Starting from:
$35

$29

Pattern Recognition (Homework 2) Solution


 Objective: Implementation of handwritten number recognition by ANN.

 

This is our 2nd exercise in a series that deal with the MNIST Database (http://yann.lecun.com/exdb/mnist/). The MNIST Database is a collection of samples of handwritten digits from many people, originally collected by the National Institute of Standards and Technology (NIST), and modified to be more easily analyzed computationally.

 

Read: “Using neural nets to recognize handwritten digits”
 (http://neuralnetworksanddeeplearning.com/chap1.html) .

Use the MNIST data samples (http://yann.lecun.com/exdb/mnist/) for training and testing.
Develop a code in Matlab (or Python) to design a neural network to perform 10 digit classification.  
Experiment with 3 different combination of layers and hidden units.
Summarize the results and report them. Include the code you ran with your report.
 

 

 

WHAT TO SUBMIT:

Submit your code, results (error vs. training epoch), and discussions.

More products