Deep Learning For Folks Without (or With!) a Ph.D.


How does a computer identify pictures of cats? Or drive a car? These are jobs for deep learning. Deep learning is a specialization of machine learning for perceptual tasks. If this sounds hard, it’s because it is! The Python community has contributed two libraries TensorFlow and Keras to help.

Talk Description

This session is a survey of deep learning fundamentals with an introduction to more advanced topics. A majority of the first half is spent on building a conceptual neural network, which is what makes deep learning work. No code is shown, just the facts. After that, the TensorFlow library will be discussed with a practical code example, but not at length. The focus of the session, and the entire second half, is Keras. This is a higher-level library that avoids the complexity of TensorFlow thus making the power of deep learning accessible. And there is no performance tradeoff either as Keras is built on top of TensorFlow. This will segue into more advanced topics including convolutional neural networks, recurrent neural networks and a brief introduction to GANs and reinforcement learning.

About the Talk

About the Author

Douglas Starnes is a polyglot ninja and tech community influencer in the Memphis area making stuff that works on more than just the web. He specializes in the fields of mobile, cloud, data science and machine learning. Douglas is a co-director of the Memphis Python User Group and a board member of the Memphis .NET User Group. He is a frequent conference speaker who has delivered more than 20 featured presentations at more than 10 conferences over the past 4 years in a variety of citiies across the southeast United States. In addition, Douglas is an active participant in local user groups. He has also served as an organizer for PyTennessee, PyOhio and TechCampMemphis. Outside of being a geek Douglas is a trained composer, aspiring triathlete and avid Lego collector.