Week four: Deep neural Networks (Deeper neural network)----------2.Programming assignments:building Your depth neural network:step by Step

Building your deep neural network:step by Step

Welcome to your third programming exercise of the deep learning specialization. You'll implement all the building blocks of a neural network and use these building blocks in the next assignment to Bui LD a neural network of any architecture you want. By completing the assignment you'll:

-Develop an intuition of the over all structure of a neural network.

-Write functions (e.g. forward propagation, backward propagation, logistic loss, etc ...) that's would help you decompose yo ur code and ease the process of building a neural network.

-Initialize/update parameters According to your desired structure.

This assignment prepares the upcoming assignment. Take your time-to-complete it and make sure you get the expected outputs when working through the different exercises. In the some code blocks, you'll find a "#GRADED function:functionname" comment. Please don't modify it. After you do, submit your work and check your results. You need to score 70% to pass. Good luck:)!

"Chinese Translation"

Build your deep neural network step-by- stepyou are welcome to the third programming exercise of the deep learning profession. You will implement all the building blocks of the neural network and use these building blocks in the next task to build the neural network of any architecture you want. By completing this task, you will:(1) Intuition that forms all structures of a neural network.

(2) writing functions (such as forward propagation, reverse propagation, logic loss functions, etc.) can help you break down your code and simplify the process of building a neural network.

(3) Initialize/update parameters according to the desired structure.

This task is ready for the upcoming mission. Use your time to complete it, complete the different exercises and make sure you get the results you expect. In some code blocks, you will find a comment for "#GRADED function:functionname". Please do not modify it. When you are done, submit your work and check your results. You need to score 70% to pass. Good luck to you:)!--------------------------------------------------------------------------------------------------------------- -----Building your deep neural network:step by Step

Welcome to your Week 4 assignment (Part 1 of 2)! You are previously trained a 2-layer neural Network (with a single hidden layer). This week, you'll build a deep neural network with the as many layers as you want!

• In this notebook, you'll implement all the functions required to build a deep neural network.
• In the next assignment, you'll use these functions to build a deep neural network for image classification.

After the assignment you'll be able to:

• Use non-linear units like ReLU to improve your model
• Build A deeper neural network (with more than 1 hidden layer)
• Implement an easy-to-use neural network class

Notation:

• Superscript[l] denotes a quantity associated with the LtH layer.
  • Example:a[L] is theLth Layer activation.W[L] andb[L] is the LT-h layer parameters.
• Superscript ( Span id= "mathjax-span-60" class= "Mi" >i) denotes a quantity associated with the ItH example.
  • Example:x (i< Span id= "mathjax-span-78" class= "Mo" >)   is the itH Training example.
• LowerscriptI denotes the itH Entry (item) of a vector.
  • Example:Ai[l] denotes theItH entry of the LT-h layer ' s activations.

Let ' s get started!

Week four: Deep neural Networks (Deeper neural network)----------2.Programming assignments:building Your depth neural network:step by Step