Search

Your search keyword '"Petersen, Stig"' showing total 606 results
Start Over Author "Petersen, Stig"
606 results on '"Petersen, Stig"'

2. Inverse method applied to autonomous broadband hydroacoustic survey detects higher densities of zooplankton in near-surface aggregations than vessel-based net survey

Author

Dunn, Muriel, Pedersen, Geir, Basedow, Sunnje L., Daase, Malin, Falk-Petersen, Stig, Bachelot, Loic, Camus, Lionel, and Geoffroy, Maxime

Subjects
Environmental monitoring, Zooplankton -- Distribution -- Environmental aspects, Zoological research, Machine learning -- Usage, Company distribution practices, Earth sciences
Abstract

Throughout all oceans, aggregations of zooplankton and ichthyoplankton appear as horizontal sound scattering layers (SSLs) when detected with active acoustic techniques. Quantifying the composition and density of these layers is prone to sampling biases. We conducted a net and trawl survey of the epipelagic fauna in northern Norway (70[degrees] N) in June 2018 while an autonomous surface vehicle equipped with a broadband echosounder (283-383 kHz) surveyed the same region. Densities from the autonomous hydroacoustic survey were calculated using forward estimates from the relative density from the net and trawl, and inversion estimates with statistical data-fitting. All four methods (net, trawl, acoustic forward and inverse methods) identified that copepods dominated the epipelagic SSL, while pteropods, amphipods and fish larvae were present in low densities. The density estimates calculated with the inverse method were higher for mobile zooplankton, such as euphausiid larvae, than with the other methods. We concluded that the inverse method applied to broadband autonomous acoustic surveys can improve density estimates of epipelagic organisms by diminishing avoidance biases and increasing the spatio-temporal resolution of ship-based surveys. Key words: broadband acoustics, inversion, machine learning, autonomous surface vehicle, zooplankton, Introduction Pelagic zooplankton and ichthyoplankton form dense horizontal aggregations throughout all oceans and represent an easily accessible food source for higher trophic levels. In the North Atlantic, these organisms funnel [...]

Published
2023
Full Text
View/download PDF

3. Spectral Inference Networks: Unifying Deep and Spectral Learning

Author

Pfau, David, Petersen, Stig, Agarwal, Ashish, Barrett, David G. T., and Stachenfeld, Kimberly L.

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning
Abstract

We present Spectral Inference Networks, a framework for learning eigenfunctions of linear operators by stochastic optimization. Spectral Inference Networks generalize Slow Feature Analysis to generic symmetric operators, and are closely related to Variational Monte Carlo methods from computational physics. As such, they can be a powerful tool for unsupervised representation learning from video or graph-structured data. We cast training Spectral Inference Networks as a bilevel optimization problem, which allows for online learning of multiple eigenfunctions. We show results of training Spectral Inference Networks on problems in quantum mechanics and feature learning for videos on synthetic datasets. Our results demonstrate that Spectral Inference Networks accurately recover eigenfunctions of linear operators and can discover interpretable representations from video in a fully unsupervised manner., Comment: Fixed typo in math in section 4

Published
2018

4. StarCraft II: A New Challenge for Reinforcement Learning

Author

Vinyals, Oriol, Ewalds, Timo, Bartunov, Sergey, Georgiev, Petko, Vezhnevets, Alexander Sasha, Yeo, Michelle, Makhzani, Alireza, Küttler, Heinrich, Agapiou, John, Schrittwieser, Julian, Quan, John, Gaffney, Stephen, Petersen, Stig, Simonyan, Karen, Schaul, Tom, van Hasselt, Hado, Silver, David, Lillicrap, Timothy, Calderone, Kevin, Keet, Paul, Brunasso, Anthony, Lawrence, David, Ekermo, Anders, Repp, Jacob, and Tsing, Rodney

Subjects
Computer Science - Learning, Computer Science - Artificial Intelligence
Abstract

