版权说明:本文档由用户提供并上传,收益归属内容提供方,若内容存在侵权,请进行举报或认领
文档简介
1、MLP,Week 03,Outline,Introduction Architecture Learning Process Learning Issues Summary and Further Discussion,Limit of Perceptron,XOR Problem,Limit of Perceptron,Nonlinear Separable Problem,+,Positive Class,Negative Class,Limit of Perceptron,Linear Classifier Linear Decision Boundary in Perceptron 2
2、 Dimensional Space: Line 3 Dimensional Space: Plane N Dimensional Space: Hyperplane Unsolvable to Problems XOR Problem Nonlinear Separable Research on Neural Network in Dark Age 1960 1980 (20 years) Motivation for inventing MLP Addition of intermediate layer called hidden layer Solvable even to Nonl
3、inear Separable,Limit of Perceptron,Solution to XOR Problem,1,1,bias,-0.5,0, 00 0, 11 1, 01 1, 11,Limit of Perceptron,Solution to XOR Problem,1,1,bias,-1.5,0, 00 0, 10 1, 00 1, 11,Limit of Perceptron,Solution to XOR Problem,0, 00 0, 11 1, 01 1, 10,1,1,1,1,1,-1.5,bias,bias,-1.5,-0.5,-0.5,Limit of Per
4、ceptron,Overview of MLP Addition of one more layer between input and output layer Added Layer called Hidden Layer Boundary: Linear Quadratic Solvable even to non-linear separable classification Approximation of any nonlinear function By Universe Theorem,Architecture,Input Layer,Output Layer,Hidden L
5、ayer,Architecture,Input Layer Receive input vector #Nodes = dimension of input vector Net input: element of input vector Output = Net Input Linear Function as Activation Function,Architecture,Input Nodes,Architecture,Hidden Layer Encode Input Vector into another Form Intermediate Layer Receive Net I
6、nput as the summation of product of input value and weights Compute its own output and transfer it to output layer #Nodes: Arbitrary Too Many Nodes Overfitting and High Complexity Too Few Nodes Underfitting and Poor Learning Linear Boundary Quadratic Boundary Activation Function: Sigmoid Function,Ar
7、chitecture,Hidden Nodes,Architecture,Output Layer Classification Output Value = CSV (Categorical Score Value) #Output Nodes = #Classes (or Categories) Output Value with Maximum Value Classified Class or Category Regression Univariate Regression: #Output Node = 1 Multivariate Regression: #Ouput Nodes
8、 = # Variables Output Value Estimated Output Value,Architecture,Hidden Nodes,Learning Rule: Back Propagation,Feed Forward,Output Computation,Input Layer,Output Layer,Hidden Layer,Learning Rule: Back Propagation,Weight Update,Input Layer,Output Layer,Hidden Layer,Backward,Learning Rule: Back Propagat
9、ion,Notations,Learning Rule: Back Propagation,Notations,Learning Rule: Back Propagation,Gradient Descent for Weights Optimization,Error Function to minimize,E,w,Learning Rule: Back Propagation,Update weight between output and hidden,Learning Rule: Back Propagation,Update weight between hidden and in
10、put,.,jth input,ith hidden,First output,cth ouput,.,Learning Rule: Back Propagation,Update weight between hidden and input,Learning Rule: Back Propagation,Batch Learning,Input: Training Examples Initialize Weights at Random Iterate T times for each training example compute values of hidden nodes com
11、pute value of output nodes compute average error update weights between output and hidden update weights between hidden and input Output: Optimized Weights,Learning Rule: Back Propagation,Interactive Learning,Input: Training Examples Initialize Weights at Random Iterate T times for each training exa
