[HTML][HTML] Are deep neural networks adequate behavioral models of human visual perception?
FA Wichmann, R Geirhos - Annual Review of Vision Science, 2023 - annualreviews.org
Deep neural networks (DNNs) are machine learning algorithms that have revolutionized
computer vision due to their remarkable successes in tasks like object classification and …
computer vision due to their remarkable successes in tasks like object classification and …
The relational bottleneck as an inductive bias for efficient abstraction
A central challenge for cognitive science is to explain how abstract concepts are acquired
from limited experience. This has often been framed in terms of a dichotomy between …
from limited experience. This has often been framed in terms of a dichotomy between …
Large language models and the reverse turing test
TJ Sejnowski - Neural computation, 2023 - direct.mit.edu
Large language models (LLMs) have been transformative. They are pretrained foundational
models that are self-supervised and can be adapted with fine-tuning to a wide range of …
models that are self-supervised and can be adapted with fine-tuning to a wide range of …
Physics-informed machine learning: A survey on problems, methods and applications
Recent advances of data-driven machine learning have revolutionized fields like computer
vision, reinforcement learning, and many scientific and engineering domains. In many real …
vision, reinforcement learning, and many scientific and engineering domains. In many real …
Mind's eye: Grounded language model reasoning through simulation
Successful and effective communication between humans and AI relies on a shared
experience of the world. By training solely on written text, current language models (LMs) …
experience of the world. By training solely on written text, current language models (LMs) …
Meta-learned models of cognition
Psychologists and neuroscientists extensively rely on computational models for studying
and analyzing the human mind. Traditionally, such computational models have been hand …
and analyzing the human mind. Traditionally, such computational models have been hand …
The enemy of my enemy is my friend: Exploring inverse adversaries for improving adversarial training
J Dong, SM Moosavi-Dezfooli… - Proceedings of the …, 2023 - openaccess.thecvf.com
Although current deep learning techniques have yielded superior performance on various
computer vision tasks, yet they are still vulnerable to adversarial examples. Adversarial …
computer vision tasks, yet they are still vulnerable to adversarial examples. Adversarial …
[HTML][HTML] Commonsense psychology in human infants and machines
Human infants are fascinated by other people. They bring to this fascination a constellation
of rich and flexible expectations about the intentions motivating people's actions. Here we …
of rich and flexible expectations about the intentions motivating people's actions. Here we …
Quantifying the impact of large language models on collective opinion dynamics
The process of opinion expression and exchange is a critical component of democratic
societies. As people interact with large language models (LLMs) in the opinion shaping …
societies. As people interact with large language models (LLMs) in the opinion shaping …
A rubric for human-like agents and NeuroAI
I Momennejad - … Transactions of the Royal Society B, 2023 - royalsocietypublishing.org
Researchers across cognitive, neuro-and computer sciences increasingly reference 'human-
like'artificial intelligence and 'neuroAI'. However, the scope and use of the terms are often …
like'artificial intelligence and 'neuroAI'. However, the scope and use of the terms are often …