【学习笔记】WEEK3_Shallow Neural Network_Neural Network Representation
2018-04-03 15:47
393 查看
1、计算神经网络的层数时,输入层不计算在内
例:下图为2层神经网络、隐藏层(Hidden Layer)为第1层,输出层(Output Layer)为第2层
2、各层的参数的维数
1)第 [1] 层(隐藏层,输入层为第0层)的参数 w-[1], b-[1] 中:
(1)w-[1]为(4, 3)矩阵,对应本层[1](隐藏层)的4个神经元与上一层[0](输入层)的3个输入
(2)b-[1]为(4, 1)向量,对应本层[1](隐藏层)的4个神经元,每个神经元对应的b_i为一个一维实数
2)第[2]层(输出层)的参数w-[2], b-[2]中:
(1)w-[2]为(1, 4)矩阵,对应本层[2](输出层)的1个神经元与上一层[1]的4个神经元
(2)b-[2]为(1, 1)向量(即实数),对应本层[2](输出层)的1个神经元
3、(无随堂测验)
例:下图为2层神经网络、隐藏层(Hidden Layer)为第1层,输出层(Output Layer)为第2层
2、各层的参数的维数
1)第 [1] 层(隐藏层,输入层为第0层)的参数 w-[1], b-[1] 中:
(1)w-[1]为(4, 3)矩阵,对应本层[1](隐藏层)的4个神经元与上一层[0](输入层)的3个输入
(2)b-[1]为(4, 1)向量,对应本层[1](隐藏层)的4个神经元,每个神经元对应的b_i为一个一维实数
2)第[2]层(输出层)的参数w-[2], b-[2]中:
(1)w-[2]为(1, 4)矩阵,对应本层[2](输出层)的1个神经元与上一层[1]的4个神经元
(2)b-[2]为(1, 1)向量(即实数),对应本层[2](输出层)的1个神经元
3、(无随堂测验)
相关文章推荐
- 【学习笔记】WEEK3_Shallow Neural Network_Explanation for Vectorized Implementation
- 【学习笔记】WEEK3_Shallow Neural Network_Neural Networks Overview
- 【学习笔记】WEEK3_Shallow Neural Network_Gradient descent for Neural Networks
- 【学习笔记】WEEK3_Shallow Neural Network_Backpropagation intuition (optional)
- 【学习笔记】WEEK3_Shallow Neural Network_Activation functions
- 【学习笔记】WEEK3_Shallow Neural Network_Computing a Neural Network's Output
- 【学习笔记】WEEK3_Shallow Neural Network_Why do you need non-linear activation functions?
- 【学习笔记】WEEK3_Shallow Neural Network_Random Initialization
- 【学习笔记】WEEK3_Shallow Neural Network_Vectorizing across multiple examples
- 【学习笔记】WEEK3_Shallow Neural Network_Derivatives of activation functions
- 【学习笔记】WEEK 1_Introduction to Deep Learning_What is a neural network?
- 【学习笔记】WEEK2_Practice Questions_Quiz_Neural Network Basics
- 【学习笔记】WEEK3_Practice Questions_Quiz_Shallow Neural Networks
- 学习笔记5 Supervised Convolutional Neural Network 之 Stochastic Gradient Descent
- [coursera/dl&nn/week3]Shallow Neural Network(summary&question)
- 深度学习论文笔记--Recover Canonical-View Faces in the Wild with Deep Neural Network
- 学习笔记6 Supervised Convolutional Neural Network 之 Convolutional Neural Network
- CNTK学习笔记 -- Computation Network part3 -- Convolutional Neural Network
- 台大李宏毅Machine Learning 2017Fall学习笔记 (11)Convolutional Neural Network
- 【Deep Learning学习笔记】NEURAL NETWORK BASED LANGUAGE MODELS FOR HIGHLY INFLECTIVE LANGUAGES_google2009