Deep Learning (Adaptive Computation and Machine Learning series) by Ian Goodfellow, Yoshua Bengio, Aaron Courville
Came out in November 2016. Split in 3 parts:
Part I: Applied Math and Machine Learning Basics (Linear Algebra, Probability and Information Theory, Numerical computation)
Part II: Deep Networks: Modern Practices (Deep Feedforward Networks, Regularization, CNNs, RNNs, Practical Methodology & Applications)
Part III: Deep Learning Research (Linear Factor Models, Autoencoders, Representation Learning, Structured Probabilistic Models, Monte Carlo Methods, Inference, Partition Function, Deep Generative Models)
What's interesting is how to cast Bill Murray for a movie. He doesn't have an agent, lawyer, personal phone number, or email address. Only a mythical anonymous 1-800 number where you leave a voicemail describing your script and hope he calls back. He's known to check his voicemail only once in a while..
He's also a nomad, so if he's interested, the script is sent through snail mail to his variable current location.
I've used it mostly for prototyping and gifts. I've made a photography turntable, a functional arduino robot, and 3D printed my dad's house to put in a shadow box frame as a gift.
Famo.us founder was a Powerset co-founder, which had an highly successful exit to Microsoft. This pattern often explains generous funding of outlandish ideas.