资源列表
斯坦福大学-深度学习基础教程
- 斯坦福大学的深度学习,基础教程。ps:要求先学完吴恩达的机器学习基础再来看,不然看不懂(Depth study of Stanford University, basic course. Ps: needs to learn the basis of Wu Enda's machine learning first, or you can't understand it.)
gpml-matlab-v4.1-2017-10-19
- MATLAB code. It was originally demonstrated the main algorithms from Rasmussen and Williams: Gaussian Processes for Machine Learning.(The code provided here originally demonstrated the main algorithms from Rasmussen and Williams: Gaussian Processes f
linear code
- 感知器和线性神经网络,有助于初次接触人工智能的学生(the codes contain a lot of good data.besides,they are helpful for you get the main thought soon.)
SVM-tool
- 支持向量机的里一个工具包,里面的函数我自己改了一下,有所优化(Support vector machine in a toolkit, the function inside I changed it, some optimization)
支持向量机(ML in action)整理
- Python实现支持向量机的算法,拟合和分类,包括0-9数字识别(Python implements the algorithm, fitting and classification of support vector machines, including 0-9 digital recognition)
Deep Learning with Python-Manning
- 深入学习Python介绍领域的深入学习使用Python语言和强大的Keras图书馆。通过keras创造者和谷歌人工智能研究者弗兰?ois Chollet写的,这本书让你了解通过直观的解释和实例。您将探索具有挑战性的概念和实践与计算机视觉,自然语言处理和生成模型的应用程序。当你完成学业的时候,你将具备在自己的项目中应用深度学习的知识和动手能力。(Deep Learning with Python introduces the field of deep learning using the Pyt
MLInActionCode-master
- 机器学习实战的源代码集合,第一部分主要介绍机器学习基础,以及如何利用算法进行分类,并逐步介绍了多种经典的监督学习算法,如k近邻算法、朴素贝叶斯算法、Logistic回归算法、支持向量机、AdaBoost集成方法、基于树的回归算法和分类回归树(CART)算法等。第三部分则重点介绍无监督学习及其一些主要算法:k均值聚类算法、Apriori算法、FP-Growth算法。第四部分介绍了机器学习算法的一些附属工具(Machine learning combat source code collection
DL_L1
- 关于最新的python3上的decision tree 的算法(An algorithm for decision tree on the latest python3)
SVM_face_recognition
- 基于python的使用SVM的算法实现人脸的识别程序(Face recognition program based on Python based algorithm using SVM)
figure_recognition
- 基于python3的利用神经网络进行的手写数字识别程序。(A handwritten numeric recognition program based on python3 based on Neural Network.)
DL_basic_code
- 基于python3的机器学习中可能用到的一些基本的算法。(Some basic algorithms that may be used in machine learning based on python3.)
Deep_Learning(深度学习)
- 深度学习入门教程,由浅入深,包含深度学习的基本思想,各种训练模型已经卷积神经网络相关内容(Deep learning introduction course, from shallow to deep, including deep learning basic ideas, various training models have convolution neural network related content)