This course covers the basics of deep learning. Starting from the simple artificial neuron (perceptron), artificial neural networks and their most common architectures, such as fully connected and convolutional models, are introduced. The process by which these networks learn to accomplish specific tasks from data is then explained, along with backpropagation, loss function optimization, and the standard pipeline to train, validate, and test models. Basic concepts of unsupervised deep learning are also introduced.