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

What problem does batch normalization solve?

<p>What problem does batch normalization solve?</p>


When the weights of a model all tend towards negative infinity

Model accuracy decreasing upon adding a large enough number of layers

Both vanishing and exploding gradients occurring

Training a model in increments across many different training runs

Adding small constants to each layer's weights to improve training

Dropping layers from the model when their weights tend to 0

The process of learning the residual function, to make identity mapping easier

Their weights converge faster than regular blocks

The bottleneck block reduces the number of parameters for extremely large ResNet models

They increase training accuracy for models with many layers

Why do we use bottleneck blocks for certain ResNet configurations?

<p>Why do we use bottleneck blocks for certain ResNet configurations?</p>


Image Processing

CNN

SqueezeNet

ResNet

Conclusion

Quiz