In this video:
Romeo chats with Adam Gibson, CTO of Skymind, about how he created Deeplearning4J. Romeo gets Adam talking about how Skymind implemented parallel neural network training in ApacheSpark and other advanced deep learning capabilities like automated differentiation of arbitrary neural network models. Finally, he explains how custom made neural network layer types can be implemented using those framework capabilities.
Adam has co-authored a book on deep learning (along with Josh Patterson): Deep Learning: A Practitioner’s Approach.
Resources for you
- Explore Deeplearning4j, the open source, distributed, deep learning library for the JVM
- Romeo provides Deeplearning4j examples on GitHub
- Use this article as an introduction to deep learning and long-short term memory networks
- Learn about Watson machine learning
- Explore Watson machine learning on Bluemix
- Here’s a Python notebook that shows you how to use deep learning to build a classification model