About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Abhiram Iyer
- sl:arxiv_num : 2201.00042
- sl:arxiv_published : 2021-12-31T19:52:42Z
- sl:arxiv_summary : A key challenge for AI is to build embodied systems that operate in
dynamically changing environments. Such systems must adapt to changing task
contexts and learn continuously. Although standard deep learning systems
achieve state of the art results on static benchmarks, they often struggle in
dynamic scenarios. In these settings, error signals from multiple contexts can
interfere with one another, ultimately leading to a phenomenon known as
catastrophic forgetting. In this article we investigate biologically inspired
architectures as solutions to these problems. Specifically, we show that the
biophysical properties of dendrites and local inhibitory systems enable
networks to dynamically restrict and route information in a context-specific
manner. Our key contributions are as follows. First, we propose a novel
artificial neural network architecture that incorporates active dendrites and
sparse representations into the standard deep learning framework. Next, we
study the performance of this architecture on two separate benchmarks requiring
task-based adaptation: Meta-World, a multi-task reinforcement learning
environment where a robotic agent must learn to solve a variety of manipulation
tasks simultaneously; and a continual learning benchmark in which the model's
prediction task changes throughout training. Analysis on both benchmarks
demonstrates the emergence of overlapping but distinct and sparse subnetworks,
allowing the system to fluidly learn multiple tasks with minimal forgetting.
Our neural implementation marks the first time a single architecture has
achieved competitive results on both multi-task and continual learning
settings. Our research sheds light on how biological properties of neurons can
inform deep learning systems to address dynamic scenarios that are typically
impossible for traditional ANNs to solve.@en
- sl:arxiv_title : Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments@en
- sl:arxiv_updated : 2022-04-25T15:36:13Z
- sl:bookmarkOf : https://arxiv.org/abs/2201.00042
- sl:creationDate : 2022-06-26
- sl:creationTime : 2022-06-26T01:23:08Z
Documents with similar tags (experimental)