Neural network automated verification of a VAE and SegNet using NNV. Although neural networks are promising, they are easily confused, particularly if the input domain is perturbed. In this project, I demonstrate the robustness of MNIST-trained VAE and SegNet against varying brightness attacks.

Visualizing the resulting link prediction graph from a temporal graph network on a Wikipedia dataset using Observable and d3.js.

For most of my life, I’ve been writing poetry when I experience a lightbulb moment. Over time, this habit shapeshifted to mainly haiku & senryū, often composing sequences of 23 - 31 or more on a day out. Although they’re usually reluctant to share, the more people that I’ve met, the more I’ve discovered that also have this practice in one way or another. People are like onions; they have layers. If you peel back enough, you’ll reach the heart – haiku & senryū are the key to mine.

Implementation of face detection / following and vSLAM on a Ryze Tello using its MATLAB toolkit.

I found it on YouTube and, as my friend reminded me the other night, this algorithm is not new. The fast inverse square root shook the nerd world with its implementation in Quake III (1999).

My introduction to quadcopters and robotics in which I learned a lot about the quad ecosystem and their constitution. However, I suggest following a smaller, cheaper, and more recent build guide. Although my naivete showed through here, my fascination with quads has not soured; check out my Tello face following and vSLAM project!

I fell in love with dimensionality reduction when I was learning statistical ML. Since I also study neuroscience, I wanted to practice the art at the intersection of my interests. I compared the 3D projections of a 53-dimensional neurophysiology dataset produced by PCA and a shallow autoencoder.