中文
相关论文

相关论文: Bucketed PCA Neural Networks with Neurons Mirrorin…

200 篇论文

Building large models with parameter sharing accounts for most of the success of deep convolutional neural networks (CNNs). In this paper, we propose doubly convolutional neural networks (DCNNs), which significantly improve the performance…

机器学习 · 计算机科学 2016-11-01 Shuangfei Zhai , Yu Cheng , Weining Lu , Zhongfei Zhang

In this paper, we propose a novel unsupervised deep learning model, called PCA-based Convolutional Network (PCN). The architecture of PCN is composed of several feature extraction stages and a nonlinear output stage. Particularly, each…

机器学习 · 计算机科学 2015-05-15 Yanhai Gan , Jun Liu , Junyu Dong , Guoqiang Zhong

Comparing different neural network representations and determining how representations evolve over time remain challenging open questions in our understanding of the function of neural networks. Comparing representations in neural networks…

机器学习 · 统计学 2018-10-25 Ari S. Morcos , Maithra Raghu , Samy Bengio

Backpropagation (BP) is the standard algorithm for training the deep neural networks that power modern artificial intelligence including large language models. However, BP is energy inefficient and unlikely to be implemented by the brain.…

机器学习 · 计算机科学 2025-10-30 Francesco Innocenti

Improving the efficiency of current neural networks and modeling them in biological neural systems have become popular research directions in recent years. Pulse-coupled neural network (PCNN) is a well applicated model for imitating the…

计算机视觉与模式识别 · 计算机科学 2026-01-01 Haoran Liu , Mingzhe Liu , Peng Li , Jiahui Wu , Xin Jiang , Zhuo Zuo , Bingqi Liu

Deep Neural Networks (DNN) and especially Convolutional Neural Networks (CNN) are a de-facto standard for the analysis of large volumes of signals and images. Yet, their development and underlying principles have been largely performed in…

信息论 · 计算机科学 2022-03-24 Ljubisa Stankovic , Danilo Mandic

As convolutional neural networks (CNNs) become more accurate at object recognition, their representations become more similar to the primate visual system. This finding has inspired us and other researchers to ask if the implication also…

计算机视觉与模式识别 · 计算机科学 2022-09-07 Cassidy Pirlot , Richard C. Gerum , Cory Efird , Joel Zylberberg , Alona Fyshe

Recent work has sought to understand the behavior of neural networks by comparing representations between layers and between different trained models. We examine methods for comparing neural network representations based on canonical…

机器学习 · 计算机科学 2019-07-22 Simon Kornblith , Mohammad Norouzi , Honglak Lee , Geoffrey Hinton

With more and more data being collected, data-driven modeling methods have been gaining in popularity in recent years. While physically sound, classical gray-box models are often cumbersome to identify and scale, and their accuracy might be…

机器学习 · 计算机科学 2023-04-05 Loris Di Natale , Bratislav Svetozarevic , Philipp Heer , Colin Neil Jones

Deep convolutional neural networks (CNNs) have shown great potential for numerous real-world machine learning applications, but performing inference in large CNNs in real-time remains a challenge. We have previously demonstrated that…

机器学习 · 统计学 2016-12-14 Bodo Rueckauer , Iulia-Alexandra Lungu , Yuhuang Hu , Michael Pfeiffer

Of particular interest is to discover useful representations solely from observations in an unsupervised generative manner. However, the question of whether existing normalizing flows provide effective representations for downstream tasks…

计算机视觉与模式识别 · 计算机科学 2022-08-24 Shen Li , Bryan Hooi

Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification. However, the development of high-quality deep models typically relies on a substantial amount…

计算机视觉与模式识别 · 计算机科学 2016-05-05 Mengchen Liu , Jiaxin Shi , Zhen Li , Chongxuan Li , Jun Zhu , Shixia Liu

Based on the predictive coding theory in neuroscience, we designed a bi-directional and recurrent neural net, namely deep predictive coding networks (PCN). It has feedforward, feedback, and recurrent connections. Feedback connections from a…

计算机视觉与模式识别 · 计算机科学 2018-07-31 Haiguang Wen , Kuan Han , Junxing Shi , Yizhen Zhang , Eugenio Culurciello , Zhongming Liu

Comparing learned neural representations in neural networks is a challenging but important problem, which has been approached in different ways. The Centered Kernel Alignment (CKA) similarity metric, particularly its linear variant, has…

机器学习 · 计算机科学 2022-11-17 MohammadReza Davari , Stefan Horoi , Amine Natik , Guillaume Lajoie , Guy Wolf , Eugene Belilovsky

Understanding feature representation for deep neural networks (DNNs) remains an open question within the general field of explainable AI. We use principal component analysis (PCA) to study the performance of a k-nearest neighbors classifier…

机器学习 · 计算机科学 2023-09-28 Amit Harlev , Andrew Engel , Panos Stinis , Tony Chiang

Graph neural networks (GNN) are an effective framework that exploit inter-relationships within graph-structured data for learning. Principal component analysis (PCA) involves the projection of data on the eigenspace of the covariance matrix…

机器学习 · 计算机科学 2023-01-18 Saurabh Sihag , Gonzalo Mateos , Corey McMillan , Alejandro Ribeiro

Convolutional Neural Networks (CNN) have been the centerpiece of many applications including but not limited to computer vision, speech processing, and Natural Language Processing (NLP). However, the computationally expensive convolution…

新兴技术 · 计算机科学 2019-07-11 Armin Mehrabian , Yousra Al-Kabani , Volker J Sorger , Tarek El-Ghazawi

Spiking neural networks (SNNs) have closer dynamics to the brain than current deep neural networks. Their low power consumption and sample efficiency make these networks interesting. Recently, several deep convolutional spiking neural…

计算机视觉与模式识别 · 计算机科学 2022-11-01 Shahriar Rezghi Shirsavar , Mohammad-Reza A. Dehaqani

Bayesian neural networks (BNNs) allow rigorous uncertainty quantification in deep learning, but often come at a prohibitive computational cost. We propose three different innovative architectures of partial trace-class Bayesian neural…

机器学习 · 统计学 2025-11-04 Arran Carter , Torben Sell

Neural operator learning has emerged as a powerful approach for solving partial differential equations (PDEs) in a data-driven manner. However, applying principal component analysis (PCA) to high-dimensional solution fields incurs…

机器学习 · 计算机科学 2025-09-24 Mrigank Dhingra , Romit Maulik , Adil Rasheed , Omer San
‹ 上一页 1 2 3 10 下一页 ›