Learn machine learning algorithms for image recognition, which is used in various applications in computer vision and self-driving cars.

Neural Networks: Beginners to Advanced

If you want to dive into the technology behind computer vision and self-driving cars, this is where to start. In this module, you'll learn how to process data from image files and create convolutional neural networks (CNNs) to classify different types of images. 

The code for this module 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. 

After completing this module, you will have a solid understanding of why CNNs work and which CNN architectures to use for different tasks.

Neural Networks for Image Recognition

<h2 class="section-title">Chapter Goals:</h2>
<ul>
	<li>Obtain the logits for each digit class</li>
</ul>


<h2>A. Multiclass logits</h2>

<div id="section1_l8" class="collapse show">
<p>Since there are 10 possible digits an MNIST image can be, we use a 10 neuron fully-connected layer to obtain the logits for each digit class. The logits are the output of the <code>model_layers</code> function.</p>
<p>The rest of the model follows the standard format for multiclass classification:
	<ul>
		<li>Softmax applied to the logits to convert them into per class probabilities</li>
		<li>The <code>labels</code> are one-hot vectors, where the "hot index" corresponds to the digit in the MNIST image</li>
		<li>Softmax cross entropy to calculate loss</li>
	</ul>
</p>
</div>


<h2>Chapter Goals:</h2>
<ul>
	<li>Obtain the logits for each digit class</li>
</ul>


<h2>A. Multiclass logits</h2>

<div id="section1_l8">
<p>Since there are 10 possible digits an MNIST image can be, we use a 10 neuron fully-connected layer to obtain the logits for each digit class. The logits are the output of the <code>model_layers</code> function.</p>
<p>The rest of the model follows the standard format for multiclass classification:
	<ul>
		<li>Softmax applied to the logits to convert them into per class probabilities</li>
		<li>The <code>labels</code> are one-hot vectors, where the "hot index" corresponds to the digit in the MNIST image</li>
		<li>Softmax cross entropy to calculate loss</li>
	</ul>
</p>
</div>


Use a fully-connected layer to extract multiclass logits from the CNN.

Image Processing

CNN

SqueezeNet

ResNet

Conclusion

Logits

Chapter Goals:

A. Multiclass logits