My education was focused on the earth sciences (geophysics, carbonate geology) and computer science (data analytics); and previous work experience was geared toward data science and plug-in development for the energy industry. Technical skills: Python (10 years) and R (4 years), with 2 years' experience building data science products using Hadoop and its associated dongles (especially Spark). When I'm not sitting in front of glowing rectangular screens at work, I absolutely adore hiking / kayaking / mountain-biking around Texas' glorious Green Belt; resuscitating Apples; and (poorly!) attempting to play bass guitar. Personal passions are sustainable energy and climate change research; STEM education reform; and empowering local governments via data science https://twitter.com/DynamicWebPaige
My education was focused on the earth sciences (geophysics, carbonate geology) and computer science (data analytics); and previous work experience was geared toward data science and plug-in development for the energy industry. Technical skills: Python (10 years) and R (4 years), with 2 years' experience building data science products using Hadoop and its associated dongles (especially Spark). When I'm not sitting in front of glowing rectangular screens at work, I absolutely adore hiking / kayaking / mountain-biking around Texas' glorious Green Belt; resuscitating Apples; and (poorly!) attempting to play bass guitar. Personal passions are sustainable energy and climate change research; STEM education reform; and empowering local governments via data science https://twitter.com/DynamicWebPaige
My education was focused on the earth sciences (geophysics, carbonate geology) and computer science (data analytics); and previous work experience was geared toward data science and plug-in development for the energy industry. Technical skills: Python (10 years) and R (4 years), with 2 years' experience building data science products using Hadoop and its associated dongles (especially Spark). When I'm not sitting in front of glowing rectangular screens at work, I absolutely adore hiking / kayaking / mountain-biking around Texas' glorious Green Belt; resuscitating Apples; and (poorly!) attempting to play bass guitar. Personal passions are sustainable energy and climate change research; STEM education reform; and empowering local governments via data science.
In this talk, we'll use image recognition to take an existing deep learning model and adapt it to a specialized domain (namely: guessing whether articles of clothing are preppy, sporty, punk, etc.). Instead of using a more intensive data classifier, like a Residual Network, we'll use deep transfer learning to overcome a data scarcity problem and build on top of an existing model.
Once the transfer learning model has been trained, we'll pack it up into a dockerized container (specifying inputs and outputs, as well as a score.py file), and then call it as a web service. We will also discuss a #DataOps process for refreshing the model as trends change over time.