建筑物提取matlab代码-adanet:基于文章AdaNet-人工神经网络的自适应结构学习
紫外线matlab代码艾达网
AdaNet：人工神经网络的自适应结构学习
参考资料：Cortes,
C.,
Gonzalvo,
X.,
Kuznetsov,
V.,
Mohri,
M.
&
Yang,
S..
(2017)。
AdaNet：人工神经网络的自适应结构学习。
第
34
届机器学习国际会议论文集，PMLR
70:874-883
这个
Python
项目旨在实现
AdaNet
的
API，使用基于文章的算法：简而言之，这个模型正在根据它适合的数据复杂性从头构建一个神经网络，
这就是它命名为自适应模型的原因。
对于这个实现，手头的问题总是一个二元分类。
在拟合操作期间，它将构建隐藏层和每层中的神经元数量。
决定是更深（添加隐藏层）还是更宽（将神经元添加到现有层），
或者更新现有的神经元权重以封闭的计算形式完成（通过使用巴拿赫空间对偶）文章中所示。
最后，它将优化最佳神经元（添加或现有）的权重，更新参数并进行迭代。
文章讲了AdaNet的几个变种，这是AdaNet.CVX的实现，
在附录
C
中解释
-
以封闭形式解决每个步骤中的凸子问题。
文章
[v.1]
的先前版本中显示了对该
文件下载
资源详情
[{"title":"（ 57 个子文件 39.86MB ） 建筑物提取matlab代码-adanet:基于文章AdaNet-人工神经网络的自适应结构学习","children":[{"title":"adanet-master","children":[{"title":"twospirals.py <span style='color:#111;'> 1.25KB </span>","children":null,"spread":false},{"title":"adanet_val_results.csv <span style='color:#111;'> 9.86KB </span>","children":null,"spread":false},{"title":"AdaNet- Adaptive Structural Learning of Artificial Neural Networks___1607.01097v1.pdf <span style='color:#111;'> 593.32KB </span>","children":null,"spread":false},{"title":".ipynb_checkpoints","children":[{"title":"AdaNet - NN compared model-checkpoint.ipynb <span style='color:#111;'> 72B </span>","children":null,"spread":false},{"title":"Adanet-checkpoint.ipynb <span style='color:#111;'> 72B </span>","children":null,"spread":false},{"title":"AdaNet - LR compared model-checkpoint.ipynb <span style='color:#111;'> 51.60KB </span>","children":null,"spread":false}],"spread":true},{"title":"AdaNet_CIFAR_10_feature_extraction.py <span style='color:#111;'> 4.88KB </span>","children":null,"spread":false},{"title":"tic-tac-toe","children":[{"title":"tic-tac-toe.names.txt <span style='color:#111;'> 3.17KB </span>","children":null,"spread":false},{"title":"tic-tac-toe.data <span style='color:#111;'> 25.26KB </span>","children":null,"spread":false}],"spread":true},{"title":"AdaNet - LR compared model.ipynb <span style='color:#111;'> 54.93KB </span>","children":null,"spread":false},{"title":"Adanet.ipynb <span style='color:#111;'> 58.98KB </span>","children":null,"spread":false},{"title":"AdaNet_CVX.py <span style='color:#111;'> 52.09KB </span>","children":null,"spread":false},{"title":"datasets","children":[{"title":"CIFAR10_pair_cat_dog.npz <span style='color:#111;'> 7.30MB </span>","children":null,"spread":false},{"title":"CIFAR10_pair_automobile_truck.npz <span style='color:#111;'> 7.71MB </span>","children":null,"spread":false},{"title":"CIFAR10_pair_deer_horse.npz <span style='color:#111;'> 6.98MB </span>","children":null,"spread":false},{"title":"CIFAR10_pair_dog_horse.npz <span style='color:#111;'> 7.28MB </span>","children":null,"spread":false},{"title":"CIFAR10_pair_deer_truck.npz <span style='color:#111;'> 7.16MB </span>","children":null,"spread":false}],"spread":true},{"title":"test_adanet.py <span style='color:#111;'> 24.05KB </span>","children":null,"spread":false},{"title":"test_results.csv <span style='color:#111;'> 7.30KB </span>","children":null,"spread":false},{"title":"AdaNet- Adaptive Structural Learning of Artificial Neural Networks___1607.01097v2.pdf <span style='color:#111;'> 497.00KB </span>","children":null,"spread":false},{"title":"MLP_val_results.csv <span style='color:#111;'> 8.01KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 4.32KB </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"AdaNet_CIFAR_10_feature_extraction.cpython-36.pyc <span style='color:#111;'> 3.57KB </span>","children":null,"spread":false},{"title":"AdaNet_CVX.cpython-36.pyc <span style='color:#111;'> 38.46KB </span>","children":null,"spread":false},{"title":"twospirals.cpython-36.pyc <span style='color:#111;'> 1.30KB </span>","children":null,"spread":false}],"spread":false},{"title":"LR_val_results.csv <span style='color:#111;'> 3.07KB </span>","children":null,"spread":false},{"title":"AdaNet_FinalReport.pdf <span style='color:#111;'> 1.21MB </span>","children":null,"spread":false},{"title":"MD template.md <span style='color:#111;'> 1.99KB </span>","children":null,"spread":false},{"title":".gitattributes <span style='color:#111;'> 66B </span>","children":null,"spread":false},{"title":"AdaNet- Adaptive Structural Learning of Artificial Neural Networks___1607.01097v3.pdf <span style='color:#111;'> 524.07KB </span>","children":null,"spread":false},{"title":"AdaNet - NN compared model.ipynb <span style='color:#111;'> 64.23KB </span>","children":null,"spread":false},{"title":"tuning","children":[{"title":"LAM100_T300_BFGS_stopped.png <span style='color:#111;'> 45.92KB </span>","children":null,"spread":false},{"title":"LAM0.1_T300.png <span style='color:#111;'> 33.24KB </span>","children":null,"spread":false},{"title":"LAM100_T300_StoppedAt67.png <span style='color:#111;'> 46.72KB </span>","children":null,"spread":false},{"title":"LAM0.1_20EpochConvergeT500.png <span style='color:#111;'> 33.77KB </span>","children":null,"spread":false},{"title":"German_LAM1_T300.png <span style='color:#111;'> 40.51KB </span>","children":null,"spread":false},{"title":"LAM0.1_T300_convergeStop_BFGS.png <span style='color:#111;'> 35.85KB </span>","children":null,"spread":false},{"title":"LAM10_T300_BFGS.png <span style='color:#111;'> 44.29KB </span>","children":null,"spread":false},{"title":"results.csv <span style='color:#111;'> 20.82KB </span>","children":null,"spread":false},{"title":"LAM0.1_lam-5_augTrue_20EpochConverge.png <span style='color:#111;'> 31.02KB </span>","children":null,"spread":false},{"title":"German_LAM0.1_T300_BFGS.png <span style='color:#111;'> 35.65KB </span>","children":null,"spread":false},{"title":"German_LAM10_T300.png <span style='color:#111;'> 48.35KB </span>","children":null,"spread":false},{"title":"LAM0.1_lam-5_augFalse_10EpochConverge.png <span style='color:#111;'> 30.03KB </span>","children":null,"spread":false},{"title":"German_LAM10_T300_BFGS.png <span style='color:#111;'> 48.32KB </span>","children":null,"spread":false},{"title":"LAM1_T300_BFGS.png <span style='color:#111;'> 44.43KB </span>","children":null,"spread":false},{"title":"German_LAM1_T300_BFGS.png <span style='color:#111;'> 39.75KB </span>","children":null,"spread":false},{"title":"LAM0.1_10EpochConverge.png <span style='color:#111;'> 29.58KB </span>","children":null,"spread":false},{"title":"LAM0.1_lam-4_augFalse_20EpochConverge.png <span style='color:#111;'> 30.22KB </span>","children":null,"spread":false},{"title":"German_LAM100_T300.png <span style='color:#111;'> 49.15KB </span>","children":null,"spread":false},{"title":"LAM1_T300_Stopped.png <span style='color:#111;'> 45.12KB </span>","children":null,"spread":false},{"title":"LAM1_T300_StoppedAt113.png <span style='color:#111;'> 44.88KB </span>","children":null,"spread":false},{"title":"LAM10_T300_StoppedAt67.png <span style='color:#111;'> 47.24KB </span>","children":null,"spread":false},{"title":"LAM10_T300.png <span style='color:#111;'> 43.87KB </span>","children":null,"spread":false},{"title":"LAM0.1_20EpochConverge.png <span style='color:#111;'> 29.19KB </span>","children":null,"spread":false},{"title":"German_LAM100_T300_BFGS.png <span style='color:#111;'> 43.59KB </span>","children":null,"spread":false},{"title":"German_LAM0.1_T300.png <span style='color:#111;'> 35.16KB </span>","children":null,"spread":false},{"title":"LAM0.1_T300_convergeStop.png <span style='color:#111;'> 33.55KB </span>","children":null,"spread":false}],"spread":false}],"spread":false}],"spread":true}]
评论信息
其他资源
- 粒子群算法求16个经典函数的最小最大值
- 竞争性自适应重加权
- 现代数字信号处理习题答案
- 基于OpenCL的FPGA计算系统设计指南
- VrMl程序实现别墅，房子，树，公路，小汽车，飞机
- 软件项目管理课件PPT（主编：夏辉）
- AForge官方SDK(含手册、源码、示例代码、引用库)
- 基于三维轴距的图像去噪算法
- 2020年银行从业资格《个人贷款》第六章习题及答案解析.pdf
- setup_common.py
- 微机课程设计 基于8086 的proteus仿真的4路竞赛抢答器
- CLO_3D_2011中文手册
- MUI实例Demo
- 毕业设计：在线购物系统
- jsp 留言板管理系统
- KPMtools程序
- Pro JavaFX 9 A Definitive Guide to Building Desktop, Clients(4th) 无水印原版pdf
- openlayers最新版完整API v4.6.5
- 人脸分割matlab
- 数值分析算法程序设计 C++实现
免责申明
【只为小站】的资源来自网友分享，仅供学习研究，请务必在下载后24小时内给予删除，不得用于其他任何用途，否则后果自负。基于互联网的特殊性，【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查；无论 【只为小站】 经营者是否已进行审查，用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明