Research/
Research
·
May 31, 2022

Preserving Knowledge in Simulated Behavioral Action Loops

The importance of investigating what types of architectures are well suited for preserving knowledge lies in constructing artificial learning systems that can not only provide utility in our daily lives, but also give insight into our understanding of human learning and intelligence.

Rachel St. Clair
Rachel St. Clair
Co-Founder, CEO
Abstract

One basic goal of artificial learning systems is the ability to continually learn throughout that system’s lifetime. Transitioning between tasks and re-deploying prior knowledge is thus a desired feature of artificial learning. However, in the deep-learning approaches, the problem of catastrophic forgetting of prior knowledge persists. As a field, we want to solve the catastrophic forgetting problem without requiring exponential computations or time, while demonstrating real-world relevance. This work proposes a novel model which uses an evolutionary algorithm similar to a meta-learning objective, that is fitted with a resource constraint metrics. Four reinforcement learning environments are considered with the shared concept of depth although the collection of environments is multi-modal. This system shows preservation of some knowledge in sequential task learning and protection of catastrophic forgetting in deep neural networks.

@phdthesis{stclair2022preserving, title = {Preserving Knowledge in Simulated Behavioral Action Loops}, author = {St. Clair, Rachel}, school = {Florida Atlantic University}, year = {2022} }