We just accomplished our second computer vision project in this R and deep learning journey! Through this chapter, we got more familiar with convolutional neural networks and their implementation in MXNet, and another powerful deep learning tool: Keras with TensorFlow.

We started with what self-driving cars are and how deep learning techniques are making self-driving cars feasible and more reliable. We also discussed how deep learning stands out and becomes the state-of-the-art solution for object recognition in intelligent vehicles. After exploring the traffic sign dataset, we developed our first CNN model using MXNet and achieved more than 99% accuracy. Then we moved on to another powerful deep learning framework, Keras + TensorFlow, and obtained comparable results.

We introduced the dropout technique to reduce overfitting. We also learned how to deal with lack of training data and utilize data augmentation techniques, including flipping, shifting, and rotation. We finally wrapped up the chapter by summarizing some approaches to prevent overfitting in CNN models. That was the second example where we observed how deep learning removes manual or explicit feature extraction steps taken in traditional approaches, and instead efficiently finds the best sets of features.

We have practiced CNNs in these two computer vision projects. In the next project, we will be working with totally different types of deep neural networks—autoencoders.