Dissociating language and thought in large language models

K Mahowald, AA Ivanova, IA Blank, N Kanwisher… - Trends in Cognitive …, 2024 - cell.com
Large language models (LLMs) have come closest among all models to date to mastering
human language, yet opinions about their linguistic and cognitive capabilities remain split …

[HTML][HTML] Catalyzing next-generation artificial intelligence through neuroai

A Zador, S Escola, B Richards, B Ölveczky… - Nature …, 2023 - nature.com
Neuroscience has long been an essential driver of progress in artificial intelligence (AI). We
propose that to accelerate progress in AI, we must invest in fundamental research in …

What can transformers learn in-context? a case study of simple function classes

S Garg, D Tsipras, PS Liang… - Advances in Neural …, 2022 - proceedings.neurips.cc
In-context learning is the ability of a model to condition on a prompt sequence consisting of
in-context examples (input-output pairs corresponding to some task) along with a new query …

[HTML][HTML] Human-in-the-loop machine learning: a state of the art

E Mosqueira-Rey, E Hernández-Pereira… - Artificial Intelligence …, 2023 - Springer
Researchers are defining new types of interactions between humans and machine learning
algorithms generically called human-in-the-loop machine learning. Depending on who is in …

Curricular contrastive regularization for physics-aware single image dehazing

Y Zheng, J Zhan, S He, J Dong… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Considering the ill-posed nature, contrastive regularization has been developed for single
image dehazing, introducing the information from negative images as a lower bound …

A survey on curriculum learning

X Wang, Y Chen, W Zhu - IEEE transactions on pattern analysis …, 2021 - ieeexplore.ieee.org
Curriculum learning (CL) is a training strategy that trains a machine learning model from
easier data to harder data, which imitates the meaningful learning order in human curricula …

How variability shapes learning and generalization

L Raviv, G Lupyan, SC Green - Trends in cognitive sciences, 2022 - cell.com
Learning is using past experiences to inform new behaviors and actions. Because all
experiences are unique, learning always requires some generalization. An effective way of …

Meta-learning in neural networks: A survey

T Hospedales, A Antoniou, P Micaelli… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …

Curriculum learning: A survey

P Soviany, RT Ionescu, P Rota, N Sebe - International Journal of …, 2022 - Springer
Training machine learning models in a meaningful order, from the easy samples to the hard
ones, using curriculum learning can provide performance improvements over the standard …

End-to-end speech recognition: A survey

R Prabhavalkar, T Hori, TN Sainath… - … on Audio, Speech …, 2023 - ieeexplore.ieee.org
In the last decade of automatic speech recognition (ASR) research, the introduction of deep
learning has brought considerable reductions in word error rate of more than 50% relative …