Machine Learning in VR

Inspiration

ML is difficult for beginners to visualize because of complex mathematical concepts that are utilized in creating models. To ease that pain, our project helps students visualize datasets and how ML models work on them in VR.

What it does

• For now, our VR project generates a data set and uses Linear Regression to find a best fit line. These data points and the best fit line are visible in 3D.

How we built it

• The VR world is built using A-Frame and Three.js.
• Our app works on backend that is on Flask and Python.
• We used the scikit learn python library to perform Linear Regression on datasets generated by a python script.

Challenges we ran into

• Learning A-Frame.
• Combining python scripts with JavaScript and ultimately A-Frame to visualize everything.
• Choosing frameworks to build our app on. (Node.js or Flask?) ## Accomplishments that we're proud of Learning A-Frame and building something on VR.

What's next for Machine Learning in VR

• Add animations, add new machine learning models such as k-means clustering, support vector machines, Bayesian networks etc. And hopefully, neural networks.

• Deploy the app on Heroku or AWS

Built With

• a-frame
• flask
• github
• html
• javascript
• python
• three.js