-
MATLAB
最速下降法 优化算法问题以及其说明等等 (decent answerr method )
- 2009-05-16 11:32:10下载
- 积分：1
-
lab-report
声音信号的处理以及重新编译，其中包含完整的code以及lab report(UNDERSTAND SIMULATION SOFTWARE OF MATLAB TO PLOT SIGNALS)
- 2013-10-05 12:05:55下载
- 积分：1
-
基于空间飞行器的姿态仿真程序-MATLAB源代码
基于空间飞行器的姿态仿真程序-MATLAB源代码，给出姿态仿真结果(Spacecraft based attitude simulation program - MATLAB source code, gives attitude simulation results)
- 2021-01-19 10:08:43下载
- 积分：1
-
VSR_double
simulink环境下的双极性PWM控制的单向电压型整流器的模型(simulink environment bipolar PWM control unidirectional voltage source rectifier model)
- 2013-08-04 17:54:40下载
- 积分：1
-
TD6-2012-sources
file for the resolution of the transport equation
With an implicit scheme
- 2013-12-24 06:07:34下载
- 积分：1
-
LSS06
mimo ofdm book-helps to build up mimo ofdm model
- 2009-11-13 01:38:47下载
- 积分：1
-
db6xiaobochonggou
db6小波分解upcoef重构与wrcoef重构的对比，可换成任意输入(db6 decomposition upcoef reconstruction compared with wrcoef reconstruction can be replaced by any input)
- 2010-05-10 13:34:24下载
- 积分：1
-
ML_and_MAP
最大似然（ML）准则和最大后验概率（MAP）准则Matlab仿真(Maximum Likelihood (ML) criteria and maximum a posteriori probability (MAP) criteria Matlab simulation )
- 2011-05-31 15:45:22下载
- 积分：1
-
engine_model
基于Matlab simulink 环境下开发的发动机仿真。(Development of the engine simulation of Matlab Simulink-based environment.)
- 2012-05-27 20:21:49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
