▍1. CNN
这是一个为1D心电图数据训练而设计的神经网络。(this is a Covoluntional Neural Network deisigned for 1D ECG data training.)
更多选项
▍2. RL01
Overview This repository provides code, exercises and solutions for popular Reinforcement Learning algorithms.
▍3. PR代码及资料
1. 以身高为例，画出男女生身高的直方图并做对比； 2. 采用最大似然估计方法，求男女生身高以及体重分布的参数； 3. 采用贝叶斯估计方法，求男女生身高以及体重分布的参数（注明自己选定的参数情况）； 4. 采用最小错误率贝叶斯决策，画出类别判定的决策面。并判断某样本的身高体重分别为(160,45)时应该属于男生还是女生？为(178,70)时呢？(1. Take the height as an example, draw the histogram of the height of boys and girls and make a comparison. 2. Using the maximum likelihood estimation method, the parameters of height and weight distribution of male and female students are obtained. 3. Using Bayesian estimation method, the parameters of height and weight distribution of male and female students were calculated (indicating the parameters selected by themselves). 4. Using Bayesian decision-making with minimum error rate, the decision-making surface of category decision-making is drawn. When the height and weight of a sample are (160,45), should it belong to boys or girls? For (178,70)?)
▍4. pic2txt.py
图片转字符画，可以保存为txt等格式（Python语言）(convert picture to character painting by python)
▍5. Keras中文手册
Keras是一个高层神经网络库， Keras由纯Python编写而成并基Tensorflow或Theano。 Keras 为支持快 速实验而生，能够把你的idea迅速转换为结果，如果你有如下需求，请选择Keras： 简易和快速的原型设计（keras具有高度模块化，极简，和可扩充特性） 支持CNN和RNN，或二者的结合 支持任意的链接方案（包括多输入和多输出训练） 无缝CPU和GPU切换(Keras is a high-level neural network library. Keras is written from pure Python and is based on Tensorflow or Theano. Keras support fast Quick experimentation can transform your idea into results quickly. If you have the following requirements, please choose Keras: Simple and fast prototyping (keras is highly modular, minimized, and extensible). Support for CNN and RNN or the combination of the two Supports arbitrary link schemes (including multiple input and multiple output training). Seamless CPU and GPU handoff)
▍6. python machine learning
作者是Sebastian Raschka，密歇根州立大学的博士生，他在计算生物学领域提出了几种新的计算方法，还被科技博客Analytics Vidhya评为GitHub上最具影响力的数据科学家。他有一整年都使用Python进行编程的经验，同时还多次参加数据科学应用与机器学习领域的研讨会。在数据科学、机器学习以及Python等领域他拥有丰富的演讲和写作经验，本书可使得不具备机器学习背景的人设计出由数据驱动的解决方案。(The author, Sebastian Raschka, a PhD student at Michigan State University, has come up with several new computational methods in computational biology and has been named the most influential data scientist on GitHub by Analytics Vidhya, a technology blog. He has a year of programming experience using Python, and has attended many seminars in data science applications and machine learning. He has extensive lecture and writing experience in data science, machine learning, and Python, and this book enables people who do not have a machine learning background to design data-driven solutions.)
▍7. flower_CNN
简单的CNN对花进行分类,里面含有数据和代码(Using CNN to classify the flower,which include data and code.)
▍8. 迁移学习对花进行分类
迁移学习简单算法，涉及到迁移学习的一些简单原理，学习参考使用(transfer_learning.py)
▍9. yolo_tensorflow
以tensorflow架构的YOLO算法做目标识别，识别车辆状况。(The tensorflow structure of YOLO algorithm is used for target recognition and vehicle status recognition.)
▍10. Python神经网络编程.pdf+代码
本书首先从简单的思路着手，详细介绍了理解神经网络如何工作所必须的基础知识。第一部分介绍基本的思路，包括神经网络底层的数学知识，第2部分是实践，介绍了学习Python编程的流行和轻松的方法，从而逐渐使用该语言构建神经网络，以能够识别人类手写的字母，特别是让其像专家所开发的网络那样地工作。第3部分是扩展，介绍如何将神经网络的性能提升到工业应用的层级，甚至让其在Raspberry Pi上工作。(This book begins with a brief introduction to the basics necessary to understand how neural networks work. The first part introduces the basic ideas, including the basic mathematical knowledge of the neural network, the second part is the practice, introduces the popular and easy way to learn Python programming, so as to gradually use the language to construct neural networks to recognize human handwritten letters, especially to make them as well as the network developed by experts. Do. Part 3 is an extension of how to improve the performance of neural networks to the level of industrial applications, and even let them work on Raspberry Pi.)
