Search Results - "Palm, Rasmus Berg"

Severe damage recovery in evolving soft robots through differentiable programming by Horibe, Kazuya, Walker, Kathryn, Berg Palm, Rasmus, Sudhakaran, Shyam, Risi, Sebastian

“…Biological systems are very robust to morphological damage, but artificial systems (robots) are currently not. In this paper we present a system based on…”
Get full text

Physical Neural Cellular Automata for 2D Shape Classification by Walker, Kathryn, Palm, Rasmus Berg, Moreno, Rodrigo, Faina, Andres, Stoy, Kasper, Risi, Sebastian

“…Materials with the ability to self-classify their own shape have the potential to advance a wide range of engineering applications and industries. Biological…”
Get full text

CloudScan - A Configuration-Free Invoice Analysis System Using Recurrent Neural Networks by Palm, Rasmus Berg, Winther, Ole, Laws, Florian

“…We present CloudScan; an invoice analysis system that requires zero configuration or upfront annotation. In contrast to previous work, CloudScan does not rely…”
Get full text

Attend, Copy, Parse End-to-end Information Extraction from Documents by Palm, Rasmus Berg, Laws, Florian, Winther, Ole

“…Document information extraction tasks performed by humans create data consisting of a PDF or document image input, and extracted string outputs. This…”
Get full text

Finding Game Levels with the Right Difficulty in a Few Trials through Intelligent Trial-and-Error by Gonzalez-Duque, Miguel, Palm, Rasmus Berg, Ha, David, Risi, Sebastian

“…Methods for dynamic difficulty adjustment allow games to be tailored to particular players to maximize their engagement. However, current methods often only…”
Get full text

Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry by Gonzalez-Duque, Miguel, Palm, Rasmus Berg, Hauberg, Soren, Risi, Sebastian

“…Deep generative models can automatically create content of diverse types. However, there are no guarantees that such content will satisfy the criteria…”
Get full text

Fast Game Content Adaptation Through Bayesian-based Player Modelling by Gonzalez-Duque, Miguel, Palm, Rasmus Berg, Risi, Sebastian

“…In games, as well as many user-facing systems, adapting content to users' preferences and experience is an important challenge. This paper explores a novel…”
Get full text

Testing the Genomic Bottleneck Hypothesis in Hebbian Meta-Learning by Palm, Rasmus Berg, Najarro, Elias, Risi, Sebastian

“…Hebbian meta-learning has recently shown promise to solve hard reinforcement learning problems, allowing agents to adapt to some degree to changes in the…”
Get full text

Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry by González-Duque, Miguel, Palm, Rasmus Berg, Hauberg, Søren, Risi, Sebastian

“…Deep generative models can automatically create content of diverse types. However, there are no guarantees that such content will satisfy the criteria…”
Get full text

Variational Neural Cellular Automata by Palm, Rasmus Berg, González-Duque, Miguel, Sudhakaran, Shyam, Risi, Sebastian

“…In nature, the process of cellular growth and differentiation has lead to an amazing diversity of organisms -- algae, starfish, giant sequoia, tardigrades, and…”
Get full text

Fast Game Content Adaptation Through Bayesian-based Player Modelling by González-Duque, Miguel, Palm, Rasmus Berg, Risi, Sebastian

“…In games, as well as many user-facing systems, adapting content to users' preferences and experience is an important challenge. This paper explores a novel…”
Get full text

Severe Damage Recovery in Evolving Soft Robots through Differentiable Programming by Horibe, Kazuya, Walker, Kathryn, Palm, Rasmus Berg, Sudhakaran, Shyam, Risi, Sebastian

“…Biological systems are very robust to morphological damage, but artificial systems (robots) are currently not. In this paper we present a system based on…”
Get full text

Attend, Copy, Parse -- End-to-end information extraction from documents by Palm, Rasmus Berg, Laws, Florian, Winther, Ole

“…ICDAR 2019 Document information extraction tasks performed by humans create data consisting of a PDF or document image input, and extracted string outputs…”
Get full text

Physical Neural Cellular Automata for 2D Shape Classification by Walker, Kathryn, Palm, Rasmus Berg, Garcia, Rodrigo Moreno, Faina, Andres, Stoy, Kasper, Risi, Sebastian

“…Materials with the ability to self-classify their own shape have the potential to advance a wide range of engineering applications and industries. Biological…”
Get full text

Finding Game Levels with the Right Difficulty in a Few Trials through Intelligent Trial-and-Error by González-Duque, Miguel, Palm, Rasmus Berg, Ha, David, Risi, Sebastian

“…Methods for dynamic difficulty adjustment allow games to be tailored to particular players to maximize their engagement. However, current methods often only…”
Get full text

Is an encoder within reach? by Hauschultz, Helene, Moreno-Muños, Rasmus Berg Palm. Pablo, Detlefsen, Nicki Skafte, Plessis, Andrew Allan du, Hauberg, Søren

“…The encoder network of an autoencoder is an approximation of the nearest point projection onto the manifold spanned by the decoder. A concern with this…”
Get full text

Recurrent Relational Networks by Palm, Rasmus Berg, Paquet, Ulrich, Winther, Ole

“…This paper is concerned with learning to solve tasks that require a chain of interdependent steps of relational inference, like answering complex questions…”
Get full text

CloudScan - A configuration-free invoice analysis system using recurrent neural networks by Palm, Rasmus Berg, Winther, Ole, Laws, Florian

“…We present CloudScan; an invoice analysis system that requires zero configuration or upfront annotation. In contrast to previous work, CloudScan does not rely…”
Get full text

EvoCraft: A New Challenge for Open-Endedness by Grbic, Djordje, Palm, Rasmus Berg, Najarro, Elias, Glanois, Claire, Risi, Sebastian

“…This paper introduces EvoCraft, a framework for Minecraft designed to study open-ended algorithms. We introduce an API that provides an open-source Python…”
Get full text

Evolutionary Planning in Latent Space by Olesen, Thor V. A. N, Nguyen, Dennis T. T, Palm, Rasmus Berg, Risi, Sebastian

“…Planning is a powerful approach to reinforcement learning with several desirable properties. However, it requires a model of the world, which is not readily…”
Get full text