中文
相关论文

相关论文: The Propagation Field: A Geometric Substrate Theor…

200 篇论文

Deep learning is the mainstream technique for many machine learning tasks, including image recognition, machine translation, speech recognition, and so on. It has outperformed conventional methods in various fields and achieved great…

机器学习 · 计算机科学 2018-06-01 Na Lei , Zhongxuan Luo , Shing-Tung Yau , David Xianfeng Gu

Theoretical understanding of deep learning remains elusive despite its empirical success. In this study, we propose a novel "synaptic field theory" that describes the training dynamics of synaptic weights and biases in the continuum limit.…

高能物理 - 理论 · 物理学 2025-08-01 Donghee Lee , Hye-Sung Lee , Jaeok Yi

Despite significant advances in the field of deep learning in applications to various fields, explaining the inner processes of deep learning models remains an important and open question. The purpose of this article is to describe and…

机器学习 · 计算机科学 2022-04-20 German Magai , Anton Ayzenberg

Neural fields, which represent signals as a function parameterized by a neural network, are a promising alternative to traditional discrete vector or grid-based representations. Compared to discrete representations, neural representations…

机器学习 · 计算机科学 2023-09-14 Jeffrey Gu , Kuan-Chieh Wang , Serena Yeung

We study the behavior of untrained neural networks whose weights and biases are randomly distributed using mean field theory. We show the existence of depth scales that naturally limit the maximum depth of signal propagation through these…

机器学习 · 统计学 2017-04-06 Samuel S. Schoenholz , Justin Gilmer , Surya Ganguli , Jascha Sohl-Dickstein

Diffusion probabilistic models have quickly become a major approach for generative modeling of images, 3D geometry, video and other domains. However, to adapt diffusion generative modeling to these domains the denoising network needs to be…

计算机视觉与模式识别 · 计算机科学 2023-03-02 Peiye Zhuang , Samira Abnar , Jiatao Gu , Alex Schwing , Joshua M. Susskind , Miguel Ángel Bautista

The success of deep learning, a brain-inspired form of AI, has sparked interest in understanding how the brain could similarly learn across multiple layers of neurons. However, the majority of biologically-plausible learning algorithms have…

Deep neural networks implement a sequence of layer-by-layer operations that are each relatively easy to understand, but the resulting overall computation is generally difficult to understand. We consider a simple hypothesis for interpreting…

机器学习 · 计算机科学 2022-11-29 Richard D. Lange , Devin Kwok , Jordan Matelsky , Xinyue Wang , David S. Rolnick , Konrad P. Kording

Training neural networks via backpropagation is often hindered by vanishing or exploding gradients. In this work, we design architectures that mitigate these issues by analyzing and controlling the network Jacobian. We first provide a…

机器学习 · 计算机科学 2026-02-12 Alex Massucco , Davide Murari , Carola-Bibiane Schönlieb

In recent years, the mean field theory has been applied to the study of neural networks and has achieved a great deal of success. The theory has been applied to various neural network structures, including CNNs, RNNs, Residual networks, and…

机器学习 · 计算机科学 2020-06-11 Wei Huang , Richard Yi Da Xu , Weitao Du , Yutian Zeng , Yunce Zhao

Humans gain an implicit understanding of physical laws through observing and interacting with the world. Endowing an autonomous agent with an understanding of physical laws through experience and observation is seldom practical: we should…

Graph neural networks have shown significant success in the field of graph representation learning. Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations. Nevertheless, one layer of…

机器学习 · 计算机科学 2020-07-21 Meng Liu , Hongyang Gao , Shuiwang Ji

The fundamental idea of embedding a network in a metric space is rooted in the principle of proximity preservation. Nodes are mapped into points of the space with pairwise distance that reflects their proximity in the network. Popular…

物理与社会 · 物理学 2021-01-15 Yi-Jiao Zhang , Kai-Cheng Yang , Filippo Radicchi

How to balance training accuracy and adversarial robustness has become a challenge since the birth of deep learning. Here, we introduce a geometry-aware deep learning framework that leverages layer-wise local training to sculpt the internal…

机器学习 · 计算机科学 2025-09-05 Yixiong Ren , Wenkang Du , Jianhui Zhou , Haiping Huang

Deep learning models are often considered black boxes due to their complex hierarchical transformations. Identifying suitable architectures is crucial for maximizing predictive performance with limited data. Understanding the geometric…

机器学习 · 计算机科学 2025-03-11 Michael Wienczkowski , Addisu Desta , Paschal Ugochukwu

The goal of this thesis is to improve our understanding of the internal mechanisms by which deep artificial neural networks create meaningful representations and are able to generalize. We focus on the challenge of characterizing the…

机器学习 · 计算机科学 2025-10-29 Diego Doimo

This paper presents a locally decoupled network parameter learning with local propagation. Three elements are taken into account: (i) sets of nonlinear transforms that describe the representations at all nodes, (ii) a local objective at…

机器学习 · 计算机科学 2018-05-22 Dimche Kostadinov , Behrooz Razeghi , Sohrab Ferdowsi , Slava Voloshynovskiy

Deep learning has arguably achieved tremendous success in recent years. In simple words, deep learning uses the composition of many nonlinear functions to model the complex dependency between input features and labels. While neural networks…

机器学习 · 统计学 2019-04-16 Jianqing Fan , Cong Ma , Yiqiao Zhong

This paper investigates the foundations of deep learning through insight of geometry, algebra and differential calculus. At is core, artificial intelligence relies on assumption that data and its intrinsic structure can be embedded into…

微分几何 · 数学 2025-10-22 Tsemo Aristide

Deep convolutional neural networks have been widely used in numerous applications, but their demanding storage and computational resource requirements prevent their applications on mobile devices. Knowledge distillation aims to optimize a…

机器学习 · 计算机科学 2018-12-18 Hanting Chen , Yunhe Wang , Chang Xu , Chao Xu , Dacheng Tao
‹ 上一页 1 2 3 10 下一页 ›