Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Azabou, Mehdi"'
Autor:
Zhang, Yizi, Wang, Yanchen, Jimenez-Beneto, Donato, Wang, Zixuan, Azabou, Mehdi, Richards, Blake, Winter, Olivier, Laboratory, International Brain, Dyer, Eva, Paninski, Liam, Hurwitz, Cole
Neuroscience research has made immense progress over the last decade, but our understanding of the brain remains fragmented and piecemeal: the dream of probing an arbitrary brain region and automatically reading out the information encoded in its neu
Externí odkaz:
http://arxiv.org/abs/2407.14668
Graph neural networks are typically trained on individual datasets, often requiring highly specialized models and extensive hyperparameter tuning. This dataset-specific approach arises because each graph dataset often has unique node features and div
Externí odkaz:
http://arxiv.org/abs/2407.11907
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
Autor:
Azabou, Mehdi, Ganesh, Venkataramana, Thakoor, Shantanu, Lin, Chi-Heng, Sathidevi, Lakshmi, Liu, Ran, Valko, Michal, Veličković, Petar, Dyer, Eva L.
Message passing neural networks have shown a lot of success on graph-structured data. However, there are many instances where message passing can lead to over-smoothing or fail when neighboring nodes belong to different classes. In this work, we intr
Externí odkaz:
http://arxiv.org/abs/2308.09198
Autor:
Azabou, Mehdi, Mendelson, Michael, Ahad, Nauman, Sorokin, Maks, Thakoor, Shantanu, Urzay, Carolina, Dyer, Eva L.
Natural behavior consists of dynamics that are complex and unpredictable, especially when trying to predict many steps into the future. While some success has been found in building representations of behavior under constrained or simplified task-bas
Externí odkaz:
http://arxiv.org/abs/2303.08811
Autor:
Mendelson, Michael J, Azabou, Mehdi, Jacob, Suma, Grissom, Nicola, Darrow, David, Ebitz, Becket, Herman, Alexander, Dyer, Eva L.
Human behavior is incredibly complex and the factors that drive decision making--from instinct, to strategy, to biases between individuals--often vary over multiple timescales. In this paper, we design a predictive framework that learns representatio
Externí odkaz:
http://arxiv.org/abs/2302.11023
Autor:
Quesada, Jorge, Sathidevi, Lakshmi, Liu, Ran, Ahad, Nauman, Jackson, Joy M., Azabou, Mehdi, Xiao, Jingyun, Liding, Christopher, Jin, Matthew, Urzay, Carolina, Gray-Roncal, William, Johnson, Erik C., Dyer, Eva L.
There are multiple scales of abstraction from which we can describe the same image, depending on whether we are focusing on fine-grained details or a more global attribute of the image. In brain mapping, learning to automatically parse images to buil
Externí odkaz:
http://arxiv.org/abs/2301.00345
Autor:
Azabou, Mehdi, Mendelson, Michael, Sorokin, Maks, Thakoor, Shantanu, Ahad, Nauman, Urzay, Carolina, Dyer, Eva L.
Natural behavior consists of dynamics that are both unpredictable, can switch suddenly, and unfold over many different timescales. While some success has been found in building representations of behavior under constrained or simplified task-based co
Externí odkaz:
http://arxiv.org/abs/2206.07041
Complex time-varying systems are often studied by abstracting away from the dynamics of individual components to build a model of the population-level dynamics from the start. However, when building a population-level description, it can be easy to l
Externí odkaz:
http://arxiv.org/abs/2206.06131
Autor:
Liu, Ran, Azabou, Mehdi, Dabagia, Max, Lin, Chi-Heng, Azar, Mohammad Gheshlaghi, Hengen, Keith B., Valko, Michal, Dyer, Eva L.
Meaningful and simplified representations of neural activity can yield insights into how and what information is being processed within a neural circuit. However, without labels, finding representations that reveal the link between the brain and beha
Externí odkaz:
http://arxiv.org/abs/2111.02338