paper-with-me

홈 › Papers

Iterative VAE as a predictive brain model for out-of-distribution generalization

2020-12-01 · NeurIPS Workshop SVRHM 2020 12 · Victor Boutin, Aimen Zerroug, Minju Jung, Thomas Serre

Our ability to generalize beyond training data to novel, out-of-distribution, image degradations is a hallmark of primate vision. The predictive brain, exemplified by predictive coding networks (PCNs), has become a prominent neuroscience theory of neural computation. Motivated by the recent successes of variational autoencoders (VAEs) in machine learning, we rigorously derive a correspondence between PCNs and VAEs. This motivates us to consider iterative extensions of VAEs (iVAEs) as plausible variational extensions of the PCNs. We further demonstrate that iVAEs generalize to distributional shifts significantly better than both PCNs and VAEs. In addition, we propose a novel measure of recognizability for individual samples which can be tested against human psychophysical data. Overall, we hope this work will spur interest in iVAEs as a promising new direction for modeling in neuroscience.

📄 PDF Abstract BibTeX arXiv:2012.00557

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution Generalization

Similar Papers 제목 키워드 기반

Brain-like variational inference

2024-10-25 · Hadi Vafaii, Dekel Galor, Jacob L. Yates

Inference in both brains and machines can be formalized by optimizing a shared objective: maximizing the evidence lower bound (ELBO) in machine learning, or minimizing variational free energy (F) in neuroscience (ELBO = …

Variational Inference

Spiking Graph Predictive Coding for Reliable OOD Generalization

2026-02-22 · Jing Ren, Jiapeng Du, Bowen Li, Ziqi Xu 외 arxiv

Graphs provide a powerful basis for modeling Web-based relational data, with expressive GNNs to support the effective learning in dynamic web environments. However, real-world deployment is hindered by pervasive out-of-d…

Graph Learning

Density Regression and Uncertainty Quantification with Bayesian Deep Noise Neural Networks

2022-06-12 · Daiwei Zhang, Tianci Liu, Jian Kang

Deep neural network (DNN) models have achieved state-of-the-art predictive accuracy in a wide range of supervised learning applications. However, accurately quantifying the uncertainty in DNN predictions remains a challe…

regressionUncertainty Quantification

Adaptive Synaptic Failure Enables Sampling from Posterior Predictive Distributions in the Brain

2022-10-04 · Kevin McKee, Ian Crandell, Rishidev Chaudhuri, Randall O'Reilly

Bayesian interpretations of neural processing require that biological mechanisms represent and operate upon probability distributions in accordance with Bayes' theorem. Many have speculated that synaptic failure constitu…

Bayesian Inference

BrainOOD: Out-of-distribution Generalizable Brain Network Analysis

2025-02-02 · Jiaxing Xu, Yongqiang Chen, Xia Dong, Mengcheng Lan 외

In neuroscience, identifying distinct patterns linked to neurological disorders, such as Alzheimer's and Autism, is critical for early diagnosis and effective intervention. Graph Neural Networks (GNNs) have shown promisi…