no code implementations • 9 Feb 2024 • Feiyang Wu, Zhaoyuan Gu, Ye Zhao, Anqi Wu
We implement variants of our methods, conduct experiments on the MuJoCo benchmark, and apply our methods to the Cassie robot locomotion problem.
no code implementations • 5 Feb 2024 • Weihan Li, Chengrui Li, Yule Wang, Anqi Wu
Consequently, the model achieves a linear inference cost over time points and provides an interpretable low-dimensional representation, revealing communication directions across brain regions and separating oscillatory communications into different frequency bands.
no code implementations • 2 Feb 2024 • Chengrui Li, Weihan Li, Yule Wang, Anqi Wu
For (1), we propose a new differentiable POGLM, which enables the pathwise gradient estimator, better than the score function gradient estimator used in existing works.
no code implementations • 4 Nov 2023 • Chengrui Li, Yule Wang, Weihan Li, Anqi Wu
Maximizing the log-likelihood is a crucial aspect of learning latent variable models, and variational inference (VI) stands as the commonly adopted method.
no code implementations • 23 Oct 2023 • Chengrui Li, Soon Ho Kim, Chris Rodgers, Hannah Choi, Anqi Wu
We introduce both a Gaussian prior and a one-hot prior over the GLM in each state.
no code implementations • 28 Sep 2023 • Feiyang Wu, Zhaoyuan Gu, Hanran Wu, Anqi Wu, Ye Zhao
Enabling bipedal walking robots to learn how to maneuver over highly uneven, dynamically changing terrains is challenging due to the complexity of robot dynamics and interacted environments.
1 code implementation • 9 Jun 2023 • Yule Wang, Zijing Wu, Chengrui Li, Anqi Wu
Specifically, the latent dynamics structures of the source domain are first extracted by a diffusion model.
1 code implementation • 3 Jun 2023 • Han Yi Chiu, Liang Zhao, Anqi Wu
However, traditional approaches for integrating FC and SC overlook the dynamical variations, which stand a great chance to over-generalize the brain neural network.
1 code implementation • 11 Nov 2022 • Chengrui Li, Anqi Wu
To deal with very noisy data with weak correlations, we propose two solutions -- blockwise and geodesic -- to make use of locally correlated data points and provide better and numerically more stable latent estimations.
no code implementations • 14 Apr 2022 • Ari Blau, Christoph Gebhardt, Andres Bendesky, Liam Paninski, Anqi Wu
Multi-animal pose estimation is essential for studying animals' social behaviors in neuroscience and neuroethology.
no code implementations • 12 Oct 2021 • Anqi Wu
Researchers have been facing a difficult problem that data generation mechanisms could be influenced by internal or external factors leading to the training and test data with quite different distributions, consequently traditional classification or regression from the training set is unable to achieve satisfying results on test data.
1 code implementation • 9 Sep 2021 • Felix Pei, Joel Ye, David Zoltowski, Anqi Wu, Raeed H. Chowdhury, Hansem Sohn, Joseph E. O'Doherty, Krishna V. Shenoy, Matthew T. Kaufman, Mark Churchland, Mehrdad Jazayeri, Lee E. Miller, Jonathan Pillow, Il Memming Park, Eva L. Dyer, Chethan Pandarinath
We curate four datasets of neural spiking activity from cognitive, sensory, and motor areas to promote models that apply to the wide variety of activity seen across these areas.
1 code implementation • NeurIPS 2020 • Anqi Wu, E. Kelly Buchanan, Matthew Whiteway, Michael Schartner, Guido Meijer, Jean-Paul Noel, Erica Rodriguez, Claire Everett, Amy Norovich, Evan Schaffer, Neeli Mishra, C. Daniel Salzman, Dora Angelaki, Andrés Bendesky, The International Brain Laboratory The International Brain Laboratory, John P. Cunningham, Liam Paninski
Noninvasive behavioral tracking of animals is crucial for many scientific investigations.
no code implementations • 11 May 2020 • Ming Bo Cai, Michael Shvartsman, Anqi Wu, Hejia Zhang, Xia Zhu
With the wide adoption of functional magnetic resonance imaging (fMRI) by cognitive neuroscience researchers, large volumes of brain imaging data have been accumulated in recent years.
1 code implementation • 1 Jul 2019 • Qi She, Anqi Wu
In the experiment, we show that our model outperforms other state-of-the-art methods in reconstructing insightful latent dynamics from both simulated and experimental neural datasets with either Gaussian or Poisson observations, especially in the low-sample scenario.
no code implementations • NeurIPS 2018 • Anqi Wu, Stan Pashkovski, Sandeep R. Datta, Jonathan W. Pillow
Our approach is based on the Gaussian process latent variable model, and seeks to map odorants to points in a low-dimensional embedding space, where distances between points in the embedding space relate to the similarity of population responses they elicit.
3 code implementations • ICLR 2019 • Anqi Wu, Sebastian Nowozin, Edward Meeds, Richard E. Turner, José Miguel Hernández-Lobato, Alexander L. Gaunt
We provide two innovations that aim to turn VB into a robust inference tool for Bayesian neural networks: first, we introduce a novel deterministic method to approximate moments in neural networks, eliminating gradient variance; second, we introduce a hierarchical prior for parameters and a novel Empirical Bayes procedure for automatically selecting prior variances.
no code implementations • NeurIPS 2017 • Anqi Wu, Nicholas G. Roy, Stephen Keeley, Jonathan W. Pillow
We apply the model to spike trains recorded from hippocampal place cells and show that it compares favorably to a variety of previous methods for latent structure discovery, including variational auto-encoder (VAE) based methods that parametrize the nonlinear mapping from latent space to spike rates with a deep neural network.
1 code implementation • 28 Nov 2017 • Anqi Wu, Oluwasanmi Koyejo, Jonathan W. Pillow
Our approach represents a hierarchical extension of the relevance determination framework, where we add a transformed Gaussian process to model the dependencies between the prior variances of regression weights.
no code implementations • 31 Mar 2017 • Anqi Wu, Mikio C. Aoi, Jonathan W. Pillow
An exciting branch of machine learning research focuses on methods for learning, optimizing, and integrating unknown functions that are difficult or costly to evaluate.
no code implementations • NeurIPS 2015 • Anqi Wu, Il Memming Park, Jonathan W. Pillow
Subunit models provide a powerful yet parsimonious description of neural spike responses to complex stimuli.
no code implementations • NeurIPS 2014 • Anqi Wu, Mijung Park, Oluwasanmi O. Koyejo, Jonathan W. Pillow
Classical sparse regression methods, such as the lasso and automatic relevance determination (ARD), model parameters as independent a priori, and therefore do not exploit such dependencies.