Alignment with human representations supports robust few-shot learning

01/27/2023
by   Ilia Sucholutsky, et al.
12

Should we care whether AI systems have representations of the world that are similar to those of humans? We provide an information-theoretic analysis that suggests that there should be a U-shaped relationship between the degree of representational alignment with humans and performance on few-shot learning tasks. We confirm this prediction empirically, finding such a relationship in an analysis of the performance of 491 computer vision models. We also show that highly-aligned models are more robust to both adversarial attacks and domain shifts. Our results suggest that human-alignment is often a sufficient, but not necessary, condition for models to make effective use of limited data, be robust, and generalize well.

READ FULL TEXT

page 2

page 3

research
11/29/2021

Exploring Alignment of Representations with Human Perception

We argue that a valuable perspective on when a model learns good represe...
research
04/17/2022

Learning Compositional Representations for Effective Low-Shot Generalization

We propose Recognition as Part Composition (RPC), an image encoding appr...
research
11/02/2022

Human alignment of neural network representations

Today's computer vision models achieve human or near-human level perform...
research
05/31/2023

Analyzing Text Representations by Measuring Task Alignment

Textual representations based on pre-trained language models are key, es...
research
02/02/2022

Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks

Recent work suggests that representations learned by adversarially robus...
research
03/25/2021

Learning Dynamic Alignment via Meta-filter for Few-shot Learning

Few-shot learning (FSL), which aims to recognise new classes by adapting...
research
12/19/2019

Quantifying the effect of representations on task complexity

We examine the influence of input data representations on learning compl...

Please sign up or login with your details

Forgot password? Click here to reset