Academic Journal

Results of training the same architecture on data seriated via different distance metrics, as well as using unsorted data (i.e. individuals within each population are arranged in the arbitrary order produced by the simulator), for the ghost-introgression problem (top row, panels A and B) and the Drosophila demographic model (bottom row, panels C and D).

التفاصيل البيبلوغرافية
العنوان: Results of training the same architecture on data seriated via different distance metrics, as well as using unsorted data (i.e. individuals within each population are arranged in the arbitrary order produced by the simulator), for the ghost-introgression problem (top row, panels A and B) and the Drosophila demographic model (bottom row, panels C and D).
المؤلفون: Dylan D. Ray, Lex Flagel, Daniel R. Schrider
سنة النشر: 2024
مصطلحات موضوعية: Genetics, Evolutionary Biology, Ecology, Biological Sciences not elsewhere classified, world scenarios underscores, trained neural network, much higher frequencies, insufficient — ideally, div >< p, deep neural network, deep learning approaches, deep learning algorithm, significant fitness advantage, closely related species, recovering introgressed haplotypes, image classification problem, harbor introgressed loci, region previously shown, use simulated data, population genetic alignment, identifying introgressed alleles, use =", population alignment, one species, fitness effects, correctly identifying, introgressed material, introgressed alleles, image representation, image belongs
الوصف: These plots show the values of training (A and C) and validation (B and D) loss over the course of training. Validation loss is usually lower than training in the case of Drosophila because label smoothing was applied to the training data for the purposes of regularization, but not to the validation data. (PDF)
نوع الوثيقة: article in journal/newspaper
اللغة: unknown
Relation: https://figshare.com/articles/journal_contribution/Results_of_training_the_same_architecture_on_data_seriated_via_different_distance_metrics_as_well_as_using_unsorted_data_i_e_individuals_within_each_population_are_arranged_in_the_arbitrary_order_produced_by_the_simulator_for_the_ghost-intr/25252417
DOI: 10.1371/journal.pgen.1010657.s018
الاتاحة: https://doi.org/10.1371/journal.pgen.1010657.s018
https://figshare.com/articles/journal_contribution/Results_of_training_the_same_architecture_on_data_seriated_via_different_distance_metrics_as_well_as_using_unsorted_data_i_e_individuals_within_each_population_are_arranged_in_the_arbitrary_order_produced_by_the_simulator_for_the_ghost-intr/25252417
Rights: CC BY 4.0
رقم الانضمام: edsbas.75AA648E
قاعدة البيانات: BASE
الوصف
DOI:10.1371/journal.pgen.1010657.s018