-
simulink_fourbar
用simulink做的四杆机构的运动和仿真主要参数参见程序(the simulation of fourbar with simulink)
- 2010-11-25 10:51:01下载
- 积分：1
-
chapter3
matlab智能算法遗传算法优化人工神经网络权值和阈值(Matlab intelligent algorithm of genetic algorithm to optimize neural network weights and threshold)
- 2014-09-08 15:21:07下载
- 积分：1
-
matlab2
【matlab编程代做】matlab搭接栗色球视频 可以作为参考使用 学习([Do] matlab matlab programming generation lap maroon ball video can be used as a reference study)
- 2015-01-12 20:55:27下载
- 积分：1
-
matlab16
Matlab的经典入门级教材。很适合初学者入门学习使用(Matlab' s classic entry-level teaching. Very suitable for beginners learning to use Getting Started)
- 2009-10-14 15:23:06下载
- 积分：1
-
ransacF
RANSAC implementation for fundamental matrix computation using the seven point algorithm. Returns inliers and best F estimate.
- 2010-01-29 08:18:26下载
- 积分：1
-
kalman_test
kalman滤波的基本原理，在飞行器轨迹预测方面的应用，非常有用(The basic principle of the kalman filter in aircraft trajectory prediction application, is very useful)
- 2013-04-12 14:54:28下载
- 积分：1
-
OFDMPrinciplAndApplication
讲述了OFDM的一些基本知识，包含框图，及OFDM的优缺点等。对OFDM有个全面认识。(OFDM about some of the basics, including block diagram, and the advantages and disadvantages of OFDM and so on. Have a comprehensive understanding of OFDM.)
- 2010-12-30 10:48:25下载
- 积分：1
-
MATLAB-changyongsuanfa
MATLAB语言常用算法程序集 快速提高matlab技术(MATLAB language commonly used algorithm matlab rapid increase in the assembly technology)
- 2011-06-23 15:12:47下载
- 积分：1
-
遗传算法实数编码
遗传算法的实数编码MATLAB程序，不是工具箱，有助于理解遗传算法的编程实现(Genetic algorithm written by maltab)
- 2020-07-02 15:40:01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
