Figure 2: Positions of a sample of node vectors in 2-D space from an actual Poincaré embedding. Note that as we move toward the boundary, we begin to see nodes lower and lower in the hierarchy. Also, nodes similar to each other are close to each other.

Like many of you, I thoroughly enjoyed Ali Rahimi’s NIPS talk in response to winning the test-of time award for their work on random kitchen sinks. I recommend everyone to watch it if you haven’t already.

In software, it’s said that all abstractions are leaky, and this is true for the Jupyter notebook as it is for any other software. I most often see this manifest itself with the following issue:

## What are computers for?

Introduction

When Bayesian optimization meets the Stochastic Gradient Descent algorithm on the AWS marketplace, rich features bloom, models are trained, Time-To-Market shrinks and stakeholders are satisfied.

What is your car’s worth? This tutorial will guide you through the steps for estimating it’s value by using Machine Learning techniques. I will use my Peugeot 106 as an example!

I’m at NIPS 2017. Please catch me or e-mail me if you’d like to chat about research!

Missed a post last week due to the Thanksgiving long weekend :-). We had gone to San Francisco to see the city and try out a couple of hikes). Just FYI – strolling around SF is also as much a hike as any of the real trails at Mt Sutro – with all the uphill & downhill roads! As for Robotics, I am currently on Week 3 of the Mobility course, which is more of physics than ‘computer science’; its a welcome change of pace from all the ML/CS stuff I usually do.

This problem originated from a blog post I wrote for DataCamp on graph optimization here. The algorithm I sketched out there for solving the Chinese Problem on the Sleeping Giant state park trail network has since been formalized into the postman_problems python library. I’ve also added the Rural Postman solver that is implemented here.