LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 140

Search options

  1. Book ; Online: Fully Variational Noise-Contrastive Estimation

    Zach, Christopher

    2023  

    Abstract: By using the underlying theory of proper scoring rules, we design a family of noise-contrastive estimation (NCE) methods that are tractable for latent variable models. Both terms in the underlying NCE loss, the one using data samples and the one using ... ...

    Abstract By using the underlying theory of proper scoring rules, we design a family of noise-contrastive estimation (NCE) methods that are tractable for latent variable models. Both terms in the underlying NCE loss, the one using data samples and the one using noise samples, can be lower-bounded as in variational Bayes, therefore we call this family of losses fully variational noise-contrastive estimation. Variational autoencoders are a particular example in this family and therefore can be also understood as separating real data from synthetic samples using an appropriate classification loss. We further discuss other instances in this family of fully variational NCE objectives and indicate differences in their empirical behavior.

    Comment: SCIA 2023, 13 pages
    Keywords Computer Science - Machine Learning ; Computer Science - Computer Vision and Pattern Recognition
    Publishing date 2023-04-04
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Article ; Online: Psychology's Stewardship of Gender/Sex.

    Schudson, Zach C

    Perspectives on psychological science : a journal of the Association for Psychological Science

    2021  Volume 16, Issue 6, Page(s) 1105–1112

    Abstract: Psychological theories of gender and/or sex (gender/sex) have the capacity to shape people's self-perceptions, social judgments, and behaviors. The institutional power of psychology to affect cognition and behavior-not just to measure them-necessitates a ...

    Abstract Psychological theories of gender and/or sex (gender/sex) have the capacity to shape people's self-perceptions, social judgments, and behaviors. The institutional power of psychology to affect cognition and behavior-not just to measure them-necessitates a serious consideration of our social responsibility to manage the products of our intellectual labor. Therefore, I propose that psychological research should be understood as
    MeSH term(s) Employment ; Humans ; Psychological Theory ; Psychology
    Language English
    Publishing date 2021-11-01
    Publishing country United States
    Document type Journal Article
    ZDB-ID 2224911-4
    ISSN 1745-6924 ; 1745-6916
    ISSN (online) 1745-6924
    ISSN 1745-6916
    DOI 10.1177/17456916211018462
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  3. Book ; Online: Bilevel Programs Meet Deep Learning

    Zach, Christopher

    A Unifying View on Inference Learning Methods

    2021  

    Abstract: In this work we unify a number of inference learning methods, that are proposed in the literature as alternative training algorithms to the ones based on regular error back-propagation. These inference learning methods were developed with very diverse ... ...

    Abstract In this work we unify a number of inference learning methods, that are proposed in the literature as alternative training algorithms to the ones based on regular error back-propagation. These inference learning methods were developed with very diverse motivations, mainly aiming to enhance the biological plausibility of deep neural networks and to improve the intrinsic parallelism of training methods. We show that these superficially very different methods can all be obtained by successively applying a particular reformulation of bilevel optimization programs. As a by-product it becomes also evident that all considered inference learning methods include back-propagation as a special case, and therefore at least approximate error back-propagation in typical settings. Finally, we propose Fenchel back-propagation, that replaces the propagation of infinitesimal corrections performed in standard back-propagation with finite targets as the learning signal. Fenchel back-propagation can therefore be seen as an instance of learning via explicit target propagation.

    Comment: 17 pages
    Keywords Computer Science - Machine Learning ; Mathematics - Optimization and Control
    Subject code 006
    Publishing date 2021-05-15
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  4. Article ; Online: Non-binary gender/sex identities.

    Schudson, Zach C / Morgenroth, Thekla

    Current opinion in psychology

    2022  Volume 48, Page(s) 101499

    Abstract: An increasing number of individuals openly identify as non-binary (i.e., not exclusively female or male). Accordingly, psychological research on non-binary identities has expanded rapidly. We review key insights from this growing literature, first ... ...

