting

confidence: 92%

“…Conventional neural decoding techniques process well-segmented neural activities in previous time windows where task-related information is likely encoded as spiking sequences. Thus, neural decoding may benefit from continuous neural activity because movement intention often occurs before execution [ 5 ]. Therefore, a sequence of spike count vectors from many preceding time windows is usually adopted to capture the neural response dynamics [ 6 ] and improve the decoding accuracy [ 7 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Selection of Essential Neural Activity Timesteps for Intracortical Brain–Computer Interface Based on Recurrent Neural Network

Yang

Huang

et al. 2021

Sensors

View full text Add to dashboard Cite

Intracortical brain–computer interfaces (iBCIs) translate neural activity into control commands, thereby allowing paralyzed persons to control devices via their brain signals. Recurrent neural networks (RNNs) are widely used as neural decoders because they can learn neural response dynamics from continuous neural activity. Nevertheless, excessively long or short input neural activity for an RNN may decrease its decoding performance. Based on the temporal attention module exploiting relations in features over time, we propose a temporal attention-aware timestep selection (TTS) method that improves the interpretability of the salience of each timestep in an input neural activity. Furthermore, TTS determines the appropriate input neural activity length for accurate neural decoding. Experimental results show that the proposed TTS efficiently selects 28 essential timesteps for RNN-based neural decoders, outperforming state-of-the-art neural decoders on two nonhuman primate datasets (R2=0.76±0.05 for monkey Indy and CC=0.91±0.01 for monkey N). In addition, it reduces the computation time for offline training (reducing 5–12%) and online prediction (reducing 16–18%). When visualizing the attention mechanism in TTS, the preparatory neural activity is consecutively highlighted during arm movement, and the most recent neural activity is highlighted during the resting state in nonhuman primates. Selecting only a few essential timesteps for an RNN-based neural decoder provides sufficient decoding performance and requires only a short computation time.

show abstract

Section: Discussionsupporting

confidence: 92%

Section: Introductionmentioning

confidence: 99%

Selection of Essential Neural Activity Timesteps for Intracortical Brain–Computer Interface Based on Recurrent Neural Network

Yang

Huang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…An alternative approach for latent trajectory modeling is to estimate the underlying linear dynamics of the latent state (Macke et al, 2011; Churchland et al, 2012; Pandarinath et al, 2018a). While the classical Kalman filter is the most thoroughly developed method for estimating the transition matrix in a linear dynamical system, a more appropriate generative model for neurons is the Poisson linear dynamical system (PLDS, Figure 3A) (Macke et al, 2011), which substitutes Poisson observations for the Gaussian emissions in the Kalman filter to directly model observed spike counts.…”

Section: Latent Factor Modelsmentioning

confidence: 99%

Probabilistic Encoding Models for Multivariate Neural Data

Triplett

Goodhill

2019

Front. Neural Circuits

View full text Add to dashboard Cite

A key problem in systems neuroscience is to characterize how populations of neurons encode information in their patterns of activity. An understanding of the encoding process is essential both for gaining insight into the origins of perception and for the development of brain-computer interfaces. However, this characterization is complicated by the highly variable nature of neural responses, and thus usually requires probabilistic methods for analysis. Drawing on techniques from statistical modeling and machine learning, we review recent methods for extracting important variables that quantitatively describe how sensory information is encoded in neural activity. In particular, we discuss methods for estimating receptive fields, modeling neural population dynamics, and inferring low dimensional latent structure from a population of neurons, in the context of both electrophysiology and calcium imaging data.

show abstract

“…There exist many quantitative methods for relating population activity and computation (e.g., [22][23][24] ).…”

mentioning

confidence: 99%

Neural trajectories in the supplementary motor area and primary motor cortex exhibit distinct geometries, compatible with different classes of computation

Russo

Khajeh

Bittner

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

The supplementary motor area (SMA) is believed to contribute to higher-order aspects of motor control.To examine this contribution, we employed a novel cycling task and leveraged an emerging strategy: testing whether population trajectories possess properties necessary for a hypothesized class of computations. We found that, at the single-neuron level, SMA exhibited multiple response features absent in M1. We hypothesized that these diverse features might contribute, at the population level, to avoidance of 'population trajectory divergence' -ensuring that two trajectories never followed the same path before separating. Trajectory divergence was indeed avoided in SMA but not in M1. Network simulations confirmed that low trajectory divergence is necessary when guidance of future action depends upon internally tracking contextual factors. Furthermore, the empirical trajectory geometryhelical in SMA versus elliptical in M1 -was naturally reproduced by networks that did, versus did not, internally track context. 2Relative to primary motor cortex (M1), SMA activity is less coupled to actions of a specific body part 10-12 .3 Instead, SMA computations appear related to learned sensory-motor associations 11 , reward 4 anticipation 13 , internal initiation and guidance of movement 3,14 , movement timing 15,16 , and movement 5 sequencing 7,17,18 . Single-neuron responses in SMA reflect a variety of task-specific contingencies. For 6 example, in a sequence of three movements, a neuron may burst only when pulling precedes pushing. 7Another neuron might respond before the third movement regardless of the particular sequence 19 . 8 Different response features are observed in different tasks. Single SMA neurons exhibit a mixture of 9 ramping and rhythmic activity during an interval timing task 20 , and the SMA population exhibits 10 amplitude-modulated circular trajectories during rhythmic tapping 21 . A common thread linking prior 11 studies is that SMA computations are hypothesized to be critical when pending action depends upon 12 internal, abstract, and/or contextual factors. An important challenge is linking these high-level ideas to 13 network-level implementations. What general properties should activity exhibit in networks performing 14 the hypothesized class of computations? 15There exist many quantitative methods for relating population activity and computation (e.g., [22][23][24] ). 16These include decoding key hypothesized signals (e.g., via regression 25 ), or directly comparing empirical 17 and simulated population activity (e.g., via canonical correlation 26 ). An emerging strategy is to consider 18 the geometry of the population response: the arrangement of population states across conditions 23,27,28 19 and/or the shape traced by activity in neural state-space 15,26,[29][30][31][32][33][34][35][36] . A given geometry may be consistent 20 with some types of computation but not others 37 . An advantage of this approach is that it is sometimes 21 possible to measure geometric properties that are expected to hold f...

show abstract

Latent Factors and Dynamics in Motor Cortex and Their Application to Brain–Machine Interfaces

Cited by 92 publications

References 113 publications

Selection of Essential Neural Activity Timesteps for Intracortical Brain–Computer Interface Based on Recurrent Neural Network

Selection of Essential Neural Activity Timesteps for Intracortical Brain–Computer Interface Based on Recurrent Neural Network

Probabilistic Encoding Models for Multivariate Neural Data

Neural trajectories in the supplementary motor area and primary motor cortex exhibit distinct geometries, compatible with different classes of computation

Contact Info

Product

Resources

About