In this presentation, we will introduce the essential aspects of training convolutional neural networks (CNNs). We’ll discuss the prerequisites for training, including models, data and training frameworks, with an emphasis on the characteristics of data needed for effective training. We will explore the model training process using visuals to explain the error surface and gradient-based learning techniques. Our discussion will cover key hyperparameters, loss functions and how to monitor the health of the training process. We will also address the common training problems of overfitting and underfitting, and offer practical rules of thumb for mitigating these issues. Finally, we will introduce popular training frameworks and provide resources for further learning.