” COMP 4107程序 写作、 辅导Java，CSCOMP 4107: Neural Networks Winter 2021Page 1 of 2Assignment 4This assignment may be completed individually or in groups of 2 or 3.You are recommended to use your project groups. If you are in a group, one student willsubmit all necessary files and the other student(s) will submit a text file specifying members ofthe group and who is submitting. The report must have all students names and IDs.In this assignment, you will develop implementations for self-organizing maps and Hopfieldneural networks for the handwritten digit recognition problem.DescriptionYou may use any and all functionalities found in scikit-learn and tensorflow. You may find Kmeanson MNIST useful too.NoteIn any K-fold experimentation performed ensure that you document mean and standarddeviation of performance measures obtained (e.g., accuracy).Question 1[30 marks]Using the scikit-learn utilities to load the MNIST data, implement a Hopfield network that canclassify the image data for a Subset of the handwritten digits. Subsample the data to onlyinclude images of 1 and 5. Here, correct classification means that if we present an image of a1 an image of a 1 will be recovered; however, it may not be the original image owing to thedegenerate property of this type of network. You are expected to document classificationaccuracy as a function of the number of images used to train the network. Remember, aHopfield network can only store approximately 0.15N patterns with the one shot learningdescribed in Lecture 13.Question 2[30 marks]Develop a feed forward RBF neural network in python that classifies the complete set of imagesfound in the MNIST dataset. You are to train your neural network using backpropagation. Youshould use gaussian functions as Your radial basis functions. You must show that you have:1. Used K-means to design the hidden layer in your network. You may use any existingcode for running K-means (you do not need to code your own), but you must cite yoursources in the report.2. Performed K-fold cross correlation.3. Investigated the performance of your neural network for different sizes of hidden layer.COMP 4107: Neural Networks Winter 2021Page 2 of 24. Investigated the performance of your Neural network when using dropout in the hiddenlayer. A paper on dropout is here.Question 3[30 marks]We can use self organizing maps as a substitute for K-means.In Question 2, K-means was used to compute the number of hidden layer neurons to be used inan RBF network. Using a 2D self-organizing map compare the clusters when compared to Kmeansfor the MNIST data. Sample the Data to include only images of 1 and 5. Use thescikit-learn utilities to load the data. You are expected to (a) document the dimensions of theSOM computed and the learning parameters used to generate it (b) provide 2D plots of theregions for 1 and 5 for both the SOM and K-means solutions. You may project your K-meansdata using SVD to 2 dimensions for display purposes.请加QQ：99515681 或邮箱：99515681@qq.com WX：codehelp
“
添加老师微信回复‘’官网 辅导‘’获取专业老师帮助，或点击联系老师1对1在线指导。