▍11. Python-ELM
深度融合网络 Python-ELM：基于Python的极限学习机以及深度极限学习机(Deep fusion network Python-ELM: Python based extreme learning machine and deep extreme learning machine.)
▍12. peotry_generate-master
运用python自动生成古诗，内含数据处理和模型训练的模块(Poem generation by python with data pre-processing and training model in it which uses LSTM model.)
▍13. Caffe-Python-Tutorial-master
深度学习下的卷积神经网络 剪枝算法 CNN(Deep learning Prune for CNN Deep learning Prune for CNN)
▍14. Deep Learning with Python
本书由Keras之父、现任Google人工智能研究员的弗朗索瓦?肖莱（Fran?ois Chollet）执笔，详尽介绍了用Python和Keras进行深度学习的探索实践，涉及计算机视觉、自然语言处理、生成式模型等应用。书中包含30多个代码示例，步骤讲解详细透彻。由于本书立足于人工智能的可达性和大众化，读者无须具备机器学习相关背景知识即可展开阅读。在学习完本书后，读者将具备搭建自己的深度学习环境、建立图像识别模型、生成图像和文字等能力。(Deep Learning with Python introduces the field of deep learning using the Python language and the powerful Keras library.)
▍15. FCN.tensorflow-master
全卷积网络图像分割。使用python和tensorflow的实现。(Image segmentation with full convolution network.)
▍16. MobileNet-master
我们提供一类称为MobileNets的高效模型，用于移动和嵌入式视觉应用。?MobileNets是基于一个流线型的架构，它使用深度可分离的卷积来构建轻量级的深层神经网络。我们引入两个简单的全局超参数，在延迟度和准确度之间有效地进行平衡。这两个超参数允许模型构建者根据问题的约束条件，为其应用选择合适大小的模型。我们进行了资源和精度权衡的广泛实验，与ImageNet分类上的其他流行的网络模型相比，MobileNets表现出很强的性能。最后，我们展示了MobileNets在广泛的应用场景中的有效性，包括物体检测，细粒度分类，人脸属性和大规模地理定位。(We provide an efficient model called MobileNets for mobile and embedded vision applications. MobileNets is based on a streamlined architecture that USES deep separable convolution to build a lightweight deep neural network. We introduce two simple global hyperparameters to effectively balance the delay and accuracy. These two hyperparameters allow the model builder to select an appropriate size model for its application based on the constraints of the problem. We conducted extensive experiments on resource and precision tradeoffs, and MobileNets showed strong performance compared with other popular network models on the ImageNet classification. Finally, we demonstrate the effectiveness of MobileNets in a wide range of application scenarios, including object detection, fine-grained classification, face attributes, and large-scale geographic localization.)
▍17. CNN1
建立一CNN网络，对mnist手写数据集进行分类。步骤明确。(A CNN network is built to classify MNIST handwritten data sets. Clear steps.)
▍18. RL
强化学习 DQN代码，和通信相关，利用python进行训练，大家可以看看(reinforcement learning)
▍19. tick
采用卡尔曼滤波的方法对两只股票走势相近的股票进行预测，进行低买高卖的操作，从中获利。(Kalman filter method is used to predict two stocks with similar trend, and the operation of buying low and selling high is carried out to profit from it.)
▍20. mnist_train
对0~9的数字进行识别训练。利用tensorflow构建卷积神经网络的框架。(Identify training for 0~9 numbers)
本站资源：696518 个
本站会员：104353 个
总计下载：494898 次
今日上传：0 个
- 优秀论文及配套源码 SVM Short-term-Load-Forecasting
- 综合能源优化含储能
- 用遗传算法改进粒子群GA-PSO算法
- 通过粒子群能够很好的解决优化问题 pso
- 天牛群算法 BSO
- 混沌粒子群优化算法
- 2019年中国研究生数学建模竞赛E题
- 智能算法的Matlab仿真程序及教程
- 《MATLAB R2016a神经网络设计与应用28个案例分析》随书代码
- BAS BP论文及代码
- denoising
- Airy 基模高斯光束
- EMS Microgrid
- 2012年全国大学生数学建模竞赛题目--葡萄酒的评价Wines-Evaluation
- GA-bp
- 本人调试的大作业 源程序模型+论文 intelligent_control_modle
- LSTM的例子、单向LSTM、双向LSTM、多层LSTM
- 遗传算法优化BP网络案例
- 通过yalmip平台调用cplex求解器 microgrid Cplex
- 基于lstm算法在MATLAB对短期风速进行预测 LSTM-regression-master
