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

# Review loss function
Take a look at the loss function in math notation again:

$$
\large{
L=\frac{1}{m}\sum_{i=1}^{m}((wx_i+b)-y_i)^2
}
$$

So far, we treated all the values in this function as constants, except for $w$. In particular, we fixed $b$ at a value of 0. If we change $b$ from a constant to a variable, the loss is not a two-dimensional curve anymore.

Let’s suppose our hiker doesn’t live in flatland anymore. They are free to walk around in three dimensions. The two horizontal axes are the values of $w$ and $b$, and the vertical axis is the value of the loss. In other words, each point on this surface represents the error of a line in our linear regression model, and we want to find the line with the lowest error, the point marked with a cross.

Even if the loss is now a surface, we can still reach its minimum point with gradient descent only.

Now we need to calculate the gradient of a function of multiple variables. Fortunately we can do that with a technique called **partial derivatives**.


Learn about partial derivatives along with the math behind the concept and its graphical representations.

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

Partial Derivatives

Review loss function