This paper introduces SC2LE (StarCraft II Learning Environment), a reinforcement learning environment based on the StarCraft II game. This domain poses a new grand challenge for reinforcement learning, representing a more difficult class of problems than considered in most prior work. It is a multi-agent problem with multiple players interacting; there is imperfect information due to a partially observed map; it has a large action space involving the selection and control of hundreds of units; it has a large state space that must be observed solely from raw input feature planes; and it has delayed credit assignment requiring long-term strategies over thousands of steps. We describe the observation, action, and reward specification for the StarCraft II domain and provide an open source Python-based interface for communicating with the game engine. In addition to the main game maps, we provide a suite of mini-games focusing on different elements of StarCraft II gameplay. For the main game maps, we also provide an accompanying dataset of game replay data from human expert players. We give initial baseline results for neural networks trained from this data to predict game outcomes and player actions. Finally, we present initial baseline results for canonical deep reinforcement learning agents applied to the StarCraft II domain. On the mini-games, these agents learn to achieve a level of play that is comparable to a novice player. However, when trained on the main game, these agents are unable to make significant progress. Thus, SC2LE offers a new and challenging environment for exploring deep reinforcement learning algorithms and architectures., Comment: Collaboration between DeepMind & Blizzard. 20 pages, 9 figures, 2 tables

Published
2017

5. Zooplankton in the Polar Night

Author

Berge, Jørgen, Daase, Malin, Hobbs, Laura, Falk-Petersen, Stig, Darnis, Gerald, Søreide, Janne E., Piepenburg, Dieter, Series Editor, Berge, Jørgen, editor, Johnsen, Geir, editor, and Cohen, Jonathan H., editor

Published
2020
Full Text
View/download PDF

6. DeepMind Lab

Author

Beattie, Charles, Leibo, Joel Z., Teplyashin, Denis, Ward, Tom, Wainwright, Marcus, Küttler, Heinrich, Lefrancq, Andrew, Green, Simon, Valdés, Víctor, Sadik, Amir, Schrittwieser, Julian, Anderson, Keith, York, Sarah, Cant, Max, Cain, Adam, Bolton, Adrian, Gaffney, Stephen, King, Helen, Hassabis, Demis, Legg, Shane, and Petersen, Stig

Subjects
Computer Science - Artificial Intelligence
Abstract

DeepMind Lab is a first-person 3D game platform designed for research and development of general artificial intelligence and machine learning systems. DeepMind Lab can be used to study how autonomous artificial agents may learn complex tasks in large, partially observed, and visually diverse worlds. DeepMind Lab has a simple and flexible API enabling creative task-designs and novel AI-designs to be explored and quickly iterated upon. It is powered by a fast and widely recognised game engine, and tailored for effective use by the research community., Comment: 11 pages, 8 figures

Published
2016

7. Highly accurate protein structure prediction with AlphaFold

Author

Jumper, John, Evans, Richard, Pritzel, Alexander, Green, Tim, Figurnov, Michael, Ronneberger, Olaf, Tunyasuvunakool, Kathryn, Bates, Russ, Žídek, Augustin, Potapenko, Anna, Bridgland, Alex, Meyer, Clemens, Kohl, Simon A. A., Ballard, Andrew J., Cowie, Andrew, Romera-Paredes, Bernardino, Nikolov, Stanislav, Jain, Rishub, Adler, Jonas, Back, Trevor, Petersen, Stig, Reiman, David, Clancy, Ellen, Zielinski, Michal, Steinegger, Martin, Pacholska, Michalina, Berghammer, Tamas, Bodenstein, Sebastian, Silver, David, Vinyals, Oriol, Senior, Andrew W., Kavukcuoglu, Koray, Kohli, Pushmeet, and Hassabis, Demis

Published
2021
Full Text
View/download PDF

8. Highly accurate protein structure prediction for the human proteome

Author

Tunyasuvunakool, Kathryn, Adler, Jonas, Wu, Zachary, Green, Tim, Zielinski, Michal, Žídek, Augustin, Bridgland, Alex, Cowie, Andrew, Meyer, Clemens, Laydon, Agata, Velankar, Sameer, Kleywegt, Gerard J., Bateman, Alex, Evans, Richard, Pritzel, Alexander, Figurnov, Michael, Ronneberger, Olaf, Bates, Russ, Kohl, Simon A. A., Potapenko, Anna, Ballard, Andrew J., Romera-Paredes, Bernardino, Nikolov, Stanislav, Jain, Rishub, Clancy, Ellen, Reiman, David, Petersen, Stig, Senior, Andrew W., Kavukcuoglu, Koray, Birney, Ewan, Kohli, Pushmeet, Jumper, John, and Hassabis, Demis

