资源列表
resnet-protofiles-master
- 卷积神经网络resnet18、resnet34、resnet50、resnet101、resnet152的配置文件（网络结构和解决方案文件）(Convolution neural network resnet18, resnet34, resnet50, resnet101, resnet152 configuration file (network structure and solution file))
DSI
- 一个很好用的DS证据理论工具箱，可以实现算法编程以及各种应用(A good toolbox of DS evidence theory)
rbf
- 自己编写RBF神经网络程序，RBF神经网络隐层采用标准Gaussian径向基函数，输出层采用线性激活函数，其中数据中心、扩展常数和输出权值均用梯度法求解，它们的学习率均为0.001。其中隐节点数选为10，初始输出权值取[-0.1，0.1]内的随机值，初始数据中心取[-1，1]内的随机值，初始扩展常数取[0.1，0.3]内的随机值，输入采用[0 1]的随机阶跃输入(Write your own RBF neural network, RBF neural network hidden layer
梯度下降
- 这是一篇精华文章，详细的说明了深度学习梯度下降算法的思想，并附有程序结果。(This is an essence of the article, detailed descr iption of the depth of learning, gradient descent algorithm ideas, along with program results.)
专家系统11本
- 专家系统人工智能方面的经典书籍11本打包压缩的，适合对专家系统感兴趣的本科及研究生，以及工程技术人员(Expert systems, artificial intelligence in the classic books, 11 packaged, compressed, suitable for the undergraduate and graduate students interested in expert systems, as well as engineering and te
Project1
- 多层神经网络，在训练过程中采用自适应学习率Adagrad方法。可以实现回归或分类问题。(The adaptive learning rate Adagrad method is adopted in the training process of the multilayer neural network. Regression or classification problems can be achieved.)
面向机器智能的TensorFlow实践
- 适合作为Tensorflow学习的入门书籍，很多基本概念讲的比较清楚(Suitable for Tensorflow as an introduction to learning books, explain many basic concepts more clear)
STDP_simulations
- 仿真实现STDP的波形，《STDP as presynaptic activity times rate of change of postsynaptic activity》代码。(STDP implemented on python, code in "STDP as presynaptic activity times rate of change of postsynaptic activity", arXiv:1509.05936v2.)
Helicopter
- 模拟直升机案例，供研究学习各种飞行控制方法使用(Simulated helicopter case)
Practice_03
- 深度学习,基于python的机器学习，包括挖掘之类(deep learningDepth learning, Python based machine learning, including mining and the like)
聚类算法
- 聚类算法,介绍聚类算法的原理以及应用！原理的推导，以及聚类算法应用的实例。包括迭代过程，已经迭代停止条件。(Clustering Algorithm)
Easy_HMM-master
- HMM隐马尔可夫模型进行一系列的工作。。。(HMM to do some work.)