Machine Learning for Virginia

Launched at University of Virginia in Charlottesville, VA
Founded in 2018

810

Participants

12

Categories

9

Sessions

272

Projects
Why ML4VA?

The main objective of Machine Learning for Virginia (ML4VA) is to prepare students to apply what they learn in machine learning courses to a real-world scenario, especially one that exists from the UVA local community to the state of Virginia at large. Through this 12-week project, students will be working in a team of three to use machine learning to make a meaningful contribution to the well-being of the state of Virginia and its residents. The project topic can be on various issues in education, economy, environment, healthcare, transportation, energy, finance, public safety, and culture.

 

The project will provide students with a unique opportunity for exploring one or more areas of machine learning that we covered in the course. Students should choose a data set, apply machine learning techniques to it and compare their performance with a well-known solution. As the final deliverables, each team will submit a video and a conference-styled paper describing their project. Three teams will be selected as winners for each session.

 
6316class.jpg

Featured Projects

 
 
download%20(1)_edited.jpg

ML Courses

CS 2501, 4774, CS 6316, SYS 6016
SEAS, SDS
UVA

These courses on machine learning with fundamental concepts for computational data analysis, including pattern recognition, prediction, and visualization. Topics include applied math, machine learning basics, deep neural networks, convolutional networks, sequence modeling, generative learning, and deep reinforcement learning. The course will focus on using open-source libraries such as NumPy, Keras, and TensorFlow. Students are required to have sufficient computational background to complete several substantive programming assignments.

Upon successful completion, you will be able to:

  1. Create an end-to-end machine learning project at scale using open-source libraries such as NumPy, Keras, TensorFlow, and Google Cloud.

  2. Formulate various supervised, unsupervised, and reinforcement, learning models.

  3. Apply practical skill sets on designing, deploying, and analyzing deep network architectures on complex real-world problems.

  4. Articulate concepts, algorithms, and tools to build intelligent systems.

  5. Analyze advanced approaches currently pursued by the machine learning community.

 

Instructional Team

Proud to have such a dedicated and hard working team