Expressive probabilistic sampling in recurrent neural networks

• URL: http://arxiv.org/abs/2308.11809v3
• Date: Tue, 14 Nov 2023 21:07:33 GMT
• Title: Expressive probabilistic sampling in recurrent neural networks
• Authors: Shirui Chen, Linxing Preston Jiang, Rajesh P. N. Rao, Eric Shea-Brown
• Abstract summary: We show that firing rate dynamics of a recurrent neural circuit with a separate set of output units can sample from an arbitrary probability distribution. We propose an efficient training procedure based on denoising score matching that finds recurrent and output weights such that the RSN implements Langevin sampling.
• Score: 4.3900330990701235
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In sampling-based Bayesian models of brain function, neural activities are assumed to be samples from probability distributions that the brain uses for probabilistic computation. However, a comprehensive understanding of how mechanistic models of neural dynamics can sample from arbitrary distributions is still lacking. We use tools from functional analysis and stochastic differential equations to explore the minimum architectural requirements for $\textit{recurrent}$ neural circuits to sample from complex distributions. We first consider the traditional sampling model consisting of a network of neurons whose outputs directly represent the samples (sampler-only network). We argue that synaptic current and firing-rate dynamics in the traditional model have limited capacity to sample from a complex probability distribution. We show that the firing rate dynamics of a recurrent neural circuit with a separate set of output units can sample from an arbitrary probability distribution. We call such circuits reservoir-sampler networks (RSNs). We propose an efficient training procedure based on denoising score matching that finds recurrent and output weights such that the RSN implements Langevin sampling. We empirically demonstrate our model's ability to sample from several complex data distributions using the proposed neural dynamics and discuss its applicability to developing the next generation of sampling-based brain models.

Related papers

• Training Guarantees of Neural Network Classification Two-Sample Tests by Kernel Analysis [58.435336033383145]
  We construct and analyze a neural network two-sample test to determine whether two datasets came from the same distribution. We derive the theoretical minimum training time needed to ensure the NTK two-sample test detects a deviation-level between the datasets. We show that the statistical power associated with the neural network two-sample test goes to 1 as the neural network training samples and test evaluation samples go to infinity.
  arXiv  Detail & Related papers  (2024-07-05T18:41:16Z)
• Diffusion models as probabilistic neural operators for recovering unobserved states of dynamical systems [49.2319247825857]
  We show that diffusion-based generative models exhibit many properties favourable for neural operators. We propose to train a single model adaptable to multiple tasks, by alternating between the tasks during training.
  arXiv  Detail & Related papers  (2024-05-11T21:23:55Z)
• On Feynman--Kac training of partial Bayesian neural networks [1.6474447977095783]
  Partial Bayesian neural networks (pBNNs) were shown to perform competitively with full Bayesian neural networks. We propose an efficient sampling-based training strategy, wherein the training of a pBNN is formulated as simulating a Feynman--Kac model. We show that our proposed training scheme outperforms the state of the art in terms of predictive performance.
  arXiv  Detail & Related papers  (2023-10-30T15:03:15Z)
• Generative Neural Fields by Mixtures of Neural Implicit Functions [43.27461391283186]
  We propose a novel approach to learning the generative neural fields represented by linear combinations of implicit basis networks. Our algorithm learns basis networks in the form of implicit neural representations and their coefficients in a latent space by either conducting meta-learning or adopting auto-decoding paradigms.
  arXiv  Detail & Related papers  (2023-10-30T11:41:41Z)
• Sampling weights of deep neural networks [1.2370077627846041]
  We introduce a probability distribution, combined with an efficient sampling algorithm, for weights and biases of fully-connected neural networks. In a supervised learning context, no iterative optimization or gradient computations of internal network parameters are needed. We prove that sampled networks are universal approximators.
  arXiv  Detail & Related papers  (2023-06-29T10:13:36Z)
• Adaptive Conditional Quantile Neural Processes [9.066817971329899]
  Conditional Quantile Neural Processes (CQNPs) are a new member of the neural processes family. We introduce an extension of quantile regression where the model learns to focus on estimating informative quantiles. Experiments with real and synthetic datasets demonstrate substantial improvements in predictive performance.
  arXiv  Detail & Related papers  (2023-05-30T06:19:19Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• Unrolling Particles: Unsupervised Learning of Sampling Distributions [102.72972137287728]
  Particle filtering is used to compute good nonlinear estimates of complex systems. We show in simulations that the resulting particle filter yields good estimates in a wide range of scenarios.
  arXiv  Detail & Related papers  (2021-10-06T16:58:34Z)
• Adversarial Examples Detection with Bayesian Neural Network [57.185482121807716]
  We propose a new framework to detect adversarial examples motivated by the observations that random components can improve the smoothness of predictors. We propose a novel Bayesian adversarial example detector, short for BATer, to improve the performance of adversarial example detection.
  arXiv  Detail & Related papers  (2021-05-18T15:51:24Z)
• The Neural Coding Framework for Learning Generative Models [91.0357317238509]
  We propose a novel neural generative model inspired by the theory of predictive processing in the brain. In a similar way, artificial neurons in our generative model predict what neighboring neurons will do, and adjust their parameters based on how well the predictions matched reality.
  arXiv  Detail & Related papers  (2020-12-07T01:20:38Z)
• Variational inference formulation for a model-free simulation of a dynamical system with unknown parameters by a recurrent neural network [8.616180927172548]
  We propose a "model-free" simulation of a dynamical system with unknown parameters without prior knowledge. The deep learning model aims to jointly learn the nonlinear time marching operator and the effects of the unknown parameters from a time series dataset. It is found that the proposed deep learning model is capable of correctly identifying the dimensions of the random parameters and learning a representation of complex time series data.
  arXiv  Detail & Related papers  (2020-03-02T20:57:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.