Abstraction and Analogy-Making in Artificial Intelligence

02/22/2021
by   Melanie Mitchell, et al.
0

Conceptual abstraction and analogy-making are key abilities underlying humans' abilities to learn, reason, and robustly adapt their knowledge to new domains. Despite of a long history of research on constructing AI systems with these abilities, no current AI system is anywhere close to a capability of forming humanlike abstractions or analogies. This paper reviews the advantages and limitations of several approaches toward this goal, including symbolic methods, deep learning, and probabilistic program induction. The paper concludes with several proposals for designing challenge tasks and evaluation measures in order to make quantifiable and generalizable progress in this area.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 18

03/31/2021

Imagine All the People: Citizen Science, Artificial Intelligence, and Computational Research

Machine learning, artificial intelligence, and deep learning have advanc...
07/13/2017

Human-Level Intelligence or Animal-Like Abilities?

The vision systems of the eagle and the snake outperform everything that...
08/29/2014

AI Evaluation: past, present and future

Artificial intelligence develops techniques and systems whose performanc...
10/27/2021

How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI

Many real-world problems require the combined application of multiple re...
03/06/2013

Probabilistic Conceptual Network: A Belief Representation Scheme for Utility-Based Categorization

Probabilistic conceptual network is a knowledge representation scheme de...
11/01/2018

Towards learning-to-learn

In good old-fashioned artificial intelligence (GOFAI), humans specified ...
12/21/2018

Lifelong Testing of Smart Autonomous Systems by Shepherding a Swarm of Watchdog Artificial Intelligence Agents

Artificial Intelligence (AI) technologies could be broadly categorised i...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.