Gain insights into image data processing and CNNs for image classification using TensorFlow. Delve into CNN architectures and their applications, requiring Python and TensorFlow knowledge.

irml.tar.gz

image-rec

If you want to dive into the technology behind computer vision and self driving cars, this is where to start.

In this course you'll learn how to process data from image files and create convolutional neural networks (CNNs) to classify different types of images. After completing this course, you will have a solid understanding of why CNNs work and which CNN architectures to use for different tasks.

The code for this course is built around the TensorFlow framework, one of the premier frameworks for industry machine learning, and the Python pandas library for data analysis. Knowledge of Python and TensorFlow are prerequisites. 

This course was created by AdaptiLab, a company specializing in evaluating, sourcing, and upskilling enterprise machine learning talent. It is built in collaboration with industry machine learning experts from Google, Microsoft, Amazon, and Apple.

Image Recognition with Machine Learning

<h2 class="section-title">Chapter Goals:</h2>
<ul>
	<li>Understand why we use dropout in neural networks</li>
	<li>Apply dropout to a fully-connected layer</li>
</ul>


<h2>A. Co-adaptation</h2>

<p>Co-adaptation refers to when multiple neurons in a layer extract the same, or very similar, hidden features from the input data. This can happen when the connection weights for two different neurons are nearly identical.</p>


<p>When a fully-connected layer has a large number of neurons, co-adaptation is more likely to occur. This can be a problem for two reasons. First, it is a waste of computation when we have redundant neurons computing the same output. Second, if many neurons are extracting the same features, it adds more significance to those features for our model. This leads to overfitting if the duplicate extracted features are specific to only the training set.</p>

<h2>B. Dropout</h2>

The way we minimize co-adaptation for fully-connected layers with many neurons is by applying <i>dropout</i> during training. In dropout, we randomly shut down some fraction of a layer's neurons at each training step by zeroing out the neuron values. The fraction of neurons to be zero'd out is known as the dropout rate, $r_d$. The remaining neurons have their values multiplied by $\frac{1}{1 - r_d}$ so that the overall sum of the neuron values remains the same.


<h2>Chapter Goals:</h2>
<ul>
	<li>Understand why we use dropout in neural networks</li>
	<li>Apply dropout to a fully-connected layer</li>
</ul>


Learn about dropout and how it can reduce overfitting in large neural networks.

What you'll learn from this course

Image Processing

CNN

SqueezeNet

ResNet

Dropout

Chapter Goals:

A. Co-adaptation