Four keys to machine learning on the edge

Machine learning is hard but moving your ML model to your embedded device can be even harder. Here, we'll discuss a few pain points in this process, and some up-front Addressing these issues early in the design process is key to getting your new gadget out the door. Most likely you will develop and train your machine-learning models using one of the big four (Google, Amazon, Microsoft, IBM) service stacks, one of the many MLaaS platforms (C3, BigML, WandB, Databricks, Algorithmia, OpenML, Paperspace, PredictionIO, DeepAI, DataRobot, etc.), or you'll roll your own using some variant of Anaconda/Jupyter and ML frameworks such as Keras, TensorFlow, PyTorch, Caffe, MXNet, Theano, CNTK, Chainer, or Scikit-Learn. How do you get from this set of tools, code and data using many different formats, sources, licenses and execution environments into something that you can execute entirely inside some little box--one that may (or may not) be connected to the internet ever again? The initial code for your model will be written in Python, R, MATLAB, Lua, Java, Scala, C, or C .