subspace_iteration

Speech Recognition - Numbers 1 to 5 Energy normalization and time alignment References: [1] L. Rabiner and B.H. Juang,Fundamentals of Speech Recognition, Prentice-Hall, 1993. ％ [2] P.E. Papamichalis, Practical Approaches to Speech Coding, Prentice-Hall, 1987. ％ [3] J.D. Markel and A.H. Gray,Linear Prediction of Speech(Speech Recognition-Numbers 1 to 5 Energy n ormalization and time alignment References : [1] L. Paras and B. H. Juang, Fundamentals of Speech Recognition. Prentice-Hall, 1993. % [2] P. E. Papamichalis, Practical Approaches to Speech Coding, Prentice-Hall, 1987. % [3] J. D. Markel and A. H. Gray, Linear Prediction of Speech)

说明：  lpi信号的生成，如lfm，多相编码，步进频信号，时频分析测试成像，(LPI signal generation, such as LFM, polyphase coding, step frequency signal, time-frequency analysis, test imaging,)

包含单位负反馈的三阶系统的设计与校正（matlab程序）(Contains the unit)

examples contain source codes about PID control

STEP模型读取的类库，官方资料，附文档说明(Read STEP model library, official data, with documentation)

说明：  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.)

DEKLPHI THIS WORLD IS THE FUTURE

说明：  对原有修正PRI变换进行改进，将分散在真实PRI箱附近几个箱中的到达时间差值累加起来，提高检测性能(PRI transform the original amendment to improve, will be scattered around a few boxes in the real PRI box add up to the arrival time difference and improve the detection performance)

since direct jornal English

CGUI在STM上的移植, PDF文件,下载查看(The transplantation of CGUI on STM)