By Joyce Xu – 11 min read.
Before I started my most recent job at ThinkTopic, the concepts of "functional programming" and "machine learning" belonged to two different worlds entirely. One was a programming paradigm surging in popularity as the world turned towards simplicity, composability, and immutability to maintain complex scaling applications; the other was a tool to teach computers to autocomplete doodles and make music. Where was the overlap?
Face2face – A Pix2Pix demo that mimics the facial expression of the German chancellor
By Dat Tran – 7 min read.
Inspired by one of Gene Kogan‘s workshop, I created my own face2face demo that translates my webcam image into the German chancellor when giving her New Year’s speech in 2017. It’s not perfect yet as the model has still a problem, for example, with learning the position of the German flag.
keras: Deep Learning in R
By Karlijn Willems – 22 min read.
As you know by now, machine learning is a subfield in Computer Science (CS). Deep learning, then, is a subfield of machine learning that is a set of algorithms that is inspired by the structure and function of the brain and which is usually called Artificial Neural Networks (ANN).
I have data. I need insights. Where do I start?
By Rama Ramakrishnan – 5 min read.
This question comes up often. It is typically asked by starting data scientists, analysts and managers new to data science. Their bosses are under pressure to show some ROI from all the money that has been spent on systems to collect, store and organize the data (not to mention the money being spent on data scientists).
"Bayesian Additive Regression Trees" paper summary
By Zak Jost – 4 min read.
This paper develops a Bayesian approach to an ensemble of trees. It is extremely readable for an academic paper and I recommend taking the time to read it if you find the subject interesting.
Reducing Dimensionality from Dimensionality Reduction Techniques
By Elior Cohen – 13 min read.
In this post I will do my best to demystify three dimensionality reduction techniques; PCA, t-SNE and Auto Encoders. My main motivation for doing so is that mostly these methods are treated as black boxes and therefore sometime are misused.
