吴恩达Machine-Learning 课后练习jupyter版本答案 exercise4(系列持续更新)
答案链接:exercise4
https://github.com/NealChalmers/Stanford-CS229-ML-AndrewNg/tree/master/Exercise4
谢谢你的star
Introduction
In this exercise, you will implement the backpropagation algorithm for neural networks and apply it to the task of hand-written digit recognition. Before starting on the programming exercise, we strongly recommend watching the video lectures and completing the review questions for the associated topics.
All the information you need for solving this assignment is in this notebook, and all the code you will be implementing will take place within this notebook. The assignment can be promptly submitted to the coursera grader directly from this notebook (code and instructions are included below).
Before we begin with the exercises, we need to import all libraries required for this programming exercise. Throughout the course, we will be using numpy for all arrays and matrix operations, matplotlib for plotting, and scipy for scientific and numerical computation functions and tools. You can find instructions on how to install required libraries in the README file in the github repository.
Submission and Grading
After completing each part of the assignment, be sure to submit your solutions to the grader. The following is a breakdown of how each part of this exercise is scored.
Section Part Submission function Points
1 Feedforward and Cost Function nnCostFunction 30
2 Regularized Cost Function nnCostFunction 15
3 Sigmoid Gradient sigmoidGradient 5
4 Neural Net Gradient Function (Backpropagation) nnCostFunction 40
5 Regularized Gradient nnCostFunction 10
Total Points 100
You are allowed to submit your solutions multiple times, and we will take only the highest score into consideration.