本课程为精品课,您可以登录eeworld继续观看: What is Machine Learning继续观看 课时1:Welcome 课时2:What is Machine Learning 课时3:Supervised Learning 课时4:Unsupervised Learning 课时5:Model Representation 课时6:Cost Function 课时7:Cost Function - Intuition I 课时8:Cost Function - Intuition II 课时9:Gradient Descent 课时10:Gradient Descent Intuition 课时11:Gradient Descent For Linear Regression 课时12:What-'s Next 课时13:Matrices and Vectors 课时14:Addition and Scalar Multiplication 课时15:Matrix Vector Multiplication 课时16:Matrix Matrix Multiplication 课时17:Matrix Multiplication Properties 课时18:Inverse and Transpose 课时19:Multiple Features 课时20:Gradient Descent for Multiple Variables 课时21:Gradient Descent in Practice I - Feature Scaling 课时22:Gradient Descent in Practice II - Learning Rate 课时23:Features and Polynomial Regression 课时24:Normal Equation 课时25:Normal Equation Noninvertibility (Optional) 课时26:Basic Operations 课时27:Moving Data Around 课时28:Computing on Data 课时29:Plotting Data 课时30:Control Statements- for, while, if statements 课时31:Vectorization 课时32:Working on and Submitting Programming Exercises 课时33:Classification 课时34:Hypothesis Representation 课时35:Decision Boundary 课时36:Cost Function 课时37:Simplified Cost Function and Gradient Descent 课时38:Advanced Optimization 课时39:Multiclass Classification- One-vs-all 课时40:The Problem of Overfitting 课时41:Cost Function 课时42:Regularized Linear Regression 课时43:Regularized Logistic Regression 课时44:Non-linear Hypotheses 课时45:Neurons and the Brain 课时46:Model Representation I 课时47:Model Representation II 课时48:Examples and Intuitions I 课时49:Examples and Intuitions II 课时50:Multiclass Classification 课时51:Cost Function 课时52:Backpropagation Algorithm 课时53:Backpropagation Intuition 课时54:Implementation Note- Unrolling Parameters 课时55:Gradient Checking 课时56:Random Initialization 课时57:Putting It Together 课时58:Autonomous Driving 课时59:Deciding What to Try Next 课时60:Evaluating a Hypothesis 课时61:Model Selection and Train-Validation-Test Sets 课时62:Diagnosing Bias vs. Variance 课时63:Regularization and Bias-Variance 课时64:Learning Curves 课时65:Deciding What to Do Next Revisited 课时66:Prioritizing What to Work On 课时67:Error Analysis 课时68:Error Metrics for Skewed Classes 课时69:Trading Off Precision and Recall 课时70:Data For Machine Learning 课时71:Optimization Objective 课时72:Large Margin Intuition 课时73:Mathematics Behind Large Margin Classification (Optional) 课时74:Kernels I 课时75:Kernels II 课时76:Using An SVM 课时77:Unsupervised Learning- Introduction 课时78:K-Means Algorithm 课时79:Optimization Objective 课时80:Random Initialization 课时81:Choosing the Number of Clusters 课时82:Motivation I- Data Compression 课时83:Motivation II- Visualization 课时84:Principal Component Analysis Problem Formulation 课时85:Principal Component Analysis Algorithm 课时86:Choosing the Number of Principal Components 课时87:Reconstruction from Compressed Representation 课时88:Advice for Applying PCA 课时89:Problem Motivation 课时90:Gaussian Distribution 课时91:Algorithm 课时92:Developing and Evaluating an Anomaly Detection System 课时93:Anomaly Detection vs. Supervised