A general approach to progressive learning

04/27/2020
by   Joshua T. Vogelstein, et al.
6

In biological learning, data is used to improve performance on the task at hand, while simultaneously improving performance on both previously encountered tasks and as yet unconsidered future tasks. In contrast, classical machine learning starts from a blank slate, or tabula rasa, using data only for the single task at hand. While typical transfer learning algorithms can improve performance on future tasks, their performance degrades upon learning new tasks. Many recent approaches have attempted to mitigate this issue, called catastrophic forgetting, to maintain performance given new tasks. But striving to avoid forgetting sets the goal unnecessarily low: the goal of progressive learning, whether biological or artificial, is to improve performance on all tasks (including past and future) with any new data. We propose a general approach to progressive learning that ensembles representations, rather than learners. We show that ensembling representations—including representations learned by decision forests or neural networks—enables both forward and backward transfer on a variety of simulated and real data tasks, including vision, language, and adversarial tasks. This work suggests that further improvements in progressive learning may follow from a deeper understanding of how biological learning achieves such high degrees of efficiency.

READ FULL TEXT

page 4

page 5

page 6

page 8

page 9

page 13

page 16

research
04/27/2020

A general approach to progressive intelligence

In biological learning, data is used to improve performance on the task ...
research
08/14/2022

A Theory for Knowledge Transfer in Continual Learning

Continual learning of a stream of tasks is an active area in deep neural...
research
01/17/2023

Artificial Neuronal Ensembles with Learned Context Dependent Gating

Biological neural networks are capable of recruiting different sets of n...
research
03/07/2020

Synaptic Metaplasticity in Binarized Neural Networks

While deep neural networks have surpassed human performance in multiple ...
research
02/22/2019

Generative Memory for Lifelong Reinforcement Learning

Our research is focused on understanding and applying biological memory ...
research
07/14/2020

Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics

A central challenge in developing versatile machine learning systems is ...
research
09/01/2022

Progressive Fusion for Multimodal Integration

Integration of multimodal information from various sources has been show...

Please sign up or login with your details

Forgot password? Click here to reset