    Abstract An increasing number of individuals openly identify as non-binary (i.e., not exclusively female or male). Accordingly, psychological research on non-binary identities has expanded rapidly. We review key insights from this growing literature, first examining work that has demonstrated links between beliefs about the true nature of gender and/or sex (gender/sex) and feelings toward non-binary people. We also review research on non-binary people's self-concepts, which has shown the inadequacy of binary-focused gender/sex measurement practices for effectively studying non-binary people's lives and has suggested treating gender/sex as multidimensional. Then, we consider scholarship on non-binary people's wellbeing, including work exploring sources of joy and pleasure in non-binary people's lives (e.g., gender euphoria). Finally, we discuss recent advances in gender-inclusive theories and methods.
    MeSH term(s) Humans ; Female ; Male ; Emotions
    Language English
    Publishing date 2022-10-25
    Publishing country Netherlands
    Document type Journal Article ; Review
    ZDB-ID 2831565-0
    ISSN 2352-2518 ; 2352-250X ; 2352-250X
    ISSN (online) 2352-2518 ; 2352-250X
    ISSN 2352-250X
    DOI 10.1016/j.copsyc.2022.101499
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  5. Thesis ; Online: The Role of Methylation in Chemical Defense of Fungi against Predators

    Zach, Christina

    2018  

    Keywords info:eu-repo/classification/ddc/570 ; Life sciences
    Language English
    Publisher ETH Zurich
    Publishing country ch
    Document type Thesis ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  6. Article ; Online: Women Versus Females: Gender Essentialism in Everyday Language.

    Troncoso, Solangel C / Schudson, Zach C / Gelman, Susan A

    Journal of psycholinguistic research

    2022  Volume 52, Issue 3, Page(s) 975–995

    Abstract: How do different words referring to gender/sex categories reflect and/or shape our understanding of gender/sex concepts? The current study examined this issue by assessing how individuals use gender/sex terms (females, males, women, men). Participants ... ...

    Abstract How do different words referring to gender/sex categories reflect and/or shape our understanding of gender/sex concepts? The current study examined this issue by assessing how individuals use gender/sex terms (females, males, women, men). Participants recruited through MTurk (N = 299) completed an online survey, rating the terms on nine dimensions, completing a fill-in-the-blank task, and reporting gender essentialist beliefs. Overall, participants rated the words females/males as more biological and technical, and women/men as higher on all other dimensions (e.g., appropriate, polite, warm). Preference for females/males correlated positively with gender essentialism among women. These findings suggest that use of certain gendered terms is linked to how people conceptualize gender/sex. Future research should further explore the relation between choice of gendered terms, how language choice reflects and shapes attitudes and beliefs about gender/sex, and factors (e.g., race) that may influence this relation.
    MeSH term(s) Male ; Humans ; Female ; Gender Identity ; Language ; Surveys and Questionnaires
    Language English
    Publishing date 2022-11-09
    Publishing country United States
    Document type Journal Article
    ZDB-ID 124517-x
    ISSN 1573-6555 ; 0090-6905
    ISSN (online) 1573-6555
    ISSN 0090-6905
    DOI 10.1007/s10936-022-09917-0
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    In stock of ZB MED Cologne/Königswinter

    Zs.A 1111: Show issues Location:
    Je nach Verfügbarkeit (siehe Angabe bei Bestand)
    bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
    Jg. 1995 - 2021: Lesesall (1.OG)
    ab Jg. 2022: Lesesaal (EG)

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  7. Book ; Online: Dual Propagation

    Høier, Rasmus / Staudt, D. / Zach, Christopher

    Accelerating Contrastive Hebbian Learning with Dyadic Neurons

    2023  

    Abstract: Activity difference based learning algorithms-such as contrastive Hebbian learning and equilibrium propagation-have been proposed as biologically plausible alternatives to error back-propagation. However, on traditional digital chips these algorithms ... ...

    Abstract Activity difference based learning algorithms-such as contrastive Hebbian learning and equilibrium propagation-have been proposed as biologically plausible alternatives to error back-propagation. However, on traditional digital chips these algorithms suffer from having to solve a costly inference problem twice, making these approaches more than two orders of magnitude slower than back-propagation. In the analog realm equilibrium propagation may be promising for fast and energy efficient learning, but states still need to be inferred and stored twice. Inspired by lifted neural networks and compartmental neuron models we propose a simple energy based compartmental neuron model, termed dual propagation, in which each neuron is a dyad with two intrinsic states. At inference time these intrinsic states encode the error/activity duality through their difference and their mean respectively. The advantage of this method is that only a single inference phase is needed and that inference can be solved in layerwise closed-form. Experimentally we show on common computer vision datasets, including Imagenet32x32, that dual propagation performs equivalently to back-propagation both in terms of accuracy and runtime.

    Comment: Added reflections on biological plausibility and results comparisons to state-of-the-art versions of equilibrium propagation and difference target propagation
    Keywords Computer Science - Machine Learning
    Subject code 006
    Publishing date 2023-02-02
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  8. Article ; Online: Increased juvenile native fish abundance following a major flood in an Arizona river

    Christopher J. Jenney / Zach C. Nemec / Larissa N. Lee / Scott A. Bonar

    Journal of Freshwater Ecology, Vol 37, Iss 1, Pp 1-

    2022  Volume 14

    Abstract: Spring floods trigger spawning in many native fishes of the desert Southwest (USA), but less is known about fish community response when native fishes are rare. Here, we document change to native and nonnative fish captures and instream habitat features ... ...

