[HTML][HTML] Reinforcement learning, fast and slow
Deep reinforcement learning (RL) methods have driven impressive advances in artificial
intelligence in recent years, exceeding human performance in domains ranging from Atari to …
intelligence in recent years, exceeding human performance in domains ranging from Atari to …
Next-generation deep learning based on simulators and synthetic data
Deep learning (DL) is being successfully applied across multiple domains, yet these models
learn in a most artificial way: they require large quantities of labeled data to grasp even …
learn in a most artificial way: they require large quantities of labeled data to grasp even …
The debate over understanding in AI's large language models
M Mitchell, DC Krakauer - Proceedings of the National …, 2023 - National Acad Sciences
We survey a current, heated debate in the artificial intelligence (AI) research community on
whether large pretrained language models can be said to understand language—and the …
whether large pretrained language models can be said to understand language—and the …
Large language models fail on trivial alterations to theory-of-mind tasks
T Ullman - arXiv preprint arXiv:2302.08399, 2023 - arxiv.org
Intuitive psychology is a pillar of common-sense reasoning. The replication of this reasoning
in machine intelligence is an important stepping-stone on the way to human-like artificial …
in machine intelligence is an important stepping-stone on the way to human-like artificial …
Deep hierarchical semantic segmentation
Humans are able to recognize structured relations in observation, allowing us to decompose
complex scenes into simpler parts and abstract the visual world in multiple levels. However …
complex scenes into simpler parts and abstract the visual world in multiple levels. However …
Savi++: Towards end-to-end object-centric learning from real-world videos
G Elsayed, A Mahendran… - Advances in …, 2022 - proceedings.neurips.cc
The visual world can be parsimoniously characterized in terms of distinct entities with sparse
interactions. Discovering this compositional structure in dynamic visual scenes has proven …
interactions. Discovering this compositional structure in dynamic visual scenes has proven …
[HTML][HTML] Intuitive physics learning in a deep-learning model inspired by developmental psychology
Abstract 'Intuitive physics' enables our pragmatic engagement with the physical world and
forms a key component of 'common sense'aspects of thought. Current artificial intelligence …
forms a key component of 'common sense'aspects of thought. Current artificial intelligence …
Conditional object-centric learning from video
Object-centric representations are a promising path toward more systematic generalization
by providing flexible abstractions upon which compositional world models can be built …
by providing flexible abstractions upon which compositional world models can be built …
Object scene representation transformer
MSM Sajjadi, D Duckworth… - Advances in neural …, 2022 - proceedings.neurips.cc
A compositional understanding of the world in terms of objects and their geometry in 3D
space is considered a cornerstone of human cognition. Facilitating the learning of such a …
space is considered a cornerstone of human cognition. Facilitating the learning of such a …
On the binding problem in artificial neural networks
Contemporary neural networks still fall short of human-level generalization, which extends
far beyond our direct experiences. In this paper, we argue that the underlying cause for this …
far beyond our direct experiences. In this paper, we argue that the underlying cause for this …