Ketil Malde
Arbeidsområde
Arbeider med å utvikle metoder basert på moderne maskinlæringsteknologi for storskala dataanalyse, i hovedsak på bildedata fra lab og felt, samt akustiske data gjennom SFI-prosjektet CRIMAC. Leder ICES' arbeidsgruppe for maskinlæring i marin forskning, WGMLEARN.
Har i tillegg en undervisningsstilling i maskinlæringsgruppen ved Institutt for Informatikk, hvor jeg for tiden har ansvar for å utvikle og undervise kurset Inf265 - Deep Learning.
Har tidligere jobbet med metodeutvikling og bioinformatisk dataanlyse, særlig rettet mot annengenerasjons sekvensdata og de novo assembly, bl.a. i prosjektet for å sekvensiere torskens og lakselusens genom. Analyse og håndtering av molekylærbiologiske data. Funksjonell programmering.
Se også blog.malde.org og biohaskell.org .
Publikasjoner
Vitenskapelige artikler (NVI)
2024
ProxyDR: Deep Hyperspherical Metric Learning with Distance Ratio-Based Formulation
Lecture Notes in Computer Science (LNCS)
2024
Trajectory-based fish event classification through pre-training with diffusion models
Ecological Informatics
82
2023
Measuring Adversarial Robustness using a Voronoi-Epsilon Adversary
Proceedings of the Northern Lights Deep Learning Workshop
2023
A contrastive learning approach for individual re-identification in a wild fish population
Proceedings of the Northern Lights Deep Learning Workshop
4
2023
Age interpretation of cod otoliths using deep learning
Ecological Informatics
2023
Annotating otoliths with a deep generative model
ICES Journal of Marine Science
2023
Machine learning in marine ecology: an overview of techniques and applications
ICES Journal of Marine Science
80
p. 1829-1853
2023
Machine learning in marine ecology: an overview of techniques and applications
ICES Journal of Marine Science
80
p. 1829-1853
2022
The salmon louse genome may be much larger than sequencing suggests
Scientific Reports
12
p. 1-14
2022
DeepOtolith v1.0: An Open-Source AI Platform for Automating Fish Age Reading from Otolith or Scale Images
Fishes
7
2021
A real-world dataset and data simulation algorithm for automated fish species identification
Geoscience Data Journal
2021
Automatic interpretation of salmon scales using deep learning
Ecological Informatics
63
2021
A deep learning-based method to identify and count pelagic and mesopelagic fishes from trawl camera images
ICES Journal of Marine Science
78
p. 3780-3792
2021
The salmon louse genome: Copepod features and parasitic adaptations
Genomics
113
p. 3666-3680
2020
Genome wide analysis reveals genetic divergence between Goldsinny wrasse populations
BMC Genetics
21
p. 1-15
2020
Acoustic classification in multifrequency echosounder data using deep convolutional neural networks
ICES Journal of Marine Science
77
p. 1391-1400
2020
Machine intelligence and the data-driven future of marine science
ICES Journal of Marine Science
2020
Microbial communities associated with the parasitic copepod Lepeophtheirus salmonis.
Marine Genomics
49
2019
An efficient protocol and data set for automated otolith image analysis
Geoscience Data Journal
p. 1-9
2019
Airgun blasts used in marine seismic surveys have limited effects on mortality, and no sublethal effects on behaviour or gene expression, in the copepod Calanus finmarchicus
ICES Journal of Marine Science
76
p. 2033-2044
2019
Machine intelligence and the data-driven future of marine science
ICES Journal of Marine Science
2019
Microbial communities associated with the parasitic copepod Lepeophtheirus salmonis.
Marine Genomics
In Press
2019
\emph{Airgun blasts used in marine seismic surveys have a minor effect on survival at distances less than 10 m and no sub-lethal effects on behaviour or gene expression in the copepod Calanus finmarchicus}
ICES Journal of Marine Science
In press
2019
Levels and temporal trends of persistent organic pollutants (POPs) in Atlantic cod (Gadus morhua) and haddock (Melanogrammus aeglefinus) from the southern Barents Sea
Environmental Research
172
p. 89-97
2018
Automatic interpretation of otoliths using deep learning
PLOS ONE
13
p. 1-14
2018
Fish species identification using a convolutional neural network trained on synthetic data
ICES Journal of Marine Science
76
p. 342-349
2018
Judging a salmon by its spots: Environmental variation is the primary determinant of spot patterns in Salmo salar
BMC Ecology
18:14
p. 1-13
2017
Whole genome resequencing reveals diagnostic markers for investigating global migration and hybridization between minke whale species
BMC Genomics
18:76
p. 1-11
2015
Characterization of a novel RXR receptor in the salmon louse (Lepeophtheirus salmonis, Copepoda) regulating growth and female reproduction
BMC Genomics
16:81
2014
Estimating the information value of polymorphic sites using pooled sequences
BMC Genomics
15
2014
Human-induced evolution caught in action: SNP-array reveals rapid amphi-atlantic spread of pesticide resistance in the salmon ecotoparasite Lepeophtheirus salmonis
BMC Genomics
2014
Gene expression in five salmon louse (Lepeophtheirus salmonis, Krøyer 1837) tissues
Marine Genomics
18
p. 39-44
2014
Simulating a population genomics data set using FlowSim
BMC Research Notes
7:68
2013
How does sequence variability affect de novo assembly quality?
