Help needed with this project

Department of Electrical Engineering and Computer Science CIS 666 Artificial Intelligence Spring 20 21 Project 5 (Due date: 0 3/17 /202 1) The objective of this project is to u se the perceptron learning method and design an artificial neural network (ANN) to train a system for the recognition of handwritten digits (0, 1, …, 9) . Use the three -layer feed -forward network architecture (input layer, hidden layer, and output layer) with the multilayer perceptron learning method and the error back -propagation algorithm for the recognition of handwritten digits (0, 1,...., 9). Design a fully connected network structure of input layer ( 784 input nodes ), hidden layer (number of hidden nodes as specified below), and output layer ( 10 output nodes ). The input to your mul tilayer network architecture will be a set of pixels representing a 28×28 image of handwritten digits. The output should indicate which of the digits (0,....,9) is in the input image. Use the MNIST database of handwritten digits available on Blackboard -Homepage -Handwritten Digits Dataset . Select a subset of the MNIST database consisting around 10000 images of handwritten digits (0,...,9) for training the system, and use another 1 000 images for testing the system. Use the same set that was used for the previous project (project 4) for training and testing you r network. Plot a learning curve that illustrates the mean square error versus iterations. (One iteration: apply all the training inputs once to the network and compute the mean square error ). Plot the percentage error in testing your handwritten digit recognition system as a bar chart. (Mean error occurred while testing each digit with the test data ). • Task #1: Repeat this expe riment for different learning rate parameters (at least 3 experiments. Start with a large value and gradually decrease to a small value ). • Task #2: Repeat Task #1 for different number of hidden nodes (10, 35, 100, 300 , 500 ). • Task # 3: Compare your results with the SVM and SLP results ( what you have got from project s 3 and 4 ). Notes: • The project should be implemented in Python. • Only one single (zipped) file should be submitted through Blackboard for evaluation, which contains : ✓ The project report as PDF file that includes the methodology, equations used, implementation results and discussion, conclusion, appropriate technical refe rences, etc. ✓ The program codes (source files) along with the dataset used. • Late submissions will not be accepted.