    Abstract Spring floods trigger spawning in many native fishes of the desert Southwest (USA), but less is known about fish community response when native fishes are rare. Here, we document change to native and nonnative fish captures and instream habitat features following a decade-high flooding event (2019) in the Verde River (AZ) where native fish captures were rare in the years pre-flood. Using prepositioned areal electrofishing devices (PAEDs), we sampled the fish community at 90 sampling units pre-flood (2017) and resampled those same units post-flood (2019) to compare and identify changes to catch and habitat features. Relative abundance of native fishes increased from 0.6% pre-flood (0.01 fish/PAED) to 53.0% post-flood (1.66 fish/PAED) and was largely attributable to the presence of juvenile Roundtail Chub Gila robusta (≤ 70 mm total length (TL)) and juvenile Sonora Sucker Catostomus insignis (≤ 100 mm TL). Juvenile Desert Sucker Catostomus clarkii experienced a lesser increase. One adult native fish was captured in 2017 and adult native fishes were absent from 2019 sampling. The catch of adult/subadult Common Carp Cyprinus carpio (> 100 mm TL) declined; however, this could be related to reservoir management and not the flood. The abundance of all size-classes of Black Bass Micropterus spp., Red Shiner Cyprinella lutrensis and other nonnative fishes did not change. The majority (97%) of juvenile native fishes were captured at the uppermost sampling reach. A 54% reduction to canopy cover across all sampling reaches and an increase of fine sediments at the most downstream reach demonstrates how floods can restructure the river environment. This case-study adds evidence that protection of spring floods is vital to the persistence and recolonization of fishes native to the desert Southwest, especially where they are rare. The continued presence of nonnative species may preclude juvenile native fishes from recruiting to adults.
    Keywords native fish ; verde river ; roundtail chub ; desert sucker ; sonora sucker ; flooding ; nonnative species ; Environmental sciences ; GE1-350 ; Ecology ; QH540-549.5
    Subject code 333 ; 590
    Language English
    Publishing date 2022-12-01T00:00:00Z
    Publisher Taylor & Francis Group
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  9. Book ; Online: Lifted Regression/Reconstruction Networks

    Høier, Rasmus Kjær / Zach, Christopher

    2020  

    Abstract: In this work we propose lifted regression/reconstruction networks (LRRNs), which combine lifted neural networks with a guaranteed Lipschitz continuity property for the output layer. Lifted neural networks explicitly optimize an energy model to infer the ... ...

    Abstract In this work we propose lifted regression/reconstruction networks (LRRNs), which combine lifted neural networks with a guaranteed Lipschitz continuity property for the output layer. Lifted neural networks explicitly optimize an energy model to infer the unit activations and therefore---in contrast to standard feed-forward neural networks---allow bidirectional feedback between layers. So far lifted neural networks have been modelled around standard feed-forward architectures. We propose to take further advantage of the feedback property by letting the layers simultaneously perform regression and reconstruction. The resulting lifted network architecture allows to control the desired amount of Lipschitz continuity, which is an important feature to obtain adversarially robust regression and classification methods. We analyse and numerically demonstrate applications for unsupervised and supervised learning.

    Comment: 12 pages, 8 figures
    Keywords Computer Science - Machine Learning ; Computer Science - Computer Vision and Pattern Recognition
    Subject code 006
    Publishing date 2020-05-07
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  10. Book ; Online: Truncated Inference for Latent Variable Optimization Problems

    Zach, Christopher / Le, Huu

    Application to Robust Estimation and Learning

    2020  

    Abstract: Optimization problems with an auxiliary latent variable structure in addition to the main model parameters occur frequently in computer vision and machine learning. The additional latent variables make the underlying optimization task expensive, either ... ...

    Abstract Optimization problems with an auxiliary latent variable structure in addition to the main model parameters occur frequently in computer vision and machine learning. The additional latent variables make the underlying optimization task expensive, either in terms of memory (by maintaining the latent variables), or in terms of runtime (repeated exact inference of latent variables). We aim to remove the need to maintain the latent variables and propose two formally justified methods, that dynamically adapt the required accuracy of latent variable inference. These methods have applications in large scale robust estimation and in learning energy-based models from labeled data.

    Comment: 16 pages
    Keywords Computer Science - Machine Learning ; Computer Science - Computer Vision and Pattern Recognition
    Publishing date 2020-03-12
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top