-
imagestitch
自己写的图像配准代码，基于harris算子(Write their own code of image registration, based on the operator harris)
- 2009-05-06 19:21:09下载
- 积分：1
-
harris-laplace
这是基本的脚点检测算法，里面包含了harris detector和harris-laplace detector code，便于操作。(This is the basic foot-point detection algorithm, which includes harris detector and harris-laplace detector code, easy to operate.)
- 2020-11-19 20:39:41下载
- 积分：1
-
bipolarwew
Symmetricdivergingbipolar cold-neutral-hot colormap
- 2010-11-11 21:23:56下载
- 积分：1
-
4.IMU_AHRS
惯性测量单元的C源代码 用于测量物体的姿态变化 可应用与惯性导航 小飞机等设计(IMU(inertial measurement unit) source code)
- 2014-02-20 16:04:33下载
- 积分：1
-
usefulpro
解决无优化问题的很有效的matlab程序，包括运行结果，希望可以多交流学习(Solve optimization problems without matlab very effective procedures, including operating results, hoping to learn more exchanges)
- 2011-04-29 21:28:25下载
- 积分：1
-
SVM_classandregress
支持向量机
内容中主要包括二种分类,二种回归,以及一种一类支持向量机算法。(Support Vector Machine
Two types of categories, and two types of regression, as well as a kind of support vector machine algorithm is included in this content.)
- 2011-09-05 15:55:16下载
- 积分：1
-
matlab-robotics-toolbox
关于matlab机器人工具箱的使用，为更好的使用matlab的仿真功能(this is about matlab robotics toolbox)
- 2012-11-27 09:56:14下载
- 积分：1
-
narrowbandCapon
该程序是一个仿真模型，对窄带的带通滤波器进行了仿真(The program is a simulation model of narrow band pass filter was simulated)
- 2011-05-18 18:00:02下载
- 积分：1
-
1807.01622
深度神经网络在函数近似中表现优越，然而需要从头开始训练。另一方面，贝叶斯方法，像高斯过程（GPs），可以利用利用先验知识在测试阶段进行快速推理。然而，高斯过程的计算量很大，也很难设计出合适的先验。本篇论文中我们提出了一种神经模型，条件神经过程（CNPs），可以结合这两者的优点。CNPs受灵活的随机过程的启发，比如GPs，但是结构是神经网络，并且通过梯度下降训练。CNPs通过很少的数据训练后就可以进行准确的预测，然后扩展到复杂函数和大数据集。我们证明了这个方法在一些典型的机器学习任务上面的的表现和功能，比如回归，分类和图像补全(Deep neural networks perform well in function approximation, but they need to be trained from scratch. On the other hand, Bayesian methods, such as Gauss Process (GPs), can make use of prior knowledge to conduct rapid reasoning in the testing stage. However, the calculation of Gauss process is very heavy, and it is difficult to design a suitable priori. In this paper, we propose a neural model, conditional neural processes (CNPs), which can combine the advantages of both. CNPs are inspired by flexible stochastic processes, such as GPs, but are structured as neural networks and trained by gradient descent. CNPs can predict accurately with very little data training, and then extend to complex functions and large data sets. We demonstrate the performance and functions of this method on some typical machine learning tasks, such as regression, classification and image completion.)
- 2020-06-23 22:20:02下载
- 积分：1
-
仿真滚动轴承信号，通过不同阈值降噪方法，降噪后的时域图
仿真滚动轴承信号，通过不同阈值降噪方法，降噪后的时域图(Simulation of rolling bearing signal, through the different threshold noise reduction method, time-domain figure after noise reduction)
- 2020-12-04 08:59:24下载
- 积分：1
