Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Niklasson, Eyvind"'
Autor:
Arcas, Blaise Agüera y, Alakuijala, Jyrki, Evans, James, Laurie, Ben, Mordvintsev, Alexander, Niklasson, Eyvind, Randazzo, Ettore, Versari, Luca
The fields of Origin of Life and Artificial Life both question what life is and how it emerges from a distinct set of "pre-life" dynamics. One common feature of most substrates where life emerges is a marked shift in dynamics when self-replication ap
Externí odkaz:
http://arxiv.org/abs/2406.19108
Autor:
Pajouheshgar, Ehsan, Xu, Yitao, Mordvintsev, Alexander, Niklasson, Eyvind, Zhang, Tong, Süsstrunk, Sabine
Texture modeling and synthesis are essential for enhancing the realism of virtual environments. Methods that directly synthesize textures in 3D offer distinct advantages to the UV-mapping-based methods as they can create seamless textures and align m
Externí odkaz:
http://arxiv.org/abs/2311.02820
Autor:
von Oswald, Johannes, Schlegel, Maximilian, Meulemans, Alexander, Kobayashi, Seijin, Niklasson, Eyvind, Zucchet, Nicolas, Scherrer, Nino, Miller, Nolan, Sandler, Mark, Arcas, Blaise Agüera y, Vladymyrov, Max, Pascanu, Razvan, Sacramento, João
Some autoregressive models exhibit in-context learning capabilities: being able to learn as an input sequence is processed, without undergoing any parameter changes, and without being explicitly trained to do so. The origins of this phenomenon are st
Externí odkaz:
http://arxiv.org/abs/2309.05858
We present a differentiable formulation of abstract chemical reaction networks (CRNs) that can be trained to solve a variety of computational tasks. Chemical reaction networks are one of the most fundamental computational substrates used by nature. W
Externí odkaz:
http://arxiv.org/abs/2302.02714
Autor:
von Oswald, Johannes, Niklasson, Eyvind, Randazzo, Ettore, Sacramento, João, Mordvintsev, Alexander, Zhmoginov, Andrey, Vladymyrov, Max
At present, the mechanisms of in-context learning in Transformers are not well understood and remain mostly an intuition. In this paper, we suggest that training Transformers on auto-regressive objectives is closely related to gradient-based meta-lea
Externí odkaz:
http://arxiv.org/abs/2212.07677
We study the problem of example-based procedural texture synthesis using highly compact models. Given a sample image, we use differentiable programming to train a generative process, parameterised by a recurrent Neural Cellular Automata (NCA) rule. C
Externí odkaz:
http://arxiv.org/abs/2111.13545
Reaction-Diffusion (RD) systems provide a computational framework that governs many pattern formation processes in nature. Current RD system design practices boil down to trial-and-error parameter search. We propose a differentiable optimization meth
Externí odkaz:
http://arxiv.org/abs/2107.06862
Neural Cellular Automata (NCA) have shown a remarkable ability to learn the required rules to "grow" images, classify morphologies, segment images, as well as to do general computation such as path-finding. We believe the inductive prior they introdu
Externí odkaz:
http://arxiv.org/abs/2105.07299
We present a novel method for learning the weights of an artificial neural network - a Message Passing Learning Protocol (MPLP). In MPLP, we abstract every operations occurring in ANNs as independent agents. Each agent is responsible for ingesting in
Externí odkaz:
http://arxiv.org/abs/2007.00970
We propose a joint simulation and real-world learning framework for mapping navigation instructions and raw first-person observations to continuous control. Our model estimates the need for environment exploration, predicts the likelihood of visiting
Externí odkaz:
http://arxiv.org/abs/1910.09664