Search Results for author:
Found 29 papers, 10 papers with code
Jointly learning visual motion and confidence from local patches in event cameras
In the task of recovering pan-tilt ego velocities from events, we show that each individual confident local prediction of our network can be expected to be as accurate as state of the art optimization approaches which utilize the full image.
Large-scale variational Gaussian state-space models
We introduce an amortized variational inference algorithm and structured variational approximation for state-space models with nonlinear dynamics driven by Gaussian noise.
Persistent learning signals and working memory without continuous attractors
Our theory has broad implications for the design of artificial learning systems and makes predictions about observable signatures of biological neural dynamics that can support temporal dependence learning and working memory.
Linear Time GPs for Inferring Latent Trajectories from Neural Spike Trains
In this work, we propose cvHM, a general inference framework for latent GP models leveraging Hida-Mat\'ern kernels and conjugate computation variational inference (CVI).
Real-Time Variational Method for Learning Neural Trajectory and its Dynamics
Latent variable models have become instrumental in computational neuroscience for reasoning about neural computation.
Spectral learning of Bernoulli linear dynamical systems models
Latent linear dynamical systems with Bernoulli observations provide a powerful modeling framework for identifying the temporal dynamics underlying binary time series data, which arise in a variety of contexts such as binary decision-making and discrete stochastic processes (e. g., binned neural spike trains).
Metastable dynamics of neural circuits and networks
In this article, we review the experimental evidence for neural metastable dynamics together with theoretical approaches to the study of metastable activity in neural circuits.
Gating Mechanisms Underlying Sequence-to-Sequence Working Memory
We explain the learned mechanisms by which this network holds memory and extracts information from memory, and how gating is a natural architectural component to achieve these structures.
Neural Latents Benchmark '21: Evaluating latent variable models of neural population activity
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.
Hida-Matérn Kernel
We present the class of Hida-Mat\'ern kernels, which is the canonical family of covariance functions over the entire space of stationary Gauss-Markov Processes.
On 1/n neural representation and robustness
In this work, we investigate the latter by juxtaposing experimental results regarding the covariance spectrum of neural representations in the mouse V1 (Stringer et al) with artificial neural networks.
Rescuing neural spike train models from bad MLE
The standard approach to fitting an autoregressive spike train model is to maximize the likelihood for one-step prediction.
Non-parametric generalized linear model
However, obtaining a satisfactory fit often requires burdensome model selection and fine tuning the form of the basis functions and their temporal span.
Streaming Variational Monte Carlo
Nonlinear state-space models are powerful tools to describe dynamical structures in complex time series.
Gated recurrent units viewed through the lens of continuous time dynamical systems
As a result, it is both difficult to know a priori how successful a GRU network will perform on a given task, and also their capacity to mimic the underlying behavior of their biological counterparts.
The Expressive Power of Gated Recurrent Units as a Continuous Dynamical System
Gated recurrent units (GRUs) were inspired by the common gated recurrent unit, long short-term memory (LSTM), as a means of capturing temporal structure with less complex memory unit architecture.
Tree-Structured Recurrent Switching Linear Dynamical Systems for Multi-Scale Modeling
Many real-world systems studied are governed by complex, nonlinear dynamics.
Information Geometry of Orthogonal Initializations and Training
Recently mean field theory has been successfully used to analyze properties of wide, random neural networks.
Variational online learning of neural dynamics
It brings the challenge of learning both latent neural state and the underlying dynamical system because neither is known for neural systems a priori.
Variational Latent Gaussian Process for Recovering Single-Trial Dynamics from Population Spike Trains
In the V1 dataset, we find that vLGP achieves substantially higher performance than previous methods for predicting omitted spike trains, as well as capturing both the toroidal topology of visual stimuli space, and the noise-correlation.
Convolutional spike-triggered covariance analysis for neural subunit models
Subunit models provide a powerful yet parsimonious description of neural spike responses to complex stimuli.
Black box variational inference for state space models
These models have the advantage of learning latent structure both from noisy observations and from the temporal ordering in the data, where it is assumed that meaningful correlation structure exists across time.
Universal models for binary spike patterns using centered Dirichlet processes
We also establish a condition for equivalence between the cascade-logistic and the 2nd-order maxent or "Ising'' model, making cascade-logistic a reasonable choice for base measure in a universal model.
Bayesian entropy estimation for binary spike train data using parametric prior knowledge
Shannon's entropy is a basic quantity in information theory, and a fundamental building block for the analysis of neural codes.
Spectral methods for neural characterization using generalized quadratic models
The quadratic form characterizes the neuron's stimulus selectivity in terms of a set linear receptive fields followed by a quadratic combination rule, and the invertible nonlinearity maps this output to the desired response range.
Bayesian Extensions of Kernel Least Mean Squares
The kernel least mean squares (KLMS) algorithm is a computationally efficient nonlinear adaptive filtering method that "kernelizes" the celebrated (linear) least mean squares algorithm.
Bayesian Entropy Estimation for Countable Discrete Distributions
The Pitman-Yor process, a generalization of Dirichlet process, provides a tractable prior distribution over the space of countably infinite discrete distributions, and has found major applications in Bayesian non-parametric statistics and machine learning.
Information Theory Information Theory
Bayesian estimation of discrete entropy with mixtures of stick-breaking priors
We consider the problem of estimating Shannon's entropy H in the under-sampled regime, where the number of possible symbols may be unknown or countably infinite.
Bayesian Spike-Triggered Covariance Analysis
We describe an empirical Bayes method for selecting the number of features, and extend the model to accommodate an arbitrary elliptical nonlinear response function, which results in a more powerful and more flexible model for feature space inference.
