PCANet:A Simple Deep Learning Baseline for Image Classification?

来源 :第八届工业与应用数学国际大会 | 被引量 : 0次 | 上传用户：libraspace

【摘要】

：

　　We will discuss a very simple deep network for image classification which comprises only the very basic data processing components: cascaded principal compo

【作者】

：

Ma Yi

【机构】

：

ShanghaiTech Univ.

【出处】

：

第八届工业与应用数学国际大会

【发表日期】

：

2015年期

下载到本地 , 更方便阅读

下载此文赞助VIP

声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架

论文部分内容阅读

　　We will discuss a very simple deep network for image classification which comprises only the very basic data processing components: cascaded principal component analysis(PCA),binary hashing,and block-wise histograms.

其他文献

An Alternating Minimization Model for Tomography Reconstruction in Hydrodynamic Experiments

　　Flash radiography with CCD-based camera plays an important role in studying the dynamical behavior of material under a shock through tomographic reconstruct

会议

RKDG Methods with Cut Cell for Compressible Multi-phase Flows:Full Navier-Stokes Equations

　　Following our earlier works with Euler equations,full Navier-Stokes equations are realized in the cut-cell based RKDG method to simulate compressible multi-

会议

A Reconstruction Method of Intra-Ventricular Flow Velocity Using Color Flow Ultrasound

　　We propose a 2D Navier-Stokes model to reconstruct intraventricular flows using color flow images and left ventricular boundaries extracted from echocardiog

会议

Domain Decompsition for Total Variation Minimization

　　This talk is concerned with overlapping domain decomposition methods(DDMs),based on successive subspace correction(SSC)and parallel subspace correction(PSC)

会议

General Algebraic Connectivity in Consensus of Multi-agent Systems

　　This talk will discuss general algebraic connectivity representing consensus convergence rate in multi-agent systems with directed topologies.

会议

Convergence Rate of the Consensus of Linear Multi-agent Systems with Communication Noises

　　This study mainly focuses on the convergence rate of the consensus of linear multi-agent systems.It is assumed that each agent is described by the generic l

会议

Distributed Finite-time Tracking of Multiple Euler-Lagrange Systems without Velocity Measurements

　　This paper investigates the distributed finite-time tracking problem of networked agents with Euler-Lagrange dynamics.To achieve finite-time tracking,with t

会议

Distributed control of networked agent systems

　　Many real large-scale systems can be modeled as networked agent systems,where typical examples include Internet,WWW,smart grids,etc.

会议

Node-to-node Consensus of Multi-agent Systems under Directed Topology

　　Consensus of multi-agent system has recently received considerable attention from various scientific communities due to its potential applications in engine

会议

An Expander Graph Construction and Its Implication for Compressed Sensing

　　We consider a probabilistic construction of sparse matrices with provable restricted isometry constants(RICS)using l1 norms.

会议

PCANet:A Simple Deep Learning Baseline for Image Classification?

与本文相关的学术论文