中文
相关论文

相关论文: Central limit theorems for the outputs of fully co…

200 篇论文

There is a previously identified equivalence between wide fully connected neural networks (FCNs) and Gaussian processes (GPs). This equivalence enables, for instance, test set predictions that would have resulted from a fully Bayesian,…

A common theoretical approach to understanding neural networks is to take an infinite-width limit, at which point the outputs become Gaussian process (GP) distributed. This is known as a neural network Gaussian process (NNGP). However, the…

机器学习 · 统计学 2025-06-26 Ben Anson , Edward Milsom , Laurence Aitchison

A recent line of works studied wide deep neural networks (DNNs) by approximating them as Gaussian Processes (GPs). A DNN trained with gradient flow was shown to map to a GP governed by the Neural Tangent Kernel (NTK), whereas earlier works…

机器学习 · 统计学 2021-12-15 Gadi Naveh , Oded Ben-David , Haim Sompolinsky , Zohar Ringel

Graph neural networks (GNNs) have achieved remarkable success in processing graph-structured data across various applications. A critical aspect of real-world graphs is their dynamic nature, where new nodes are continually added and…

机器学习 · 计算机科学 2025-09-09 Huayi Tang , Yong Liu

We study the extent to which wide neural networks may be approximated by Gaussian processes when initialized with random weights. It is a well-established fact that as the width of a network goes to infinity, its law converges to that of a…

概率论 · 数学 2021-02-18 Ronen Eldan , Dan Mikulincer , Tselil Schramm

Global average pooling (GAP) is a popular component in deep metric learning (DML) for aggregating features. Its effectiveness is often attributed to treating each feature vector as a distinct semantic entity and GAP as a combination of…

机器学习 · 计算机科学 2023-07-25 Yeti Z. Gurbuz , A. Aydin Alatan

We show that the output of a (residual) convolutional neural network (CNN) with an appropriate prior over the weights and biases is a Gaussian process (GP) in the limit of infinitely many convolutional filters, extending similar results for…

机器学习 · 统计学 2019-05-07 Adrià Garriga-Alonso , Carl Edward Rasmussen , Laurence Aitchison

There has recently been much work on the "wide limit" of neural networks, where Bayesian neural networks (BNNs) are shown to converge to a Gaussian process (GP) as all hidden layers are sent to infinite width. However, these results do not…

机器学习 · 统计学 2020-07-07 Devanshu Agrawal , Theodore Papamarkou , Jacob Hinkle

A common architectural choice for deep metric learning is a convolutional neural network followed by global average pooling (GAP). Albeit simple, GAP is a highly effective way to aggregate information. One possible explanation for the…

计算机视觉与模式识别 · 计算机科学 2023-08-23 Yeti Z. Gurbuz , Ozan Sener , A. Aydın Alatan

We rigorously prove a central limit theorem for neural network models with a single hidden layer. The central limit theorem is proven in the asymptotic regime of simultaneously (A) large numbers of hidden units and (B) large numbers of…

概率论 · 数学 2019-06-04 Justin Sirignano , Konstantinos Spiliopoulos

Graph convolutional neural networks~(GCNs) have recently demonstrated promising results on graph-based semi-supervised classification, but little work has been done to explore their theoretical properties. Recently, several deep neural…

机器学习 · 计算机科学 2020-02-28 Jilin Hu , Jianbing Shen , Bin Yang , Ling Shao

Graph neural networks (GNN) extends deep learning to graph-structure dataset. Similar to Convolutional Neural Networks (CNN) using on image prediction, convolutional and pooling layers are the foundation to success for GNN on graph…

机器学习 · 计算机科学 2023-02-28 Lingjie Kong , Yun Liao

This article gives a new proof that fully connected neural networks with random weights and biases converge to Gaussian processes in the regime where the input dimension, output dimension, and depth are kept fixed, while the hidden layer…

概率论 · 数学 2021-07-06 Boris Hanin

We establish central and non-central limit theorems for sequences of functionals of the Gaussian output of an infinitely-wide random neural network on the d-dimensional sphere . We show that the asymptotic behaviour of these functionals as…

概率论 · 数学 2026-04-24 Simmaco Di Lillo , Leonardo Maini , Domenico Marinucci

Graph convolutional networks (GCNs) are a widely used method for graph representation learning. To elucidate the capabilities and limitations of GCNs, we investigate their power, as a function of their number of layers, to distinguish…

机器学习 · 统计学 2020-05-14 Abram Magner , Mayank Baranwal , Alfred O. Hero

Deep neural networks (DNNs) in the infinite width/channel limit have received much attention recently, as they provide a clear analytical window to deep learning via mappings to Gaussian Processes (GPs). Despite its theoretical appeal, this…

机器学习 · 计算机科学 2021-06-09 Gadi Naveh , Zohar Ringel

Convolutional Neural Networks (CNNs) have achieved outstanding performance on image processing challenges. Actually, CNNs imitate the typically developed human brain structures at the micro-level (Artificial neurons). At the same time, they…

计算机视觉与模式识别 · 计算机科学 2023-06-16 Zahra Rezvani , Soroor Shekarizeh , Mohammad Sabokrou

In this paper we study the generalization capabilities of fully-connected neural networks trained in the context of time series forecasting. Time series do not satisfy the typical assumption in statistical learning theory of the data being…

机器学习 · 统计学 2019-07-30 Anastasia Borovykh , Cornelis W. Oosterlee , Sander M. Bohte

We propose a simple but strong baseline for time series classification from scratch with deep neural networks. Our proposed baseline models are pure end-to-end without any heavy preprocessing on the raw data or feature crafting. The…

机器学习 · 计算机科学 2016-12-15 Zhiguang Wang , Weizhong Yan , Tim Oates

It has long been known that a single-layer fully-connected neural network with an i.i.d. prior over its parameters is equivalent to a Gaussian process (GP), in the limit of infinite network width. This correspondence enables exact Bayesian…

‹ 上一页 1 2 3 10 下一页 ›