While playing with some applications of binary neurons, I found myself wanting to use explicit activations that go beyond a simple yes/no decision. For example, we might want our neural network to make a choice between several categories (in the form of a one-hot vector) or we might want it to make a choice between ordered categories (e.g., a scale of 1 to 10). It’s rather easy to extend the straight-through estimator to work well on both of these cases, and I thought I would share my work in this post. I share code for implementing ternary and one-hot neurons in Tensorflow, and show that they can learn to solve MNIST.

There are two clear trends in the big-data ecosystem: the growth of machine learning use cases that leverage large distributed data sets, and the growth of Spark’s Machine Learning libraries (often referred to as MLlib) for these use cases. In fact, Spark’s MLlib library is arguably the leading solution for machine learning on large distributed data sets.

(c) 2017 by Thomas Wiecki

I recently finished a course on discrete optimization and am currently working through Richard McElreath’s excellent textbook Statistical Rethinking. Combining the two, and duly jazzed by this video on the Traveling Salesman Problem, I’d thought I’d build a toy Bayesian model and try to optimize it via simulated annealing.

We posted several blog posts about sparklyr (introduction, automation), which enables you to analyze big data leveraging Apache Spark seamlessly with R. sparklyr, developed by RStudio, is an R interface to Spark that allows users to use Spark as the backend for dplyr, which is the popular data manipulation package for R.

Deploying to AWS¶

· Read in 9 minutes · 1720 words · All posts in series  ·

This was just a very simple learning project I did as part of The Data Incubator program.