indico Blog

Resources for exploring machine learning and data science

July 28, 2016

Posted by
indico

SAS: The Unreasonable Benefits of Deep Learning

Earlier this month, Dan Kuster gave a talk discussing why businesses should consider adopting deep learning solutions. Key takeaways include simplicity, accuracy, flexibility, and some hacks for working with the tech.

July 13, 2016

Posted by
Dan Kuster

Semi-supervised Feature Transfer: The Practical Benefit of Deep Learning Today?

In this case study, we evaluate four different strategies for solving a problem with machine learning. In terms of both technical performance and practical factors like economics and amount of training data required, customized models built from semi-supervised "deep" features using transfer learning outperform models built from scratch, and rival state-of-the-art methods.

June 6, 2016

Posted by
indico

How Machine Learning is Shaping Digital Marketing

Last week Dan Kuster held a workshop at General Assembly Boston on how machine learning is changing -- and improving -- the way digital marketers do their jobs. Video and slides available for those of you who missed it.

May 16, 2016

Posted by
Luke Metz

ICLR 2016 Takeaways: Adversarial Models & Optimization

At the beginning of the month, three members of our Advanced Development team attended the International Conference on Learning Representations in Puerto Rico. Luke discusses some key takeaways and his favorite papers.

May 9, 2016

Posted by
Dan Kuster

The Good, Bad, & Ugly of TensorFlow

Much has changed since we last evaluated TensorFlow back in November. We've been using the framework in daily research and engineering - here's an update on what's happened since.

May 2, 2016

Posted by
Luke Metz

TensorFlow Data Input (Part 2): Extensions & Hacks

Luke expands on the data input methods he discussed in Part 1 of this mini blog series, namely highlighting a hybrid approach of those methods that allows for faster training, as well as some extensions to the demo.

April 25, 2016

Posted by
Luke Metz

TensorFlow Data Input (Part 1): Placeholders, Protobufs & Queues

TensorFlow is a great new deep learning framework that supports the symbolic construction of functions (similar to Theano) to perform some computation, generally a neural network based model. Luke, one of our machine learning researchers, discusses several methods for feeding data into a machine learning model using this framework.

Get updated when new posts come out

Recent Posts

Building Better Search

In speech and writing, how often do we use one term -- and only that term -- to describe an idea? For example, if you were searching... more

·

Inspiring Hack Projects: Spill.it

A few weeks ago we had the pleasure of supporting HackBeanpot, for the second year in a row, at Genuine HQ. We caught up with the winners... more

·

Creating Personalized Content Filters with CrowdLabel

We are all inundated with information. Even in a Google-powered world, where itโ€™s relatively easy to find any type of content that we may... more

·

Search for keywords