Explore machine learning's essentials for software engineers, delve into supervised learning, neural networks, and deep learning, and gain skills to tackle real-world data challenges effectively.

pml_final.tar.gz

just_run

chapter06

SPA_07

SPA_gdb_frontEnd

J12-1

J12-2

SPA-server_image

Handson-10

Machine learning is the future for the next generation of software professionals.

This course serves as a guide to machine learning for software engineers. You’ll be introduced to three of the most relevant components of the AI/ML discipline; supervised learning, neural networks, and deep learning. You’ll grasp the differences between traditional programming and machine learning by hands-on development in supervised learning before building out complex distributed applications with neural networks. You’ll go even further by layering networks to create deep learning systems. You’ll work with complex real-world datasets to explore machine behavior from scratch at each phase.

By the end of this course, you’ll have a working knowledge of modern machine learning techniques. Using software engineering, you’ll be prepared to build complex neural networks and wrangle real-world data challenges.

Fundamentals of Machine Learning for Software Engineers

Before we move on, let’s play with the code for a little while. That’s optional, but it’s a good way to revise these concepts.

Go through all the codes which we have covered in this chapter by launching the below app:


# Hands-on
Now that we have learned a few tricks, we can experiment with deep neural networks on our own.

To set up this challenge, we wrote a neural network and trained it on the MNIST dataset. We already saw plenty of MNIST classifiers, but this time, it’s a deep neural network written in Keras. It’s in `network_mnist.py`.

This network does not use any of the techniques from this chapter, but it still does okay. After training it for 10 epochs, the results are:


>loss: 0.2026 - acc: 0.9388 - val_loss: 0.2487 - val_acc: 0.9228

Now it’s your turn.  Your challenege is to improve this network’s accuracy while respecting two constraints:
* Do not change the network’s layout. Keep the same number of layers and nodes per layer.
* Do not change the number of epochs or the batch size. Keep them at 10 and 32, respectively.

You are free to experiment in all other aspects. You can use the tricks that we described in this chapter, or even explore new ones, such as _activation functions, optimization algorithms_, or whatever else you learn by browsing Keras’s documentation.


Test the deep neural network created using Keras on MNIST for better validation accuracy.

How Machine Learning Works

Our First Learning Program

Walking the Gradient

Hyperspace

A Discern Machine

Get Real

The Final Challenge

The Perceptron

Designing the Network

Building the Network

Training the Network

How Classifiers Work

Batchin’ Up

The Zen of Testing

Let’s Do Development

A Deeper Kind of Network

Diabetes Prediction Using Keras

Defeating Overfitting

Taming Deep Networks

Beyond Vanilla Networks

Into the Deep

Recognize Handwritten Digits Using a Deep Neural Network

Playground (The 10 Epochs Challenge)

Hands-on