Richard E.L. Higgins

I am a Computer Science and Engineering PhD student at the University of Michigan, advised by David Fouhey. I was previously a Master's student here in CSE.

At Michigan, I'm currently working on forecasting and future prediction. I did my bachelors at the University of Maryland, where I studied Neuroscience and Computer Science.

Email  /  Resume  /  Google Scholar  /  Github  /  Devpost  /  Kaggle  /  LinkedIn

I'm interested in computer vision, machine learning, neural networks, and weakly-supervised learning. I want to develop learning systems that scaffold or "couple" components such that they can cyclically improve from each other's improvements.

‣ I trained a UNet to predict magnetic field parameters on the sun using polarized light (IQUV's) recorded from the Solar Dynamics Observatory's HMI sensor.

‣ I constructed topologically associated domains and analyzed RNA-seq data to identify differential gene expression using bioinformatics libraries in R and Python.

‣ I wrote MATLAB functions that classified windows of mouse EEG recordings as seizure/not seizure with max-margin unsupervised learning.

‣ I wrote a Java application that changed underwater images into false-color analogs for different cone opsins, to understand fish conspicuity.
‣ The idea was that these bright fish all have very different color cones and might actually be disguised in the eyes of predators.

‣ By allocating more of fixed resources to value function improvement, we were able to train a reinforcement learning model to converge more quickly than a baseline.
‣ The idea is that policy and value networks might need very different batch sizes/GPU usage for stability in different environments and that this can be learnt.

‣ We evaluated the frequency of vehicle safety messages to identify what adjustments could augment vehicle safety and reduce potential network congestion for self-driving cars.

‣ I made a joke website for the statistically significant but insignificant results of the world.

‣ We finetuned a ResNet to classify objects appearing in road-scene images. Finished in the top 10 for the class.

‣ We trained a DenseNet language model. We explored how residual connectivity can compare favorably to RNNs.

‣ We built a (briefly) state-of-the-art multilabel x-ray disease classifer.

‣ I built a stacked hourglass model with residual connections for nerve segmentation.
‣ I released a keras residual unit for use as a configurable building block on github.

‣ We created a service for deep dreaming your Facebook profile picture with convolutional neural networks.

‣ We created a Unity and Microsoft Kinect game in virtual reality using superpowers triggered by gesture and gaze.

‣ We created a mobile app for sharing photos and videos by location with a map interface. Like Snapmap.

‣ I created a virtual reality browser for exploring the internet as if it were a 3D city with websites as buildings.
‣ The idea here is that similar and inter-linked websites should be located nearby one another.

‣ I made an Android app that matchmakes people and lets two players race from one wikipedia page to another by only clicking links.

‣ I trained a convolutional neural network in Caffe to do plankton image classification.

‣ I made a neural network in PyBrain and later PyTorch for stock forecasting using convolutional neural networks and policy gradients.

‣ We made an Android app for Air Quality, UV, and Pollen Count tracking.

‣ We made a robot which was steered by an Android phone and sent video to a Google Glass.

‣ We made an Android app for sending payment reminders to "friends".

‣ We made an Android location-based messaging app.

‣ We made Android arcade games for Google Glass, controlled through head motions.

‣ We modeled a horse robot in CAD, tested gaits in a simulator, 3D printed it, and surpassed distance requirements in the course.

‣ I led discussions, created assignments with Numpy and Pytorch in Python, graded projects, and hosted office hours for ~150 upper-level CS students.

‣ I incorporated and trained various object detection neural networks as part of a video analysis platform to identify objects in dashcam footage.

‣ I built a style-transfer service on AWS that used to process millions of images/day.
‣ I built a GAN that performs face attribute transformation for a social media company.
‣ I built a CNN backend to provide object recognition in a Fortune 500 company iOS app.
‣ I designed many CNN computer vision systems for Fortune 500 clients across industries.

‣ We built an automated document extraction service on AWS, with custom LSTMs for OCR.

‣ I developed machine learning tools to automatically scale Kubernetes pods based on networks requests, CPU, and memory usage.

‣ I instructed multi-hour discussions on cardiac function, renal system, nervous system, pharmacology, digestion, and more.

‣ I was the primary contact with landlords, handled house finances, and organized housing for the next school year.

‣ I taught children how to sail and not crash into expensive boats.

Find the origin of nice webpages