Journal of Natural History
47
p. 901-910
2013
Increasing Sequence Search Sensitivity with Transitive Alignments
PLOS ONE
8
2013
Filtering duplicate reads from 454 pyrosequencing data
Bioinformatics
29
p. 830-836
2012
Maternal 3 ' UTRs: from egg to onset of zygotic transcription in Atlantic cod
BMC Genomics
13
2011
The genome sequence of Atlantic cod reveals a unique immune system
Nature
477
p. 207-210
2011
Systematic exploration of error sources in pyrosequencing flowgram data
Bioinformatics
27
p. I304-I309
2011
EST resources and establishment and validation of a 16 k cDNA microarray from Atlantic cod (Gadus morhua)
Comparative Biochemistry and Physiology - Part D:Genomics and Proteomics
6
p. 23-30
2011
Flower: extracting information from pyrosequencing data
Bioinformatics
27
p. 1041-1042
2011
Identification of vimentin- and elastin-like transcripts specifically expressed in developing notochord of Atlantic salmon (Salmo salar L.)
Cell and Tissue Research
346
p. 191-202
2010
Calcium from salmon and cod bone is well absorbed in young healthy men: a double-blinded randomised crossover design
Nutrition & Metabolism
7
2010
Characteristics of 454 pyrosequencing data-enabling realistic simulation with flowsim
Bioinformatics
26
p. i420-i425
2009
Identification of immune related genes in Atlantic halibut (Hippoglossus hippoglossus L.) following in vivo antigenic and in vitro mitogenic stimulation
Fish and Shellfish Immunology
27
p. 729-738
2008
The effect of sequence quality on sequence alignment
Bioinformatics
24
p. 897-900
2008
Repeats and EST analysis for new organisms
BMC Genomics
9
2006
Calculating PSSM probabilities with lazy dynamic programming
Journal of functional programming
16
p. 75-81
2006
RBR: library-less repeat detection for ESTs
Bioinformatics
22
p. 2232-2236
2005
A graph based algorithm for generating EST consensus sequences
Bioinformatics
21
p. 1371-1375
2005
Masking repeats while clustering ESTs
Nucleic Acids Research (NAR)
33
p. 2176-2180
2003
Fast Sequence Clustering Using a Suffix Array Algorithm
Bioinformatics
19
p. 1221-1226
2003
A Fast Algorithm for EST Clustering using Suffix Arrays
Bioinformatics
Faglige foredrag
2024
Processing of large datasets using python and Korona
2024
Analysing large amounts of echosounder data using cloud based data access combined with deep learning models
2024
Decoding female mimicry in a fish using deep learning
2024
Deep Learning for Fisheries Acoustics
2024
Fisheries acoustics and deep learning
2024
Annotation-Free Feature Learning for Improved Acoustic Target Classification
2024
Unraveling Acoustic Signal Patterns in Fisheries Through DINO-Based Self-Supervised Learning
2023
Measuring Adversarial Robustness using a Voronoi-Epsilon Adversary
2023
A story about data extraction and deep learning applied to fishery acoustic data
2022
Artificial Intelligence methods for fisheries management
2022
An online otolith age reader using deep neural networks: Perspectives and challenges
2022
Using deep learning models to count and identify fish species from in-trawl images
2022
Exploring imaging protocols and neural network architectures for automated otolith analysis
2022
Selecting maximally informative frequency subsets for acoustic surveys
2022
A deep learning approach for individual re-identification (re-ID) of fish in the wild
2021
Combined trawl-mounted optic and acoustic methods to study the mesopelagic ecosystem
2019
Using a CNN trained on synthetic data for fish species identification
2019
Using a CNN trained on synthetic data for fish species identification
2019
The COGMAR project
2018
Drowning in data: Can deep learning approaches be the solution?
2016
Big Data og Big Analysis - hvordan drikke fra brannslangen
2015
Insitute of Marine Research - a research and advisory institute
2013
Identifying diagnostic SNPs in the presence of sequencing errors
2013
Can Software Transactional Memory make concurrent programs simple and safe?
2012
Attempts to induce sterility in Atlantic salmon by morfolino and zink finger techniques
2012
Transcriptomic analysis of the salmon louse
2012
The Salmon Louse Genome Project
2011
Maternal 3'UTRs: from egg to onset of zygotic transcription in Atlantic cod
2009
Using Bloom Filters for Large Scale Gene Sequence Analysis in Haskell
2002
A Fast Algorithm for EST Clustering using Suffix Trees
Poster
2023
Escaping the black box: explicit annotation of otolith growth rings with deep learning
2023
Annotating Otoliths with a Deep Generative Model
2020
Automatic interpretation of salmon scales using deep learning
2019
Otoliths as life history indicators
2017
Automatisk klassifisering av svømming i not
2013
A data storage strategy for generic, heterogenous scientific data
Rapporter og avhandlinger
2023
On the Significance of Distance in Machine Learning
2023
Object Tracking Approach for Catch Estimation on Trawl Surveys
2022
Selecting Maximally Informative Frequency Subsets for Acoustic Surveys
2021
Fisheries acoustics and Acoustic Target Classification - Report from the COGMAR/CRIMAC workshop on machine learning methods in fisheries acoustics
2020
Big Data in Marine Science
2019
WORKING GROUP ON MACHINE LEARNING IN MARINE SCIENCE (WGMLEARN)
2019
Machine learning to improve marine science for the sustainability of living ocean resources: Report from the 2019 Norway - U.S. Workshop
2018
Report of the Workshop on Machine Learning in Marine Science (WKMLEARN)
2005
Algorithms for the Analysis of Expressed Sequence Tags
Er denne profilen din? Rediger denne profilen (logg inn)