Discussing Innovation within Financial Services in a Time of Pandemic

How will we see innovation within financial services and other critical industries evolve during the pandemic? Introduction The world economy has slowed in response to the recent novel coronavirus pandemic. Tourism, food and beverage, and travel businesses have shuttered their physical and virtual doors, for the most part. Some critical industries soldier on either with…

Researchers and AI Practitioners Team Up to Mine Public COVID-19 Information

How machine learning and data science facilitate COVID-19 research Information has the potential to impact policy decisions, research directions, and personal decisions alike. Information-overload challenges informed and timely decision-making by increasing the chance of error and confounds decision-making. The key is to ensure relevant, actionable, and precise information is available concisely in near real-time. To…

Implementing Feedback for Programming by Demonstration

Karan K. Budhraja and Tim Oates Abstract. Agent-based modeling is a paradigm of modeling dynamic systems of interacting agents that are individually governed by specified behavioral rules. Training a model of such agents to produce an emergent behavior by specification of the emergent (as opposed to agent) behavior is easier from a demonstration perspective. Without…

Ecosembles: A Rapidly Deployable Image Classification System Using Feature-Views

Adrian Rosebrock, Tim Oates, Jesus Caban Abstract. Constructing an image classification system using strong, local invariant descriptors is time-consuming and tedious, requiring many experimentations and parameter tunings to obtain an adequately performing model. Furthermore, training a system in a given domain and then migrating the model to a different domain will likely yield poor performance. As…

AI Thought Leadership

Our New AI Thought Leadership Program

We wanted to share some exciting news about our new AI thought leadership program. Since our founding in 2017, we have partnered with over 40 clients to deliver AI, data science, and data engineering services. Given the rapidity of change in this space, it’s important visionaries and thought leaders share ideas and stories about the…

Using Machine Vision for Detecting Wildfires

Using Machine Vision for Detecting Wildfires About 4.5 million U.S. homes are considered at high or extreme risk of wildfire. While wildfires mainly destroy unpopulated land and remain relatively “manageable” (with fewer than two percent classified as “significant”), wildfires that reach populated areas wreak havoc on those who live there. Furthermore, factors such as weather…

Graph Node Embeddings using Domain-Aware Biased Random Walks

Sourav Mukherjee, PhD; Tim Oates, PhD; Ryan Wright Abstract. The recent proliferation of publicly available graph-structured data has sparked an interest in machine learning algorithms for graph data. Since most traditional machine learning algorithms assume data to be tabular, embedding algorithms for mapping graph data to real-valued vector spaces has become an active research area.…