12、mple compute values of hidden nodes compute value of output nodes compute average error update weights between output and hidden update weights between hidden and input Output: Optimized Weights,Learning Issues,Optimization Architecture #Input Nodes Dimensions #Output Nodes Binary Classification: On
13、e node Multiple Classification: #Classes Univarite Regression: One node Multivariate Regression: #Output Variables #Hidden Nodes ? Validation Set Set of some training examples separated from given Training examples Reduction of #Training Examples for Training Parameter Optimization (#Learning epochs
14、) Falling into Local Minima Reducing following descent Once reach minima, not moving,Learning Issues,Parameter Settings Learning Rate: Arbitrary between 0 and 1 Close to 1: Fast Learning but Fluctuation Close to 0: Slow Learning but Stability #Hidden Nodes Many Nodes: Much Time for Learning, Overfit
15、ting Few Nodes: Less Time for Learning , Underfitting Training Iteration: Too Many: Overfitting Too Few: Underfitting,Learning Issues,Validation Set,Training Set,Test Set,For Training MLP,For Evaluating Performance Hide Target Labels during Training,Training Set,Validation Set,Learning Issues,Fallin
16、g into local minima,E,w,Learning Issues,Other Issues of MLP Obtaining Training Examples No Evidence to given answer Slow Learning Large Dimension in its application to real problems,Summary and Further Discussions,Summary Multiple Perceptrons as solution to Limit of Perceptron Architecture of MLP Le
17、arning Process of MLP Learning Issues of MLP,Summary and Further Discussions,Virtual Training Examples Solution to insufficient number of training examples Other Training Examples derived from given Training Examples Original Training Examples Actual Ones labeled with their Target Outputs, initially
18、 Derived Training Examples Virtual Ones without their target outputs Target Output by Generalization of MLP Actual Ones and Virtual Ones Training,Summary and Further Discussions,Co Learning Two MLPs: MLP 1 and MLP 2 Training Examples: Labeled + Unlabeled MLP 1 Trained by Labeled Ones MLP 2 Trained by Labeled Ones MLP 1 labels unlabeled training examples by its own generalization Set 1 MLP 2 labels unlabeled training examples by its o
温馨提示
- 1. 本站所有资源如无特殊说明,都需要本地电脑安装OFFICE2007和PDF阅读器。图纸软件为CAD,CAXA,PROE,UG,SolidWorks等.压缩文件请下载最新的WinRAR软件解压。
- 2. 本站的文档不包含任何第三方提供的附件图纸等,如果需要附件,请联系上传者。文件的所有权益归上传用户所有。
- 3. 本站RAR压缩包中若带图纸,网页内容里面会有图纸预览,若没有图纸预览就没有图纸。
- 4. 未经权益所有人同意不得将文件中的内容挪作商业或盈利用途。
- 5. 人人文库网仅提供信息存储空间,仅对用户上传内容的表现方式做保护处理,对用户上传分享的文档内容本身不做任何修改或编辑,并不能对任何下载内容负责。
- 6. 下载文件中如有侵权或不适当内容,请与我们联系,我们立即纠正。
- 7. 本站不保证下载资源的准确性、安全性和完整性, 同时也不承担用户因使用这些下载资源对自己和他人造成任何形式的伤害或损失。
最新文档
- 2025 小学六年级语文下册 背诵方法 理解记忆课件
- 跨境电商海外仓2025年培训安排协议
- 口罩质量追溯协议2025年
- 2025年办公楼中央空调风管清洁协议
- 2025年VR虚拟现实内容制作合同协议
- 酒店管理服务合作协议2025年
- 深度解析(2026)《GBT 39160-2020薄膜太阳能电池用碲锌镉靶材》(2026年)深度解析
- 深度解析(2026)《GBT 35620.2-2024养老保险精算数据指标体系规范 第2部分:城乡居民基本养老保险》
- 2026年八年级物理上册期末考试试卷及答案(四)
- 内科学总论物理因子治疗课件
- 《化工企业可燃液体常压储罐区安全管理规范》解读课件
- 电动汽车原理与构造第3版何洪文课后答案
- 道家思想英文简介课件
- 来料检验流程与注意事项
- 当代科学技术概论知到章节答案智慧树2023年哈尔滨工业大学
- 热爱摄影手机摄影知识培训PPT教学课件
- GB/T 7690.3-2013增强材料纱线试验方法第3部分:玻璃纤维断裂强力和断裂伸长的测定
- GB/T 33525-2017输送带覆盖层性能类别
- GB/T 32891.2-2019旋转电机效率分级(IE代码)第2部分:变速交流电动机
- GB/T 30675-2014阁楼式货架
- GB/T 15622-1995液压缸试验方法
评论
0/150
提交评论