This is a course introducing modern techniques of machine learning, especially deep neural networks, to an audience of physicists. Neural networks can be trained to perform diverse challenging tasks, including image recognition and natural language processing, just by training them on many examples. Neural networks have recently achieved spectacular successes, with their performance often surpassing humans. They are now also being considered more and more for applications in physics, ranging from predictions of material properties to analyzing phase transitions. We will cover the basics of neural networks, convolutional networks, autoencoders, restricted Boltzmann machines, and recurrent neural networks, as well as the recently emerging applications in physics. Prerequisites: almost none, except for matrix multiplication and the chain rule. This is a course introducing modern techniques of machine learning, especially deep neural networks, to an audience of physicists. Neural networks can be trained to perform diverse challenging tasks, including image recognition and natural language processing, just by training them on many examples. Neural networks have recently achieved spectacular successes, with their performance often surpassing humans. They are now also being considered more and more for applications in physics, ranging from predictions of material properties to analyzing phase transitions. We will cover the basics of neural networks, convolutional networks, autoencoders, restricted Boltzmann machines, and recurrent neural networks, as well as the recently emerging applications in physics. Prerequisites: almost none, except for matrix multiplication and the chain rule.