Published
2021
Full Text
View/download PDF

9. Massively Parallel Methods for Deep Reinforcement Learning

Author

Nair, Arun, Srinivasan, Praveen, Blackwell, Sam, Alcicek, Cagdas, Fearon, Rory, De Maria, Alessandro, Panneershelvam, Vedavyas, Suleyman, Mustafa, Beattie, Charles, Petersen, Stig, Legg, Shane, Mnih, Volodymyr, Kavukcuoglu, Koray, and Silver, David

Subjects
Computer Science - Learning, Computer Science - Artificial Intelligence, Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Neural and Evolutionary Computing
Abstract

We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour; parallel learners that are trained from stored experience; a distributed neural network to represent the value function or behaviour policy; and a distributed store of experience. We used our architecture to implement the Deep Q-Network algorithm (DQN). Our distributed algorithm was applied to 49 games from Atari 2600 games from the Arcade Learning Environment, using identical hyperparameters. Our performance surpassed non-distributed DQN in 41 of the 49 games and also reduced the wall-time required to achieve these results by an order of magnitude on most games., Comment: Presented at the Deep Learning Workshop, International Conference on Machine Learning, Lille, France, 2015

Published
2015

10. Model-informed classification of broadband acoustic backscatter from zooplankton in an in situ mesocosm.

Author

Dunn, Muriel, McGowan-Yallop, Chelsey, Pedersen, Geir, Falk-Petersen, Stig, Daase, Malin, Last, Kim, Langbehn, Tom J, Fielding, Sophie, Brierley, Andrew S, Cottier, Finlo, Basedow, Sünnje L, Camus, Lionel, and Geoffroy, Maxime

Subjects
MACHINE learning, SOUND wave scattering, ACOUSTIC models, FISHING nets, BACKSCATTERING
Abstract

Classification of zooplankton to species with broadband echosounder data could increase the taxonomic resolution of acoustic surveys and reduce the dependence on net and trawl samples for 'ground truthing'. Supervised classification with broadband echosounder data is limited by the acquisition of validated data required to train machine learning algorithms ('classifiers'). We tested the hypothesis that acoustic scattering models could be used to train classifiers for remote classification of zooplankton. Three classifiers were trained with data from scattering models of four Arctic zooplankton groups (copepods, euphausiids, chaetognaths, and hydrozoans). We evaluated classifier predictions against observations of a mixed zooplankton community in a submerged purpose-built mesocosm (12 m3) insonified with broadband transmissions (185–255 kHz). The mesocosm was deployed from a wharf in Ny-Ålesund, Svalbard, during the Arctic polar night in January 2022. We detected 7722 tracked single targets, which were used to evaluate the classifier predictions of measured zooplankton targets. The classifiers could differentiate copepods from the other groups reasonably well, but they could not differentiate euphausiids, chaetognaths, and hydrozoans reliably due to the similarities in their modelled target spectra. We recommend that model-informed classification of zooplankton from broadband acoustic signals be used with caution until a better understanding of in situ target spectra variability is gained. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

14. Improved protein structure prediction using potentials from deep learning

Author

Senior, Andrew W., Evans, Richard, Jumper, John, Kirkpatrick, James, Sifre, Laurent, Green, Tim, Qin, Chongli, Žídek, Augustin, Nelson, Alexander W. R., Bridgland, Alex, Penedones, Hugo, Petersen, Stig, Simonyan, Karen, Crossan, Steve, Kohli, Pushmeet, Jones, David T., Silver, David, Kavukcuoglu, Koray, and Hassabis, Demis

Published
2020
Full Text
View/download PDF

16. Model-informed classification of broadband acoustic backscatter from zooplankton in an in situ mesocosm

Author

Dunn, Muriel, primary, McGowan-Yallop, Chelsey, additional, Pedersen, Geir, additional, Falk-Petersen, Stig, additional, Daase, Malin, additional, Last, Kim, additional, Langbehn, Tom J, additional, Fielding, Sophie, additional, Brierley, Andrew S, additional, Cottier, Finlo, additional, Basedow, Sünnje L, additional, Camus, Lionel, additional, and Geoffroy, Maxime, additional

