Neural networks have made a massive comeback in the last five years. We went from having a simple multi-layer network in 1975-1995 to Now there are dozens of different architectures, languages, patterns, and problem spaces. Trying to decide where to start learning can feel incredibly daunting. I would like to help with that. I'm going to share with you my experiences from the field about what all the different architecture are from basic to latest and greatest. We'll also see what the different types of problems we can try to solve for (using cows) and how you can get started using them today in your projects.