Traveling-salesman

This the free version of my Basis of AI Backprop designed to accompany my not yet published textbook, _The Basis of AI_. This program contains enough features for students in an ordinary AI or Neural Networking course. It includes the quickprop and delta-bar-delta algorithms for faster training and a fast integer version for machines without floating point hardware. This particular package includes C source for DOS and UNIX, examples, an ASCII manual and a number of DOS binaries. The binaries are for systems with floating point hardware (bp.exe), one for systems without floating point hardware (bp486sx.exe) and an integer version binary (ibp486sx.exe) for systems without floating point hardware.

利用matlab程序编写了如何求解连续状态空间方程的解(Use matlab to write how to solve the continuous state space equation solution )

完成对于图像的DCT变换反变换，FFT变换反变换，动态模糊，加噪声去噪声等等，配有图形界面，功能强大(For complete image DCT transform inverse transform, FFT transform inverse transform, as well as some dynamic blurring function, and with a graphical interface)

Stereovision reconstruction using Triangulation and "Mire" Calibration. Implemented in Matlab language

说明：  基于麦克风阵列的声源定位，四元十字阵的matlab仿真(Microphone array based sound localization, four-element Array of matlab simulation)

完备图像稀疏表示是一种最新的图像表示模型，采用过完备字典中原子的线性组合形式实现图像的稀疏表示．传统 的过完备图像稀疏表示模型采用重建误差的平方和作为保真项．该保真项没有充分考虑到人眼对图像的感知特性，无法度量图 像中边缘、轮廓、纹理等局部几何结构的变化．本文基于过完备稀疏表示理论思想，建立了新的稀疏性正则化的图像稀疏表示模 型．模型中的正则项约束图像表示系数的稀疏性，保真项采用更符合视觉感知的结构相似性度量．基于正交匹配追踪算法，提出 了基于结构相似度的正交匹配追踪算法．实验结果表示，新的模型能够更好地重构图像的结构信息，获得更好的重建视觉效果． (Image Sparse Representation Model bed StmctIlral SiIIIilarity )

LDA简单的小程序，线性判别，用于分类的(LDA simple little program, linear discriminant for classification)

说明：  本文档是用MATLAB仿真各种信号的波变换(This document is a variety of signals using MATLAB simulation of wave transformation)

matlab课程设计，基于matlab的图像处理课程设计(matlab)

KSVD原始算法：信号稀疏表示中的过完备字典的学习算法(KSVD original algorithm: Signal Sparse Representation of the learning algorithm over-complete dictionary)