Implementing Deep Net Architectures to Recognize Handwritten Digits

In the previous chapters, we have been through the essential concepts and have set up tools that are required for us to get our journey into Artificial Intelligence (AI) started. We also built a small prediction app to get our feet wet with the tools we will be using.

In this chapter, we are going to cover a more interesting and popular application of AI – Computer Vision, or Machine Vision. We will start by continuing from the previous chapter and ease into building convolutional neural networks (CNN), the most popular neural network type for Computer Vision. This chapter will also cover the essential concepts that were promised in Chapter 1, Artificial Intelligence Concepts and Fundamentals, but, in contrast, this chapter will have a very hands-on approach.

We will be covering the following topics in...

Building a feedforward neural network to recognize handwritten digits, version one

In this section, we will use the knowledge that we gained from the last two chapters to tackle a problem that has unstructured data – image classification. The idea is to take a dive into solving a Computer Vision task with the current setup and the basics of neural networks that we are familiar with. We have seen that feedforward neural networks can be used for prediction using structured data; let's try that on images to classify handwritten digits.

To solve this task, we are going to leverage the MNSIT database and use the handwritten digits dataset. MNSIT stands for Modified National Institute of Standards and Technology. It is a large database that's commonly used for training, testing, and benchmarking image-related tasks in Computer Vision.

The MNSIT digits dataset contains...

Building a feedforward neural network to recognize handwritten digits, version two

In the previous section, we built a very simple neural network with just an input and output layer. This simple neural network gave us an accuracy of 86%. Let's see if we can improve this accuracy further by building a neural network that is a little deeper than the previous version:

1. Let's do this on a new notebook. Loading the dataset and data pre-processing will be the same as in the previous section:

import numpy as np
np.random.seed(42)
import keras
from keras.datasets import mnist 
from keras.models import Sequential 
from keras.layers import Dense
from keras.optimizers import SG
#loading and pre-processing data
(X_train,y_train), (X_test,y_test)= mnist.load_data()
X_train= X_train.reshape( 60000, 784). astype('float32')
X_test =X_test.reshape(10000,784).astype('float32&apos...

Building a deeper neural network

In this section, we will use the concepts we learned about in this chapter to build a deeper neural network to classify handwritten digits:

1. We will start with a new notebook and then load the required dependencies:

import numpy as np
np.random.seed(42)
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
# new!
from
keras.layers.normalization
# new!
import
BatchNormalization
# new!
from keras import regularizers
# new! 
from keras.optimizers
import SGD

2. We will now load and pre-process the data:

(X_train,y_train),(X_test,y_test)= mnist.load_data()
X_train= X_train.reshape(60000,784).
astype('float32')
X_test= X_test.reshape(10000,784).astype('float32')
X_train/=255
X_test/=255
n_classes=10
y_train=keras.utils.to_categorical(y_train,n_classes...

Introduction to Computer Vision

Computer Vision can be defined as the subset of AI where we can teach a computer to see. We cannot just add a camera to a machine in order for it to see. For a machine to actually view the world like people or animals do, it relies on Computer Vision and image recognition techniques. Reading barcodes and face recognition are examples of Computer Vision. Computer Vision can be described as that part of the human brain that processes the information that's perceived by the eyes, nothing else.

Image recognition is one of the interesting uses of Computer Vision from an AI standpoint. The input that is received through Computer Vision on the machine is interpreted by the image recognition system, and based on what it sees, the output is classified.

In other words, we use our eyes to capture the objects around us, and those objects/images are processed...

Summary

In this chapter, we built a feedforward neural network to recognize handwritten digits in two versions. Then, we built a neural network to classify handwritten digits, and, finally we gave a short introduction to Computer Vision.

In the next chapter, we will build a Machine Vision mobile app to classify flower species and retrieve the necessary information.

Further reading

For in-depth knowledge on computer vision, do refer the following Packt books:

• Deep Learning for Computer Vision by Rajalingappaa Shanmugamani
• Practical Computer Vision by Abhinav Dadhich