Philosophical transactions of the Royal Society of London. Series B, Biological sciences
Feb 24, 2020
A few billion years have passed since the first life forms appeared. Since then, life has continued to forge complex associations between the different emergent levels of interconnection it forms. The advances of recent decades in molecular chemistry...
Philosophical transactions of the Royal Society of London. Series B, Biological sciences
Feb 24, 2020
Network representations are flat while mechanisms are organized into a hierarchy of levels, suggesting that the two are fundamentally opposed. I challenge this opposition by focusing on two aspects of the ways in which large-scale networks constructe...
Philosophical transactions of the Royal Society of London. Series B, Biological sciences
Dec 16, 2019
Understanding how the brain forms representations of structured information distributed in time is a challenging endeavour for the neuroscientific community, requiring computationally and neurobiologically informed approaches. The neural mechanisms f...
Philosophical transactions of the Royal Society of London. Series B, Biological sciences
Dec 16, 2019
We argue that natural language can be usefully described as quasi-compositional and we suggest that deep learning-based neural language models bear long-term promise to capture how language conveys meaning. We also note that a successful account of h...
Philosophical transactions of the Royal Society of London. Series B, Biological sciences
Dec 16, 2019
Combinatorial generalization-the ability to understand and produce novel combinations of already familiar elements-is considered to be a core capacity of the human mind and a major challenge to neural network models. A significant body of research su...
Philosophical transactions of the Royal Society of London. Series B, Biological sciences
Dec 16, 2019
Neither neurobiological nor process models of meaning composition specify the operator through which constituent parts are bound together into compositional structures. In this paper, we argue that a neurophysiological computation system cannot achie...
Philosophical transactions of the Royal Society of London. Series B, Biological sciences
Dec 16, 2019
In the last decade, deep artificial neural networks have achieved astounding performance in many natural language-processing tasks. Given the high productivity of language, these models must possess effective generalization abilities. It is widely as...
Philosophical transactions of the Royal Society of London. Series B, Biological sciences
Jul 8, 2019
The number of all possible epidemics of a given infectious disease that could occur on a given landscape is large for systems of real-world complexity. Furthermore, there is no guarantee that the control actions that are optimal, on average, over all...
Philosophical transactions of the Royal Society of London. Series B, Biological sciences
Jun 10, 2019
Reservoir computing (RC) is a powerful computational paradigm that allows high versatility with cheap learning. While other artificial intelligence approaches need exhaustive resources to specify their inner workings, RC is based on a reservoir with ...
Philosophical transactions of the Royal Society of London. Series B, Biological sciences
Apr 29, 2019
Social interaction is an extremely complex yet vital component in daily life. We present a bottom-up approach for the emergence of social behaviours from the interaction of the curiosity drive, i.e. the intrinsic motivation to learn as much as possib...