Published
2023
Full Text
View/download PDF

23. Vector-based navigation using grid-like representations in artificial agents

Author

Banino, Andrea, Barry, Caswell, Uria, Benigno, Blundell, Charles, Lillicrap, Timothy, Mirowski, Piotr, Pritzel, Alexander, Chadwick, Martin J., Degris, Thomas, Modayil, Joseph, Wayne, Greg, Soyer, Hubert, Viola, Fabio, Zhang, Brian, Goroshin, Ross, Rabinowitz, Neil, Pascanu, Razvan, Beattie, Charlie, Petersen, Stig, Sadik, Amir, Gaffney, Stephen, King, Helen, Kavukcuoglu, Koray, Hassabis, Demis, Hadsell, Raia, and Kumaran, Dharshan

Published
2018
Full Text
View/download PDF

24. Model-informed classification of broadband acoustic backscatter from zooplankton in an in situ mesocosm

Author

Dunn, Muriel, McGowan-Yallop, Chelsey, Pedersen, Geir, Falk-Petersen, Stig, Daase, Malin, Last, Kim, Langbehn, Tom J, Fielding, Sophie, Brierley, Andrew S, Cottier, Finlo, Basedow, Sünnje L, Camus, Lionel, Geoffroy, Maxime, Wieczorek, Alina, Dunn, Muriel, McGowan-Yallop, Chelsey, Pedersen, Geir, Falk-Petersen, Stig, Daase, Malin, Last, Kim, Langbehn, Tom J, Fielding, Sophie, Brierley, Andrew S, Cottier, Finlo, Basedow, Sünnje L, Camus, Lionel, Geoffroy, Maxime, and Wieczorek, Alina

Abstract

Classification of zooplankton to species with broadband echosounder data could increase the taxonomic resolution of acoustic surveys and reduce the dependence on net and trawl samples for ‘ground truthing’. Supervised classification with broadband echosounder data is limited by the acquisition of validated data required to train machine learning algorithms (‘classifiers’). We tested the hypothesis that acoustic scattering models could be used to train classifiers for remote classification of zooplankton. Three classifiers were trained with data from scattering models of four Arctic zooplankton groups (copepods, euphausiids, chaetognaths, and hydrozoans). We evaluated classifier predictions against observations of a mixed zooplankton community in a submerged purpose-built mesocosm (12 m3) insonified with broadband transmissions (185–255 kHz). The mesocosm was deployed from a wharf in Ny-Ålesund, Svalbard, during the Arctic polar night in January 2022. We detected 7722 tracked single targets, which were used to evaluate the classifier predictions of measured zooplankton targets. The classifiers could differentiate copepods from the other groups reasonably well, but they could not differentiate euphausiids, chaetognaths, and hydrozoans reliably due to the similarities in their modelled target spectra. We recommend that model-informed classification of zooplankton from broadband acoustic signals be used with caution until a better understanding of in situ target spectra variability is gained.

Published
2023

34. Response to Comment on “Pushing the frontiers of density functionals by solving the fractional electron problem”

Author

Kirkpatrick, James, primary, McMorrow, Brendan, additional, Turban, David H. P., additional, Gaunt, Alexander L., additional, Spencer, James S., additional, Matthews, Alexander G. D. G., additional, Obika, Annette, additional, Thiry, Louis, additional, Fortunato, Meire, additional, Pfau, David, additional, Román Castellanos, Lara, additional, Petersen, Stig, additional, Nelson, Alexander W. R., additional, Kohli, Pushmeet, additional, Mori-Sánchez, Paula, additional, Hassabis, Demis, additional, and Cohen, Aron J., additional

