Capturing the objects of vision with neural networks
B Peters, N Kriegeskorte - Nature human behaviour, 2021 - nature.com
Human visual perception carves a scene at its physical joints, decomposing the world into
objects, which are selectively attended, tracked and predicted as we engage our …
objects, which are selectively attended, tracked and predicted as we engage our …
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 …
Hierarchical associative memory
D Krotov - arXiv preprint arXiv:2107.06446, 2021 - arxiv.org
Dense Associative Memories or Modern Hopfield Networks have many appealing properties
of associative memory. They can do pattern completion, store a large number of memories …
of associative memory. They can do pattern completion, store a large number of memories …
Improving anytime prediction with parallel cascaded networks and a temporal-difference loss
M Iuzzolino, MC Mozer… - Advances in Neural …, 2021 - proceedings.neurips.cc
Although deep feedforward neural networks share some characteristics with the primate
visual system, a key distinction is their dynamics. Deep nets typically operate in serial stages …
visual system, a key distinction is their dynamics. Deep nets typically operate in serial stages …
Ensemble of diluted attractor networks with optimized topology for fingerprint retrieval
The present study analyzes the retrieval capacity of an Ensemble of diluted Attractor Neural
Networks for real patterns (ie, non-random ones), as it is the case of human fingerprints. We …
Networks for real patterns (ie, non-random ones), as it is the case of human fingerprints. We …
Towards Discrete Object Representations in Vision Transformers with Tensor Products
In this work, we explore the use of Tensor Product Representations (TPRs) in a Vision
Transformer model to form image representations that can later be used for symbolic …
Transformer model to form image representations that can later be used for symbolic …
Compositional visual reasoning and generalization with neural networks
A Stanić - 2024 - folia.unifr.ch
Deep neural networks (NNs) recently revolutionized the field of Artificial Intelligence, making
great progress in computer vision, natural language processing, complex game play …
great progress in computer vision, natural language processing, complex game play …
Learning structured neural representations for visual reasoning tasks
S van Steenkiste - 2020 - sonar.ch
Deep neural networks learn representations of data to facilitate problem-solving in their
respective domains. However, they struggle to acquire a structured representation based on …
respective domains. However, they struggle to acquire a structured representation based on …
The Role of Time in Machine Perception
ML Iuzzolino - 2022 - search.proquest.com
Artificial neural networks have become ubiquitous for machine perception, yielding
unprecedented performance across an ever-increasing range of tasks and domains …
unprecedented performance across an ever-increasing range of tasks and domains …
Towards unsupervised multi-object perception in neural networks
K Greff - 2022 - folia.unifr.ch
By decomposing the world in terms of objects, humans are able to recombine their existing
knowledge in a virtually unbounded number ways to understand unfamiliar situations, make …
knowledge in a virtually unbounded number ways to understand unfamiliar situations, make …