DeepAI AI Chat
Log In Sign Up

Differentiable User Models

by   Alex Hämäläinen, et al.

Probabilistic user modeling is essential for building collaborative AI systems within probabilistic frameworks. However, modern advanced user models, often designed as cognitive behavior simulators, are computationally prohibitive for interactive use in cooperative AI assistants. In this extended abstract, we address this problem by introducing widely-applicable differentiable surrogates for bypassing this computational bottleneck; the surrogates enable using modern behavioral models with online computational cost which is independent of their original computational cost. We show experimentally that modeling capabilities comparable to likelihood-free inference methods are achievable, with over eight orders of magnitude reduction in computational time. Finally, we demonstrate how AI-assistants can computationally feasibly use cognitive models in a previously studied menu-search task.


page 1

page 2

page 3

page 4


Using a Cognitive Architecture to consider antiblackness in design and development of AI systems

How might we use cognitive modeling to consider the ways in which antibl...

Differentiable Bayesian Neural Network Inference for Data Streams

While deep neural networks (NNs) do not provide the confidence of its pr...

Controlling Synthetic Characters in Simulations: A Case for Cognitive Architectures and Sigma

Simulations, along with other similar applications like virtual worlds a...

Bayesian Optimization for Likelihood-Free Inference of Simulator-Based Statistical Models

Our paper deals with inferring simulator-based statistical models given ...

Reputation blackboard systems

Blackboard systems are motivated by the popular view of task forces as b...

Reflective Linguistic Programming (RLP): A Stepping Stone in Socially-Aware AGI (SocialAGI)

This paper presents Reflective Linguistic Programming (RLP), a unique ap...