AI Icon ARTIFICIAL INTELLIGENCE

ARTIFICIAL INTELLIGENCE

Our approach to AI is unique. We combine our in-house foundational AI and machine learning research with our deep insights from working with teams in the real world to produce AI solutions that actually work the way you expect them to. Our trustable, understandable, and competency-aware AI systems help human-machine teams achieve results that outperform either one working on their own.

Explainable AI

Scientists at Charles River Analytics are generating new knowledge at the frontiers of this rapidly growing area, making human-AI collaboration possible in applications ranging from disaster response to self-driving cars to medical diagnosis.

LEARN MORE >

Explainable AI

Scientists at Charles River Analytics are generating new knowledge at the frontiers of this rapidly growing area, making human-AI collaboration possible in applications ranging from disaster response to self-driving cars to medical diagnosis.

LEARN MORE >

PRINCESS

In our PRINCESS effort, part of DARPA’s BRASS program, we developed methods that would allow the UUV’s software to adapt to change, both within the UUV itself and in its external ecosystem. We experimented with different techniques in machine learning and probabilistic programming to enable UUV software to adapt to internal change, such as upgraded sensors or computer hardware.

LEARN MORE >

Image from Princess Project from Charles River Analytics

PRINCESS

In our PRINCESS effort, part of DARPA’s BRASS program, we developed methods that would allow the UUV’s software to adapt to change, both within the UUV itself and in its external ecosystem. We experimented with different techniques in machine learning and probabilistic programming to enable UUV software to adapt to internal change, such as upgraded sensors or computer hardware.

LEARN MORE >

CAMEL

In CAMEL, we use causal modeling to identify which factors most influence the output of complex, AI-driven systems. Then, our intuitive UI adds text and visual explanations to the model so users can understand why it produced the output, and whether it is appropriate or not to trust that output.

LEARN MORE >

Image from CAMEL Project from Charles River Analytics

CAMEL

In CAMEL, we use causal modeling to identify which factors most influence the output of complex, AI-driven systems. Then, our intuitive UI adds text and visual explanations to the model so users can understand why it produced the output, and whether it is appropriate or not to trust that output.

LEARN MORE >

APPRIL

As part of the PPAML program, Charles River created a powerful new machine learning system using probabilistic programming in the Automated Probabilistic Programming Representation and Inference Languages (APPRIL) program.

LEARN MORE >

Image from APPRIL Project from Charles River Analytics

APPRIL

As part of the PPAML program, Charles River created a powerful new machine learning system using probabilistic programming in the Automated Probabilistic Programming Representation and Inference Languages (APPRIL) program.

LEARN MORE >

ALPACA

ALPACA strengthens trust in machine learning systems by clearly communicating how an AI system’s competence is affected by different, complex environments. When human operators fully understand AI tools, they can become trusted, collaborative members of a human-machine team.

LEARN MORE >

Image from ALPACA Project from Charles River Analytics

ALPACA

ALPACA strengthens trust in machine learning systems by clearly communicating how an AI system’s competence is affected by different, complex environments. When human operators fully understand AI tools, they can become trusted, collaborative members of a human-machine team.

LEARN MORE >

DATAVOID

DATAVOID provides value of information (VoI) analysis to support decision makers so they can assess and understand the relationships between the data they already have, decisions that they need to make, and the costs and benefits of acquiring additional information to make better decisions.

LEARN MORE >

Simulated image from DATAVOID Project from Charles River Analytics

DATAVOID

CyMod™, a cyber modeling and reactive agent framework that provides a tool for integrating intelligent cyber adversaries into simulation environments. CyMod enables cyber defenders to quickly and easily perform cyber wargaming to predict likely attack vectors and prepare proactive defenses against these attacks.

LEARN MORE >

PRIME

This effort resulted in probabilistic models of enterprise-deployed machine learning systems (such as insider threat detection systems). Analysts can use these models to evaluate, forecast, and understand the performance of a machine learning system within the enterprise.

LEARN MORE >

Simulated image from PRIME Project from Charles River Analytics

PRIME

The effort resulted in probabilistic models of enterprise-deployed machine learning systems (such as insider threat detection systems). Analysts can use these models to evaluate, forecast, and understand the performance of a machine learning system within the enterprise.

LEARN MORE >

Our passion for science and engineering drives us to find impactful, actionable solutions.