Machine Learning for Neural Decoding

Glaser, Joshua I.; Benjamin, Ari S.; Chowdhury, Raeed H.; Perich, Matthew G.; Miller, Lee E.; Kording, Konrad

doi:10.1523/eneuro.0506-19.2020

Cited by 203 publications

(284 citation statements)

References 67 publications

Supporting

Mentioning

268

Contrasting

Unclassified

Order By: Relevance

“…We then divided the Ca 2+ imaging data and behavioural data from each 30 min trial into the first 15 min and last 15 min halves, which were designated training and test data, respectively. For each pair of behavioural parameter (position, speed, or motion direction) and the value of the Ca 2+ signal in the training data, we trained the decoders with one of eight different machine learning methods (Dense Feedforward Neural Network (DNN), Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM) network, Recurrent Neural Network (RNN), Support Vector Regression (SVR), Wiener Cascade (WC), Wiener Filter (WF), Extreme Gradient Boosting (XGB); the codes were obtained and modified from Glaser et al ., arXiv, 2018 63 ). The decoding accuracy of the position/motion direction is reported as the mean absolute error in the distance between the predicted and actual position/motion direction.…”

Section: Methodsmentioning

confidence: 99%

“…The data analysis was performed using custom code written in MATLAB (MathWorks, R2018a) and Python (Version 2.7.12). For decoding analysis by machine learning, we obtained Python code available at https://github.com/KordingLab/Neural_Decoding (used in Glaser et al ., arXiv, 2018 63 ) and modified them for our purpose. Raw imaging data in this study is uploaded at Systems Science Biological Dynamics repository (SSBD:repository; http://ssbd.qbic.riken.jp/set/20200603).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multiple types of navigational information are independently encoded in the population activities of the dentate gyrus neurons

Murano

Nakajima

Nakao

et al. 2020

Preprint

View full text Add to dashboard Cite

AbstractThe dentate gyrus (DG) plays critical roles in cognitive functions such as learning, memory, and spatial coding, and its dysfunction is implicated in various neuropsychiatric disorders. However, it remains largely unknown how information is represented in this region. Here, we recorded neuronal activity in the DG using Ca2+ imaging in freely moving mice and analysed this activity using machine learning. Although each individual neuron was weakly and diversely tuned to multiple information types, the activity patterns of populations of DG neurons enabled us to successfully decode position, speed, and motion direction in an open field as well as current and future location in a T-maze. In αCaMKII heterozygous knockout mice, an animal model of neuropsychiatric disorders, including intellectual disability and bipolar disorder, the decoding accuracy of position in the open field and future location in the T-maze were selectively reduced. These results suggest that multiple types of information are diffusely and independently distributed in DG neurons.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Multiple types of navigational information are independently encoded in the population activities of the dentate gyrus neurons

Murano

Nakajima

Nakao

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…60 Although some challenges (such as sample size) remain, 60 interest in the use of ML algorithms for decoding brain activity continues to increase. 61,62…”

Section: Decoding Mental States Based On Classificationmentioning

confidence: 99%

Multimodal Neuroimaging: Basic Concepts and Classification of Neuropsychiatric Diseases

et al. 2018

View full text Add to dashboard Cite

Neuroimaging techniques are widely used in neuroscience to visualize neural activity, to improve our understanding of brain mechanisms, and to identify biomarkers-especially for psychiatric diseases; however, each neuroimaging technique has several limitations. These limitations led to the development of multimodal neuroimaging (MN), which combines data obtained from multiple neuroimaging techniques, such as electroencephalography, functional magnetic resonance imaging, and yields more detailed information about brain dynamics. There are several types of MN, including visual inspection, data integration, and data fusion. This literature review aimed to provide a brief summary and basic information about MN techniques (data fusion approaches in particular) and classification approaches. Data fusion approaches are generally categorized as asymmetric and symmetric. The present review focused exclusively on studies based on symmetric data fusion methods (data-driven methods), such as independent component analysis and principal component analysis. Machine learning techniques have recently been introduced for use in identifying diseases and biomarkers of disease. The machine learning technique most widely used by neuroscientists is classification-especially support vector machine classification. Several studies differentiated patients with psychiatric diseases and healthy controls with using combined datasets. The common conclusion among these studies is that the prediction of diseases increases when combining data via MN techniques; however, there remain a few challenges associated with MN, such as sample size. Perhaps in the future N-way fusion can be used to combine multiple neuroimaging techniques or nonimaging predictors (eg, cognitive ability) to overcome the limitations of MN.

show abstract

“…Lastly, these systems employ supervised learning algorithms to learn the mapping from input neural signal to output effector movement [12]. The supervised learning paradigm requires a ground truth target label to be available at every instance of time to train an appropriate model.…”

Section: Introductionmentioning

confidence: 99%

Lightweight Reinforcement Algorithms for autonomous, scalable intra-cortical Brain Machine Interfaces

Shaikh

Sibindi

et al. 2020

Preprint

View full text Add to dashboard Cite

Intra-cortical Brain Machine Interfaces (iBMIs) with wireless capability could scale the number of recording channels by integrating an intention decoder to reduce data rates. However, the need for frequent retraining due to neural signal non-stationarity is a big impediment. This paper presents an alternate paradigm of online reinforcement learning (RL) with a binary evaluative feedback in iBMIs to tackle this issue. This paradigm eliminates time-consuming calibration procedures. Instead, it relies on updating the model on a sequential sample-by-sample basis based on an instantaneous evaluative binary feedback signal. However, batch updates of weight in popular deep networks is very resource consuming and incompatible with constraints of an implant. In this work, using offline open-loop analysis on pre-recorded data, we show application of a simple RL algorithm - Banditron -in discrete-state iBMIs and compare it against previously reported state of the art RL algorithms – Hebbian RL, Attention gated RL, deep Q-learning. Owing to its simplistic single-layer architecture, Banditron is found to yield at least two orders of magnitude of reduction in power dissipation compared to state of the art RL algorithms. At the same time, post-hoc analysis performed on four pre-recorded experimental datasets procured from the motor cortex of two non-human primates performing joystick-based movement-related tasks indicate Banditron performing significantly better than state of the art RL algorithms by at least 5%, 10%, 7% and 7% in experiments 1, 2, 3 and 4 respectively. Furthermore, we propose a non-linear variant of Banditron, Banditron-RP, which gives an average improvement of 6%, 2% in decoding accuracy in experiments 2,4 respectively with only a moderate increase in power consumption.

show abstract

Machine Learning for Neural Decoding

Cited by 203 publications

References 67 publications

Multiple types of navigational information are independently encoded in the population activities of the dentate gyrus neurons

Multiple types of navigational information are independently encoded in the population activities of the dentate gyrus neurons

Multimodal Neuroimaging: Basic Concepts and Classification of Neuropsychiatric Diseases

Lightweight Reinforcement Algorithms for autonomous, scalable intra-cortical Brain Machine Interfaces

Contact Info

Product

Resources

About