DeepAI AI Chat
Log In Sign Up

Latent Properties of Lifelong Learning Systems

by   Corban Rivera, et al.
Johns Hopkins University Applied Physics Laboratory

Creating artificial intelligence (AI) systems capable of demonstrating lifelong learning is a fundamental challenge, and many approaches and metrics have been proposed to analyze algorithmic properties. However, for existing lifelong learning metrics, algorithmic contributions are confounded by task and scenario structure. To mitigate this issue, we introduce an algorithm-agnostic explainable surrogate-modeling approach to estimate latent properties of lifelong learning algorithms. We validate the approach for estimating these properties via experiments on synthetic data. To validate the structure of the surrogate model, we analyze real performance data from a collection of popular lifelong learning approaches and baselines adapted for lifelong classification and lifelong reinforcement learning.


page 1

page 2

page 3

page 4


A Review of Explainable Artificial Intelligence in Manufacturing

The implementation of Artificial Intelligence (AI) systems in the manufa...

Towards Explainable Artificial Intelligence in Banking and Financial Services

Artificial intelligence (AI) enables machines to learn from human experi...

Projective simulation for classical learning agents: a comprehensive investigation

We study the model of projective simulation (PS), a novel approach to ar...

Dynamic Algorithmic Service Agreements Perspective

A multi-disciplinary understanding of the concepts of identity, agency, ...

Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning

Latent structure models are a powerful tool for modeling language data: ...

Lifelong Learning Metrics

The DARPA Lifelong Learning Machines (L2M) program seeks to yield advanc...