Unsupervised and Semi-Supervised Machine Learning

In machine learning lingo, “labeled” data means we have the data and we also know the output that is associated with the data. For example, you’re trying to predict house prices based on features like the square footage and neighborhood of a house. You have labeled data in this case if you also have the price…

Analyzing Large Graph Datasets with Graph Embeddings

Large graph datasets on a chalkboard Relationships are everything – family, friends, mentors, colleagues, business contacts.  That’s true in life in general, but also in a great many applications of data science.  The connections between people, businesses, banks, and accounts can tell you if the flow of money is normal or a case of identity…

Stopping Cyberattacks With AI: Featured on Engineering Out Loud

Lately, Synaptiq has been collaborating with Galois on preventing cyberattacks using the combined brainpower of artificial intelligence and cybersecurity experts. It’s an exciting project, and the Engineering Out Loud podcast at OSU recorded an episode all about it. Give it a listen at their website, or directly from the embed below. You can also download it…

Cloud Provisioning Using Deep Reinforcement Learning

Our Chief Data Scientist Tim Oates recently co-published a research paper alongside Zhiguang Wang, Chul Gwon, and Adam Lezzi. Their work points to some compelling evidence that deep reinforcement learning can cut down on the costs of cloud computing. At eight pages, it’s not a dense read, and the results are strong and convincing. You…

Can Machines Decide What’s Worthwhile?

Is it Worthwhile? As a graduate student I periodically attended talks in the mathematics department. It would always be the same. A professor in the department would introduce the speaker. The speaker would read from a sheaf of papers and occasionally write or draw on the chalkboard. After an hour the speaker would finish and…