Published
2022
Full Text
View/download PDF

35. Human-level control through deep reinforcement learning

Author

Kavukcuoglu, Koray, Silver, David, Rusu, Andrei A., Veness, Joel, Bellemare, Marc G., Graves, Alex, Riedmiller, Martin, Fidjeland, Andreas K., Ostrovski, Georg, Petersen, Stig, Beattie, Charles, Sadik, Amir, Antonoglou, Ioannis, King, Helen, Kumaran, Dharshan, Wierstra, Daan, Legg, Shane, and Hassabis, Demis

Subjects
Neural networks -- Physiological aspects -- Research, Reinforcement learning (Machine learning) -- Psychological aspects -- Methods, Algorithms -- Usage, Neural network, Algorithm, Environmental issues, Science and technology, Zoology and wildlife conservation
Abstract

The theory of reinforcement learning provides a normative account (1), deeply rooted in psychological (2) and neuroscientific (3) perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems (4,5), the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms (3). While reinforcement learning agents have achieved some successes in a variety of domains (6-8), their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks (9-11) to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games (12). We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks., We set out to create a single algorithm that would be able to develop a wide range of competencies on a varied range of challenging tasks--a central goal of general [...]

Published
2015

36. Human-level control through deep reinforcement learning

Author

Mnih, Volodymyr, Kavukcuoglu, Koray, Silver, David, Rusu, Andrei A., Veness, Joel, Bellemare, Marc G., Graves, Alex, Riedmiller, Martin, Fidjeland, Andreas K., Ostrovski, Georg, Petersen, Stig, Beattie, Charles, Sadik, Amir, Antonoglou, Ioannis, King, Helen, Kumaran, Dharshan, Wierstra, Daan, Legg, Shane, and Hassabis, Demis

Published
2015
Full Text
View/download PDF

45. Application of artificial neural network to estimate the quality of little auks' potential foraging grounds on Spitsbergen

Author

Boehnke, Rafał, primary, Wichorowski, Marcin, additional, Trudnowska, Emilia, additional, Balazy, Kaja, additional, Jakubas, Dariusz, additional, Wold, Anette, additional, Wojczulanis‐Jakubas, Katarzyna, additional, Falk‐Petersen, Stig, additional, Kidawa, Dorota, additional, Hop, Haakon, additional, and Błachowiak‐Samołyk, Katarzyna, additional

Published
2022
Full Text
View/download PDF

47. Large scale patches of Calanus finmarchicus and associated hydrographic conditions off the Lofoten archipelago

Author

Weidberg, Nicholas, Santana Hernandez, Nestor, Renner, Angelika, Falk‑Petersen, Stig, and Basedow, Sünnje Linnéa

Subjects
VDP::Mathematics and natural scienses: 400::Zoology and botany: 480::Marine biology: 497, VDP::Matematikk og naturvitenskap: 400::Geofag: 450::Oseanografi: 452, VDP::Matematikk og naturvitenskap: 400::Zoologiske og botaniske fag: 480::Marinbiologi: 497, VDP::Oseanografi: 452, VDP::Oceanography: 452, Aquatic Science, Oceanography, VDP::Mathematics and natural scienses: 400::Geosciences: 450::Oceanography: 452, Ecology, Evolution, Behavior and Systematics
Abstract

Large swarms of individuals at different spatiotemporal scales characterise the distributions of many animal species. In the ocean several mesozooplankton taxa aggregate in large patches or swarms driven by active behavioural responses to hydrographic structures, although intrinsic biotic characteristics of species´ life cycles not related with the environment can also affect spatial distributions. To understand the mechanisms of aggregation and disentangle environmental and pure spatial effects contributing to patch formation, we extensively sampled a large Calanus finmarchicus patch off the Lofoten islands, northern Norway, in spring 2017 by means of Laser Optical Plankton Counter (LOPC) cross shelf transects and biophysical samplings at fixed stations. We observed a clear association between the buoyant layer of the fresh, cold Norwegian Coastal Current (NCC) and high surface copepod abundances. Off shelf lateral displacements of the NCC along its path may retain copepods from the offshore basins. At deeper layers, copepod abundances increased markedly at regions with low sea level anomalies and reduced vertical flows. Our results also suggest that copepods performed short range diel vertical migration within the patch. Potential future changes in the seasonality and structure of the NCC and their impact on swarm occurrence and formation are discussed.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results