Online Learning of Objects through Curiosity-Driven Active Learning

03/13/2021
by   Ali Ayub, et al.
0

Children learn continually by asking questions about the concepts they are most curious about. With robots becoming an integral part of our society, they must also learn unknown concepts continually by asking humans questions. This paper presents a novel framework for curiosity-driven online learning of objects. The paper utilizes a recent state-of-the-art approach for continual learning and adapts it for online learning of objects. The paper further develops a self-supervised technique to find most of the uncertain objects in an environment by utilizing an internal representation of previously learned classes. We test our approach on a benchmark dataset for continual learning on robots. Our results show that our curiosity-driven online learning approach beats random sampling and softmax-based uncertainty sampling in terms of classification accuracy and the total number of classes learned.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/25/2021

Self-Supervised Training Enhances Online Continual Learning

In continual learning, a system must incrementally learn from a non-stat...
research
10/09/2022

Few-Shot Continual Active Learning by a Robot

In this paper, we consider a challenging but realistic continual learnin...
research
07/08/2019

Fine-Grained Continual Learning

Robotic vision is a field where continual learning can play a significan...
research
08/22/2020

What am I allowed to do here?: Online Learning of Context-Specific Norms by Pepper

Social norms support coordination and cooperation in society. With socia...
research
05/05/2023

On the Effectiveness of Equivariant Regularization for Robust Online Continual Learning

Humans can learn incrementally, whereas neural networks forget previousl...
research
08/28/2023

Online Continual Learning on Hierarchical Label Expansion

Continual learning (CL) enables models to adapt to new tasks and environ...
research
01/14/2021

Continual Learning of Knowledge Graph Embeddings

In recent years, there has been a resurgence in methods that use distrib...

Please sign up or login with your details

Forgot password? Click here to reset