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

## Unreasonable effectiveness of deep networks
Throughout this course, we might have been surprised by the capabilities of simple programs like our first **MNIST classifier**. And yet, little prepares us for the uncanny capabilities of modern deep networks. In the words of one famous researcher, those networks are “_unreasonably effective._” In a sense, they do nothing more than recognize patterns yet, they increasingly beat us at quintessentially human tasks, like _facial recognition_ or _medical diagnosis_.

> **Note:** The short answer is that we don’t understand why deep neural networks work so well on so many tasks. Indeed,  a lot of ongoing research is bent to explain that fact.

At first sight, it’s not even obvious why deeper networks work better than more shallow ones. A famous theorem from 1989, called the **universal approximation theorem**, proves that _with enough hidden nodes, even a humble three-layered network can approximate any function with any possible dataset_. If shallow networks are good enough for any dataset, at least in theory, then why are deeper networks so much more accurate?

That question has been traditionally hard to answer because neural networks are mostly **opaque**. _Because it’s hard to understand why a network makes a certain decision_. We might be able to explain a small network by understanding its internals, but as the numbers of nodes and layers grow, it quickly becomes impossible to wrap our minds around all those numbers. Indeed, researchers spend a lot of time inventing techniques to explain the decision-making of neural networks in human terms.

## Levels of abstractions in Deep CNN
A scientific paper from 2016 made a leap forward in explaining how deep networks see the world ([“Towards Better Analysis of Deep Convolutional Neural Networks,”](https://arxiv.org/pdf/1604.07043.pdf) by _Mengchen Liu, Jiaxin Shi, Zhen Li, Chongxuan Li, Jun Zhu, and Hixia Liu_). Using novel techniques, the authors visualized the “**_thinking_**” of a deep CNN and showed that its layers work like **_levels of abstractions_**. 

The first layers identify basic geometric features as an image moves through the network, like vertical or horizontal lines. Deeper layers identify more complex geometries, like circles. And even deeper layers catch higher-level details, like a human face, the fins of a Cadillac, or the beak of a platypus. In other words, _each layer in a network outputs higher-level features for the next layer to work on_, as illustrated below:


# Unreasonable effectiveness of deep networks
Throughout this course, we might have been surprised by the capabilities of simple programs like our first **MNIST classifier**. And yet, little prepares us for the uncanny capabilities of modern deep networks. In the words of one famous researcher, those networks are “_unreasonably effective._” In a sense, they do nothing more than recognize patterns yet, they increasingly beat us at quintessentially human tasks, like _facial recognition_ or _medical diagnosis_.

> **Note:** The short answer is that we don’t understand why deep neural networks work so well on so many tasks. Indeed,  a lot of ongoing research is bent to explain that fact.

At first sight, it’s not even obvious why deeper networks work better than more shallow ones. A famous theorem from 1989, called the **universal approximation theorem**, proves that _with enough hidden nodes, even a humble three-layered network can approximate any function with any possible dataset_. If shallow networks are good enough for any dataset, at least in theory, then why are deeper networks so much more accurate?

That question has been traditionally hard to answer because neural networks are mostly **opaque**. _Because it’s hard to understand why a network makes a certain decision_. We might be able to explain a small network by understanding its internals, but as the numbers of nodes and layers grow, it quickly becomes impossible to wrap our minds around all those numbers. Indeed, researchers spend a lot of time inventing techniques to explain the decision-making of neural networks in human terms.

# Levels of abstractions in Deep CNN
A scientific paper from 2016 made a leap forward in explaining how deep networks see the world ([“Towards Better Analysis of Deep Convolutional Neural Networks,”](https://arxiv.org/pdf/1604.07043.pdf) by _Mengchen Liu, Jiaxin Shi, Zhen Li, Chongxuan Li, Jun Zhu, and Hixia Liu_). Using novel techniques, the authors visualized the “**_thinking_**” of a deep CNN and showed that its layers work like **_levels of abstractions_**. 

The first layers identify basic geometric features as an image moves through the network, like vertical or horizontal lines. Deeper layers identify more complex geometries, like circles. And even deeper layers catch higher-level details, like a human face, the fins of a Cadillac, or the beak of a platypus. In other words, _each layer in a network outputs higher-level features for the next layer to work on_, as illustrated below:


Explore how deep learning is too effective.

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

Unreasonable Effectiveness

Unreasonable effectiveness of deep networks