Zobrazeno 1 - 10
of 6 684
pro vyhledávání: '"Risi, A."'
Autor:
Nisioti, Eleni, Risi, Sebastian, Momennejad, Ida, Oudeyer, Pierre-Yves, Moulin-Frier, Clément
Human culture relies on collective innovation: our ability to continuously explore how existing elements in our environment can be combined to create new ones. Language is hypothesized to play a key role in human culture, driving individual cognitive
Externí odkaz:
http://arxiv.org/abs/2407.05377
Due to their architecture and how they are trained, artificial neural networks are typically not robust toward pruning, replacing, or shuffling layers at test time. However, such properties would be desirable for different applications, such as distr
Externí odkaz:
http://arxiv.org/abs/2407.04513
Autor:
Nisioti, Eleni, Glanois, Claire, Najarro, Elias, Dai, Andrew, Meyerson, Elliot, Pedersen, Joachim Winther, Teodorescu, Laetitia, Hayes, Conor F., Sudhakaran, Shyam, Risi, Sebastian
Large Language Models (LLMs) have taken the field of AI by storm, but their adoption in the field of Artificial Life (ALife) has been, so far, relatively reserved. In this work we investigate the potential synergies between LLMs and ALife, drawing on
Externí odkaz:
http://arxiv.org/abs/2407.09502
Evolving Self-Assembling Neural Networks: From Spontaneous Activity to Experience-Dependent Learning
Biological neural networks are characterized by their high degree of plasticity, a core property that enables the remarkable adaptability of natural organisms. Importantly, this ability affects both the synaptic strength and the topology of the nervo
Externí odkaz:
http://arxiv.org/abs/2406.09787
Upon introducing an heavy quark in the perturbative regime of the QCD conformal window we precisely determine the associated heavy meson spectrum and wave functions in terms of the number of light flavours and mass. We then compute the conformal Isgu
Externí odkaz:
http://arxiv.org/abs/2406.09758
Representations for black-box optimisation methods (such as evolutionary algorithms) are traditionally constructed using a delicate manual process. This is in contrast to the representation that maps DNAs to phenotypes in biological organisms, which
Externí odkaz:
http://arxiv.org/abs/2406.09020
Multiresolution Matrix Factorization (MMF) is unusual amongst fast matrix factorization algorithms in that it does not make a low rank assumption. This makes MMF especially well suited to modeling certain types of graphs with complex multiscale or hi
Externí odkaz:
http://arxiv.org/abs/2406.00469
Autor:
Kundu, Soumyabrata, Kondor, Risi
In this work we introduce Steerable Transformers, an extension of the Vision Transformer mechanism that maintains equivariance to the special Euclidean group $\mathrm{SE}(d)$. We propose an equivariant attention mechanism that operates on features ex
Externí odkaz:
http://arxiv.org/abs/2405.15932
In biological evolution complex neural structures grow from a handful of cellular ingredients. As genomes in nature are bounded in size, this complexity is achieved by a growth process where cells communicate locally to decide whether to differentiat
Externí odkaz:
http://arxiv.org/abs/2405.08510
Image-generation models are changing how we express ourselves in visual art. However, what people think of AI-generated art is still largely unexplored, especially compared to traditional art. In this paper, we present the design of an interactive re
Externí odkaz:
http://arxiv.org/abs/2405.01901