The course will help you understand machine learning fundamentals by diving into theoretical concepts and algorithms of machine learning.

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

Fully connected NN is used only for one-dimensional data while CNN is used solely for higher dimensional data.

Weights are arranged in a filter that slides over the input, calculating the output piece by piece. 

Instead of using nonlinear activation functions, it uses linear activation functions

What is the core difference between the fully connected neural network and the CNN?

What is the core difference between the fully connected neural network and the CNN?

**(Fill in the blank.)** The output dimensions of an image of size 256×256 pixels, passing through a convolutional filter of dimensions 5×5 will be ________.


(Fill in the blank.) The output dimensions of an image of size 256×256 pixels, passing through a convolutional filter of dimensions 5×5 will be ________.

**(Fill in the blank.)** A 5×5 convolutional filter with 4 filters in 3 layers, applied to a $32×32$ image will have an output in the form of ________.


(Fill in the blank.) A 5×5 convolutional filter with 4 filters in 3 layers, applied to a <math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mn>32</mn><mo>×</mo><mn>32</mn></mrow><annotation encoding="application/x-tex">32×32</annotation></semantics></math>32×32 image will have an output in the form of ________.

It adds an empty frame around the input image to keep the dimensions of the output the same as the input.

It adds additional layers in the CNN to increase the accuracy of the network.

What is the purpose of padding in the convolution?

What is the purpose of padding in the convolution?

What will be the shape of the data at the output layer after executing the following code on input data of dimension $3 \times 2$?

```python
model = Sequential()
model.add(Dense(16, input_shape=(3, 2))) 
model.add(Activation('relu')) 
model.add(Flatten()) 
model.add(Dense(4))
```

What will be the shape of the data at the output layer after executing the following code on input data of dimension <math><semantics><mrow><mn>3</mn><mo>×</mo><mn>2</mn></mrow><annotation encoding="application/x-tex">3 \times 2</annotation></semantics></math>3×2?
<pre><code class="language-python">model = Sequential()
model.add(Dense(16, input_shape=(3, 2))) 
model.add(Activation('relu')) 
model.add(Flatten()) 
model.add(Dense(4))
</code></pre>

Evaluate yourself by attempting the quiz on deep networks.

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 on Deep Networks