The monochromatic black-and-green that defined night vision for decades is quickly receding into the past. The U.S. military already issues night-vision goggles that outline people and other objects in bright white, and researchers across the world are racing to develop even more advanced ways of seeing in the dark. A new proof-of-principle study offers intriguing hints about how the next generation of such technology might work. In a paper published Wednesday in the academic journal PLOS ONE, researchers demonstrate that a deep learning algorithm can build a full-color reconstruction of a scene using only infrared images the human eye can't see. These findings suggest an exciting new future for night-vision technology.

In particular, the more potential inputs you have to an algorithm, the more out of control your scaling problem gets when analyzing its problem space. This is where MACH, a research project authored by Rice University's Tharun Medini and Anshumali Shrivastava, comes in. MACH is an acronym for Merged Average Classifiers via Hashing, and according to lead researcher Shrivastava, "[its] training times are about 7-10 times faster, and... memory footprints are 2-4 times smaller" than those of previous large-scale deep learning techniques. In describing the scale of extreme classification problems, Medini refers to online shopping search queries, noting that "there are easily more than 100 million products online." This is, if anything, conservative--one data company claimed Amazon US alone sold 606 million separate products, with the entire company offering more than three billion products worldwide.

Thanks to the strength of the open source community, the second part is getting easier every day. There are many great tutorials on the specifics of how to train and use Deep Learning models using libraries such as TensorFlow -- many of which publications like Towards Data Science publish on a weekly basis. The implication of this is that once you have an idea for how you'd like to use Deep Learning, implementing your idea, while not easy, involves standard "dev" work: following tutorials like the ones linked throughout this article, modifying them for your specific purpose and/or data, troubleshooting via reading posts on StackOverflow, and so on. They don't, for example, require being (or hiring) a unicorn with Ph.D who can code original neural net architectures from scratch and is an experienced software engineer. This series of essays will attempt to fill a gap on the first part: covering, at a high level, what Deep Learning is capable of, while giving resources for those of you who want to learn more and/or dive into the code and tackle the second part.

Today's artificial intelligence (AI) technologies are usually run using machine learning algorithms. These operate on what's called a neural network -- systems designed to mimic the human brain inner workings -- as part of what is called deep learning. Currently, most AI advances are largely due to deep learning, with developments like AlphaGo, the Go-playing AI created by Google's DeepMind. Now, IBM has announced that they have developed an AI that makes the entire machine learning process faster. Instead of running complex deep learning models on just a single server, the team, led by IBM Research's director of systems acceleration and memory Hillery Hunter, managed to efficiently scale up distributed deep learning (DDL) using multiple servers.