Convolutional neural networks (CNN)Convolutional neural networks (CNN) are extensively used in image classification and object recognition applications. Therefore, we consider them in this chapter. We introduce mathematical definition of the convolutionConvolution operation and its implementation by a single neuron first. Afterward, we introduce the convolutionConvolution definition under Keras. Then, we explore how to form a complete CNNConvolutional neural networks (CNN) model under Keras. Here, we focus on feature extractionFeature extraction and classification blocks forming the CNNConvolutional neural networks (CNN) model. Afterward, we consider training and testing steps of the formed model. We then explore transfer learningTransfer learning to benefit from existing CNNConvolutional neural networks (CNN) models to be modified for our own problem. We next consider implementation steps for embedding the trained and tested CNN model on the nRF microcontroller. Finally, we provide examples on the usage of CNN models to solve real-life problems.