Sean Wade


Educational Background


M.S. Computer Science
B.S. Applied and Computational Mathematics 09/2017 - 12/2018

Brighanm Young University

My studies and research lie at the intersection of mathematics, statistics, and computer science. I apply the tools from these fields to solve modern problems in optimization, data science, modeling, and forecasting. My current research is in the Perception, Cognition, and Control Lab at BYU focusing on Bayesian deep learning.

  • 3.8 GPA
  • National Merit Scholar
  • 2015 & 2017 Distinguished Undergraduate in Mathematics
  • MIT Innovator Finalist
  • ACM and BYU Data Science Club Officer

Professional Experience


Computer Vision / Machine Learning Engineer 03/2017 - Current
Loveland Innovations Alpine, UT
  • Used drone imaging to construct 3D models of homes
  • Built algorithms to segment 3D models, detect damage, and identify roof features
  • Applied and scaled machine leaning research to industry
Research Intern 06/2016 - 08/2016
MIT Lincoln Labs Cambridge, MA
  • Researched within Lidar and Active Optical Systems
  • Created a pipeline to process massive multidimensional point clouds
  • Implemented and analyzed many clustering and machine learning techniques
Software Engineer 05/2010 - 08/2011
EyeTech Digital Systems Mesa, AZ
  • Developed mathematical models to highly improve tracking algorithms
  • Optimized embedded computer vision algorithms with over 10x speedup

Research Experience


Healthcare: Researched machine learning techniques for survival analysis, disease prediction, and cost analysis in healthcare. Applied new methods for training gradient boosted trees and recurrent neural networks to large healthcare datasets. Also developed high dimensional disease embeddings based on the field of natural language processing.

Publications
  • Forward Thinking: Building and Training Neural Networks One Layer at a Time
  • Code2Vec: Embedding and Clustering Medical Diagnosis Data

Graph Theory: Explored graph symmetries and automorphisms. This is used to model the redundancies and patterns of large scale networks, allowing for both forecasting and separation of dynamical systems.

Relevant Coursework


  • Convex Optimization
  • Numerical Methods for Optimization (i.e. BFGS, Adam, Conjugate Gradient)
  • Deep Neural Networks
  • Interior Point Methods
  • Digital Signal Processing
  • Differential Equations
  • Statistical Machine Learning
  • Functional Analysis
  • Algorithm Design and Optimization
  • Android Programing
  • Thompson Sampling
  • Computer Science Data Structures
My Picture