Download as pdf or txt
Download as pdf or txt
You are on page 1of 86

DHA SUFFA UNIVERSITY

Deep Learning Spring 2020

Introduction to Convolutional Neural


Network (CNN)
April 15, 2020
• In previous lectures, we discussed dense nets, in which each layer is
fully connected to the adjacent layers.
• We applied those dense networks to classify the MNIST handwritten
characters dataset. In that context, each pixel in the input image is
assigned to a neuron for a total of 784 (28 x 28 pixels) input neurons.
• However, this strategy does not leverage the spatial structure and
relations of each image.
• In particular, this piece of code transforms the bitmap representing
each written digit into a flat vector, where the spatial locality is gone:
#X_train is 60000 rows of 28x28 values --> reshaped in 60000 x 784
X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)
Convolutional Neural Network (CNN)
• In deep learning, a convolutional neural network (CNN, or ConvNet) is a
class of deep neural networks, most commonly applied to analyzing
visual imagery. (Wikipedia)
Computer Vision Problem
Computer Vision Problem
Computer Vision Problem
Computer Vision Problem
Deep Learning as Large Image

64 X 64 X 3 = 12288

1000 X 1000 X 3
= 3 Millions

You might also like