Development of Few-Shot Learning Capabilities in Artificial Neural Networks When Learning Through Self-Supervised Interaction

Most artificial neural networks used for object recognition are trained in a fully supervised setup. This is not only resource consuming as it requires large data sets of labeled examples but also quite different from how humans learn. We use a setup in which an artificial agent first learns in a si...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2024-01, Vol.46 (1), p.209-219
Main Authors: Clay, Viviane, Pipa, Gordon, Kuhnberger, Kai-Uwe, Konig, Peter
Format: Article
Language:English
Subjects:
Agents (artificial intelligence)
Artificial neural networks
Concept mapping
Embodied AI
enactivism
Encoding
fast mapping
few-shot learning
Learning
Neural networks
Object recognition
Pattern analysis
Poles and towers
reinforcement learning
representation learning
Representations
Semantics
Task analysis
Training
Visualization
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most artificial neural networks used for object recognition are trained in a fully supervised setup. This is not only resource consuming as it requires large data sets of labeled examples but also quite different from how humans learn. We use a setup in which an artificial agent first learns in a simulated world through self-supervised, curiosity-driven exploration. Following this initial learning phase, the learned representations can be used to quickly associate semantic concepts such as different types of doors using one or more labeled examples. To do this, we use a method we call fast concept mapping which uses correlated firing patterns of neurons to define and detect semantic concepts. This association works instantaneously with very few labeled examples, similar to what we observe in humans in a phenomenon called fast mapping . Strikingly, we can already identify objects with as little as one labeled example which highlights the quality of the encoding learned self-supervised through interaction with the world. It therefore presents a feasible strategy for learning concepts without much supervision and shows that through pure interaction meaningful representations of an environment can be learned that work better for few-short learning than non-interactive methods.
ISSN:0162-8828
2160-9292
1939-3539
DOI:10.1109/TPAMI.2023.3323040