资源列表
深度学习机器学习入门进阶精品名师视频课程
- (23套)深度学习+(48套)机器学习入门+进阶精品名师视频课程((23 sets) deep learning + (48 sets) machine learning + video course of advanced Elite Teachers)
人工智能:一种现代方法(第2版).pdf
- 人工智能:一种现代方法:帮你更好的理解人工智能,系统的学习未开科技人工智能,走进AI时代。(Artificial Intelligence: A Modern Approach: Helping You to Understand Artificial Intelligence Better, Systemic Learning Without Artificial Intelligence, Into The AI Age.)
firefly algorithm
- 实现萤火虫算法,实现了一篇论文,主要是优化算法,用于寻找多目标时的最优值,效果比较理想,可以通过动图展示出来(Firefly algorithm to achieve)
ELM分类器
- ELM是基于深度学习的分类器,运算速度快。 在B_data.m里导入待分类矩阵B.mat(1-n列为特征值,n列为标签);运行B_data.m;再打开fuzzyEn_main.m并运行即可。(ELM is based on depth learning classifier, computing speed. In B_data.m imported matrix to be classified B.mat (1-n as eigenvalues, n as a label); Run B
libs
- 用矩阵补全或张量补全的方法,对缺失数据进行重构(matrix completion or tensor completion ,to reconstruct the missing data)
深度学习python代码
- 深度学习代码,Python,自己觉得还可以,愿对你有所帮助。(Deep study code, Python, feel that you can, may be helpful to you.)
bp神经网络
- 两个bp神经网络的预测程序(含有详细注释)。(Prediction program for two BP neural networks (detailed notes))
bp神经网络
- 根据Ecotect 模拟的12种不同的建筑形状进行能量分析,数据集包括768个样本和8个特征属性,旨在预测房屋的热负荷和冷负荷。BP神经网络(According to the 12 different building shapes simulated by Ecotect, we carry out energy analysis. The dataset includes 768 samples and 8 characteristic attributes, aiming at predi
卷积神经网络
- 建立卷积神经网络;使用训练样本对卷积神经网络进行训练;使用测试样本对卷积神经网络进行测试;卷积神经网络的前向计算过程;计算目标函数值,以及目标函数对权值和偏置的偏导数;更新网络的权值和偏置。(A convolutional neural network; convolutional neural network is trained using the training samples; test the convolutional neural network using the test s
Scikit-Learn与TensorFlow机器学习实用指南
- Scikit-Learn与TensorFlow机器学习实用指南(Scikit-Learn and TensorFlow machine learning practical guide)
深度学习的研究与发展
- 帮助你学习深度学习,理解深度学习的实战算法。常有在深度学习的知识海洋(Help you to learn deep learning)
模拟退火算法
- 模拟退火算法来源于固体退火原理,是一种基于概率的算法,将固体加温至充分高,再让其徐徐冷却,加温时,固体内部粒子随温升变为无序状,内能增大,而徐徐冷却时粒子渐趋有序,在每个温度都达到平衡态,最后在常温时达到基态,内能减为最小。(The simulated annealing algorithm derived from the principle of solid annealing, is a kind of algorithm based on probability, the solid h