Rapid Development of Compositional AI

02/12/2023
by   Lee Martie, et al.
0

Compositional AI systems, which combine multiple artificial intelligence components together with other application components to solve a larger problem, have no known pattern of development and are often approached in a bespoke and ad hoc style. This makes development slower and harder to reuse for future applications. To support the full rapid development cycle of compositional AI applications, we have developed a novel framework called (Bee)* (written as a regular expression and pronounced as "beestar"). We illustrate how (Bee)* supports building integrated, scalable, and interactive compositional AI applications with a simplified developer experience.

READ FULL TEXT

page 2

page 5

research
03/01/2022

Compositional Inverses of AGW-PPs

In this paper, we present two methods to obtain the compositional invers...
research
02/02/2023

A Survey on Compositional Generalization in Applications

The field of compositional generalization is currently experiencing a re...
research
07/07/2023

Compositionality in Model-Based Testing

Model-based testing (MBT) promises a scalable solution to testing large ...
research
11/22/2019

Moral Dilemmas for Artificial Intelligence: a position paper on an application of Compositional Quantum Cognition

Traditionally, the way one evaluates the performance of an Artificial In...
research
07/15/2020

Lifelong Learning of Compositional Structures

A hallmark of human intelligence is the ability to construct self-contai...
research
09/13/2023

Cryptography: Against AI and QAI Odds

Artificial Intelligence (AI) presents prodigious technological prospects...
research
09/05/2022

On the Horizon: Interactive and Compositional Deepfakes

Over a five-year period, computing methods for generating high-fidelity,...

Please sign up or login with your details

Forgot password? Click here to reset