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

The model tracks even the statistical noise in the training data.


The model is using too many hidden layers.

What is the main cause of overfitting in deep neural networks?


What is the main cause of overfitting in deep neural networks?

good at classifying both training and test data

good at training data and not good at test data

(Fill in the blank.) While overfitting is good at classifying the training data and less efficient at classifying the test data, the underfitting is ________.


(Fill in the blank.) While overfitting is good at classifying the training data and less efficient at classifying the test data, the underfitting is ________.

What does it mean to have a **_high variance for a supervised learning system_**?


What does it mean to have a high variance for a supervised learning system?

By keeping the weights in the system small.

By modifying the output of activation function.

How do we achieve **L1** and **L2** regularization? 

How do we achieve L1 and L2 regularization?

**(Select all that apply.)** How can we overcome overfitting through regularization?
 


(Select all that apply.) How can we overcome overfitting through regularization?

Let’s evaluate your learning by this short quiz on defeating overfitting.

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

Defeating Overfitting

Taming Deep Networks

Beyond Vanilla Networks

Into the Deep

Quiz: Defeat Overfitting