Exploiting Text Embeddings for Industry Contexts

Posted by & filed under Data Science, Machine Learning.

From Synonyms to Object Properties It’s well known that word embeddings are excellent for finding similarities between words — specifically, synonyms. We achieve this using supervised machine learning techniques by showing a neural net a dataset of hundreds of millions of pieces of text. The algorithm looks at the context and frequency in which particular… Read more

Data Science Deployments with Docker

Posted by & filed under Data Science, Developers, Machine Learning Tutorials, Tutorials.

Deploying machine learning models has always been a struggle. Most of the software industry has adopted the use of container engines like Docker for deploying code to production, but since accessing hardware resources like GPUs from Docker was difficult and required hacky, driver specific workarounds, the machine learning community has shied away from this option.… Read more

The indico Machine Learning Team’s Take on TensorFlow

Posted by & filed under Data Science, Machine Learning, Opinion Piece.

Earlier this week, Google released TensorFlow, an open source library for numerical computation. Given the general frothiness around machine learning, we thought folks might appreciate a simple, straightshootin’ take from indico’s Machine Learning team. Unlike a random person on the Internet, we deal with this stuff daily, and can hopefully shed some light on how… Read more

Three Thought-Provoking Ideas from SIGGRAPH ’15

Posted by & filed under Data Science, Developers, indico, Machine Learning, Opinion Piece.

Last month Alec Radford and I had the great pleasure of attending the SIGGRAPH 2015 conference in Los Angeles.  If you don’t know about SIGGRAPH, here’s a quick snippet from their website:  “Since its beginning in 1974 as a small group of specialists in a previously unknown discipline, ACM SIGGRAPH has evolved to become an international… Read more

Neural Image Captioning for Mortals

Posted by & filed under Data Science, Developers, Machine Learning, Machine Learning Tutorials.

Introduction to Neural Image Captioning Image Captioning is a damn hard problem — one of those frontier-AI problems that defy what we think computers can really do. This summer, I had an opportunity to work on this problem for the Advanced Development team during my internship at indico. The work I did was fascinating but not revolutionary … Read more

Visualizing with t-SNE

Posted by & filed under Data Science, Developers, Machine Learning.

Data visualization A big part of working with data is getting intuition on what those data show. Staring at raw data points, especially when there are many of them, is almost never the correct way to tackle a problem. Low dimensional data are easy to visually inspect. You can simply pick pairs of dimensions and… Read more