The Texas A&M Institute of Data Science (TAMIDS), Texas A&M High Performance Research Computing (HPRC), and Texas Engineering Experiment Station invite you to join our Bring-Your-Own-Data (BYOD) workshop! The primary goal of this workshop is to help Aggie researchers take advantage of the latest data analytics technologies and Texas A&M high performance computing facilities to speed up various data science projects.
This is a FREE service offered to all researchers at Texas A&M.
Please note that this is NOT a training session, but more in forms of a code development working meeting focusing exclusively on your project with a goal to overcome technical hurdles you may have to move forward with your data science projects. Given the limited time and resources available to offer this workshop, you must be prepared with a determined mind to create substantial progress. We can only work on the software applications that you write and plan to maintain yourself or the applications that are built on top of an open source platform.
You are advised to bring your own laptop, but it is not required as long as you provide means to share your data with us at the workshop. Please feel free to contact the organizers if you have any questions or comments.
Location & Registration
The localtion of the workshop is in 235-I WEB (AggieMap) and the registration is open. We are looking forward to seeing you at one of our BYOD workshops!
BYOD Attendees (Feb 2019 – )
|02/05/2019||WEB 235I||Morgan Jenks||Department of Visualization||We worked on a computer vision system (PlantCV) for a greenhouse to track plant growth. The data we were working on were still images of garden beds. We managed to deploy and try out PlantCV with a testing image on a JupyterLab Hub (SimHub: https://simhub.engr.tamu.edu/).|
|02/19/2019||WEB 235I||Steven Riechman||Department of Nutrition and Food Science||We looked into various algorithms and deep learning toolkits that could be used to investigate fatigue vs. readiness balance for athletes. The relevant data science problem is pattern recognition for time series. In addition to the traditional machine learning methods, we will try out a couple deep Learning methods, such as Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM)).|
|Nicos Georghiades||Department of Health and Kinesiology|