The neuroconnectionist research programme
A Doerig, RP Sommers, K Seeliger… - Nature Reviews …, 2023 - nature.com
Artificial neural networks (ANNs) inspired by biology are beginning to be widely used to
model behavioural and neural data, an approach we call 'neuroconnectionism'. ANNs have …
model behavioural and neural data, an approach we call 'neuroconnectionism'. ANNs have …
Getting aligned on representational alignment
Biological and artificial information processing systems form representations that they can
use to categorize, reason, plan, navigate, and make decisions. How can we measure the …
use to categorize, reason, plan, navigate, and make decisions. How can we measure the …
[HTML][HTML] Butterfly effects in perceptual development: A review of the 'adaptive initial degradation'hypothesis
Human perceptual development evolves in a stereotyped fashion, with initially limited
perceptual capabilities maturing over the months or years following the commencement of …
perceptual capabilities maturing over the months or years following the commencement of …
Language models as models of language
R Millière - arXiv preprint arXiv:2408.07144, 2024 - arxiv.org
This chapter critically examines the potential contributions of modern language models to
theoretical linguistics. Despite their focus on engineering goals, these models' ability to …
theoretical linguistics. Despite their focus on engineering goals, these models' ability to …
Visual cognition in multimodal large language models
A chief goal of artificial intelligence is to build machines that think like people. Yet it has
been argued that deep neural network architectures fail to accomplish this. Researchers …
been argued that deep neural network architectures fail to accomplish this. Researchers …
How aligned are different alignment metrics?
In recent years, various methods and benchmarks have been proposed to empirically
evaluate the alignment of artificial neural networks to human neural and behavioral data. But …
evaluate the alignment of artificial neural networks to human neural and behavioral data. But …
Covariance properties under natural image transformations for the generalised Gaussian derivative model for visual receptive fields
T Lindeberg - Frontiers in Computational Neuroscience, 2023 - frontiersin.org
The property of covariance, also referred to as equivariance, means that an image operator
is well-behaved under image transformations, in the sense that the result of applying the …
is well-behaved under image transformations, in the sense that the result of applying the …
Errorradar: Benchmarking complex mathematical reasoning of multimodal large language models via error detection
As the field of Multimodal Large Language Models (MLLMs) continues to evolve, their
potential to revolutionize artificial intelligence is particularly promising, especially in …
potential to revolutionize artificial intelligence is particularly promising, especially in …
Deep social neuroscience: The promise and peril of using artificial neural networks to study the social brain
B Sievers, MA Thornton - Social Cognitive and Affective …, 2024 - academic.oup.com
This review offers an accessible primer to social neuroscientists interested in neural
networks. It begins by providing an overview of key concepts in deep learning. It then …
networks. It begins by providing an overview of key concepts in deep learning. It then …
Have we built machines that think like people?
A chief goal of artificial intelligence is to build machines that think like people. Yet it has
been argued that deep neural network architectures fail to accomplish this. Researchers …
been argued that deep neural network architectures fail to accomplish this. Researchers …