Lectures‎ > ‎

Lecture 08: Classification with Neural Networks

Classifcation with Neural Networks-2011



Additional Reading


  • Marinai et al: Artificial Neural Networks for Document Analysis and Recognition View
  • LeCun et al: Gradient-based learning applied to document recognition View

Exercises

1) Download the following files from attachments:

train-images-idx3-ubyte.gz
train-labels-idx1-ubyte.gz
mnist.py

2) Add following lines of code in your python script to get mnist database in python

from mnist import *
images = mnist_read("train-images-idx3-ubyte.gz")
classes = mnist_read("train-labels-idx1-ubyte.gz")

Write a perceptron classifier to separate “6” and “3”. Divide your data into suitable training and testing sets.
e.g; use training set sizes of 100, 1000, 10000 etc. and discuss your results.


Ċ
Thomas M. Breuel,
Jun 9, 2010, 7:13 AM
Ċ
Thomas M. Breuel,
Jul 19, 2010, 3:31 AM
Ċ
Sheikh Faisal Rashid,
Jul 4, 2011, 10:43 AM
Ċ
Sheikh Faisal Rashid,
Jul 4, 2011, 11:18 AM
ċ
mnist.py
(1k)
Ilya Mezhirov,
Jun 30, 2011, 8:13 AM
ċ
train-images-idx3-ubyte.gz
(9680k)
Sheikh Faisal Rashid,
Jul 4, 2011, 11:34 AM
ċ
train-labels-idx1-ubyte.gz
(28k)
Sheikh Faisal Rashid,
Jul 4, 2011, 11:34 AM
Comments