Learning 课时94:Choosing What Features to Use 课时95:Multivariate Gaussian Distribution (Optional) 课时96:Anomaly Detection using the Multivariate Gaussian Distribution (Optional) 课时97:Problem Formulation 课时98:Content Based Recommendations 课时99:Collaborative Filtering 课时100:Collaborative Filtering Algorithm 课时101:Vectorization- Low Rank Matrix Factorization 课时102:Implementational Detail- Mean Normalization 课时103:Learning With Large Datasets 课时104:Stochastic Gradient Descent 课时105:Mini-Batch Gradient Descent 课时106:Stochastic Gradient Descent Convergence 课时107:Online Learning 课时108:Map Reduce and Data Parallelism 课时109:Problem Description and Pipeline 课时110:Sliding Windows 课时111:Getting Lots of Data and Artificial Data 课时112:Ceiling Analysis- What Part of the Pipeline to Work on Next 课时113:Summary and Thank You 课程介绍共计113课时,19小时28分58秒 机器学习 吴恩达 此课程将广泛介绍机器学习、数据挖掘与统计模式识别的知识。主题包括:(i) 监督学习(参数/非参数算法、支持向量机、内核、神经网络)。(ii) 非监督学习(聚类、降维、推荐系统、深度学习)。(iii) 机器学习的优秀案例(偏差/方差理论;机器学习和人工智能的创新过程)课程将拮取案例研究与应用,学习如何将学习算法应用到智能机器人(观感,控制)、文字理解(网页搜索,防垃圾邮件)、计算机视觉、医学信息学、音频、数据挖掘及其他领域上。 上传者:老白菜 猜你喜欢 利用高压母线转换模块 (BCM) 为LED驱动器供电 TI.com 视频系列 How do I 电赛项目《自动纸张计数显示装置》 直播回放: 安全系列19 - 符合无线电充电联盟WPC的无线充电身份验证 2017 - TI 嵌入式产品总览 随机信号处理 西电 赵国庆 Cypress TrueTouch 触摸屏解决方案 2015瑞萨电子设计大赛作品 热门下载 水木清华DSP技术精华 dsp学习不可或缺的资料 基于STC89C52单片机智能小车设计_陈飞鹏 MAX15458 关联分类算法采用贪心算法发现高质量分类规则 AVR单片机的天然气发动机电控系统设计 时序约束整理 这种数学模型的使用能使旅游学更具学科性 通信电子电路基础 IBM笔记本机型与所用屏幕品牌、型号对照表 振荡电路的设计与应用-稻叶-293页-20.3M.pdf 热门帖子 【极海APM32F407】5,跑一下内部温度传感器例子 极海的这款芯片,在ADC1也有温度传感器。而且例程中使能了DMA功能:voidDMA_Init(uint32_t*Buf){/*DMAConfigure*/DMA_Config_TdmaConfig;/*EnableDMAclock*/RCM_EnableAHB1PeriphClock(RCM_AHB1_PERIPH_DMA2);/*sizeofbuffer*/dmaConfig.bufferSize=1;/* ddllxxrr 如何对spwm波进行锁相??、、. 目前在学习dsp,产生spwm波。只会通过改变的PRD来改变spwm波的频率,现在我想让它spwm的频率,幅值,相位自动调节,进而形成可以并入电网的交流电,不知道各位老师有没有经验可以学习下?如何对spwm波进行锁相??、、.我也需要哎 huangyiqian1000 FSMC时序怎么计算 FSMC的时序怎么计算,我用103ZE驱动CS8900A和IS61LV25616,CS8900A工作在IO模式,初始化怎么也不对,同样的电路在710上工作很好,我怀疑是我的FSMC配置的不对,下面是我的初始化代码,各位大哥谁用过FSMC,指点一下,谢谢了FSMC_NORSRAMInitTypeDefFSMC_NORSRAMInitStructure;FSMC_NORSRAMTimingInitTypeDefp;GPIO_InitTypeDefGPIO_InitStructu kittenqq 开启定时器中断对程序的影响 while(1){if(PressRelease){switch(statetable){caseWELCOME:UARTSendArray(pleaseenterthreenumbersbetween0and10torepresentthebrightnessofthreemodes\\n,88);pwm(100);break;caseB1:pwm((input-48)*100);break; 很想变学霸 示波器汽车涡轮增压电磁阀波形及分析 涡轮增压器在不增加发动机排气量下增加功率,涡轮增压器的好处也包括在有效的转速范围内增加转矩,与相同功率下自然吸气的发动机相比,提高了燃油经济性,降低废弃排放污染。然而,为了获得最好的加速性、节气门反应性及发动机耐用性,增压器的压强应备控制或调节。如果增压压强不能适当调节,驾驶性能会受到影响或造成发动机损坏。调节增压压强是通过改变废气量,即旁通废气侧涡轮机气路的方法到达的,当更多的废气绕过涡轮机排出后,增压压强减少了。废气门阀通过打开和关闭来调节旁通量。废气阀由真空伺服电动机控 Micsig麦科信 C6678 EDMA 搬运有内存保护吗? 各位老师好,我再6678平台下,用edma的CC1做数据搬运。pingset:将数据从一个内存固定源地址src搬到内存ping区域,pongset:将数据从该地址搬到pong区域。ping和pong在msm上。pingpong搬运相互link。当ping搬运完成之后,edma发出中断,core0对ping区域进行处理,pong搬运完之后,core0处理pong数据。现在中断程序只是简单的将ping或pong区域的数据搬运到另外一个数组里面,然后问题出现了,如果中断程序什么都不做,则e bianpang 网友正在看 BIST2 Parallel ORA MISR 软件自带原理图库介绍与编辑 第5课 NAND FLASH控制器 各种模拟调制抗噪声性能分析及应用 ams 医用/工业CT医疗影像探测器芯片应用与解决方案 VSB和幅度调制抗噪声性能分析 字符设备驱动(第一节) 智能扬声器投影技术