Výsledky vyhledávání - "Perich, Matthew G"

Report

Expressivity of Neural Networks with Random Weights and Learned Biases

Autor: Williams, Ezekiel, Ryoo, Avery Hee-Woon, Jiralerspong, Thomas, Payeur, Alexandre, Perich, Matthew G., Mazzucato, Luca, Lajoie, Guillaume

Landmark universal function approximation results for neural networks with trained weights and biases provided impetus for the ubiquitous use of neural networks as learning models in Artificial Intelligence (AI) and neuroscience. Recent work has push

Externí odkaz: http://arxiv.org/abs/2407.00957

Zobrazit plný text záznamu

Report

A Unified, Scalable Framework for Neural Population Decoding

Autor: Azabou, Mehdi, Arora, Vinam, Ganesh, Venkataramana, Mao, Ximeng, Nachimuthu, Santosh, Mendelson, Michael J., Richards, Blake, Perich, Matthew G., Lajoie, Guillaume, Dyer, Eva L.

Our ability to use deep learning approaches to decipher neural activity would likely benefit from greater scale, in terms of both model size and datasets. However, the integration of many neural recordings into one unified model is challenging, as ea

Externí odkaz: http://arxiv.org/abs/2310.16046

Zobrazit plný text záznamu

Report

Capturing cross-session neural population variability through self-supervised identification of consistent neuron ensembles

Autor: Jude, Justin, Perich, Matthew G., Miller, Lee E., Hennig, Matthias H.

Decoding stimuli or behaviour from recorded neural activity is a common approach to interrogate brain function in research, and an essential part of brain-computer and brain-machine interfaces. Reliable decoding even from small neural populations is

Externí odkaz: http://arxiv.org/abs/2205.09829

Zobrazit plný text záznamu

Report

Robust alignment of cross-session recordings of neural population activity by behaviour via unsupervised domain adaptation

Autor: Jude, Justin, Perich, Matthew G, Miller, Lee E, Hennig, Matthias H

Neural population activity relating to behaviour is assumed to be inherently low-dimensional despite the observed high dimensionality of data recorded using multi-electrode arrays. Therefore, predicting behaviour from neural population recordings has

Externí odkaz: http://arxiv.org/abs/2202.06159

Zobrazit plný text záznamu

Report

Targeted Neural Dynamical Modeling

Autor: Hurwitz, Cole, Srivastava, Akash, Xu, Kai, Jude, Justin, Perich, Matthew G., Miller, Lee E., Hennig, Matthias H.

Latent dynamics models have emerged as powerful tools for modeling and interpreting neural population activity. Recently, there has been a focus on incorporating simultaneously measured behaviour into these models to further disentangle sources of ne

Externí odkaz: http://arxiv.org/abs/2110.14853

Zobrazit plný text záznamu

Report

Machine learning for neural decoding

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

Despite rapid advances in machine learning tools, the majority of neural decoding approaches still use traditional methods. Modern machine learning tools, which are versatile and easy to use, have the potential to significantly improve decoding perfo

Externí odkaz: http://arxiv.org/abs/1708.00909

Zobrazit plný text záznamu