LIVIVO - Search results -

Search results

Result 1 - 10 of total 11

Search options

Book ; Online ; Thesis: Prospektive Studie zur Validierung eines computergestützten Auswerteprogramms bei der Diagnostik des Schildwächterlymphknotens mittels fusionierter SPECT/CT - Bildgebung beim Prostatakarzinom

Loh, Charlotte [Verfasser]

2018

Author's details	Charlotte Loh
Keywords	Medizin, Gesundheit ; Medicine, Health
Subject code	sg610
Language	German
Publisher	Universitätsbibliothek Kiel
Publishing place	Kiel
Document type	Book ; Online ; Thesis
Database	Digital theses on the web

Full text online

Full text

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.

Article ; Online: Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science.

Loh, Charlotte / Christensen, Thomas / Dangovski, Rumen / Kim, Samuel / Soljačić, Marin

Nature communications

2022 Volume 13, Issue 1, Page(s) 4223

Abstract: Deep learning techniques have been increasingly applied to the natural sciences, e.g., for property prediction and optimization or material discovery. A fundamental ingredient of such approaches is the vast quantity of labeled data needed to train the ... ...

Abstract	Deep learning techniques have been increasingly applied to the natural sciences, e.g., for property prediction and optimization or material discovery. A fundamental ingredient of such approaches is the vast quantity of labeled data needed to train the model. This poses severe challenges in data-scarce settings where obtaining labels requires substantial computational or labor resources. Noting that problems in natural sciences often benefit from easily obtainable auxiliary information sources, we introduce surrogate- and invariance-boosted contrastive learning (SIB-CL), a deep learning framework which incorporates three inexpensive and easily obtainable auxiliary information sources to overcome data scarcity. Specifically, these are: abundant unlabeled data, prior knowledge of symmetries or invariances, and surrogate data obtained at near-zero cost. We demonstrate SIB-CL's effectiveness and generality on various scientific problems, e.g., predicting the density-of-states of 2D photonic crystals and solving the 3D time-independent Schrödinger equation. SIB-CL consistently results in orders of magnitude reduction in the number of labels needed to achieve the same network accuracies.
Language	English
Publishing date	2022-07-21
Publishing country	England
Document type	Journal Article
ZDB-ID	2553671-0
ISSN	2041-1723 ; 2041-1723
ISSN (online)	2041-1723
ISSN	2041-1723
DOI	10.1038/s41467-022-31915-y
Database	MEDical Literature Analysis and Retrieval System OnLINE

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.

Article ; Online: Inflammatory Myositis Secondary to Anti-Retroviral Therapy in a Child; Case Report and Review of the Literature.

Monaghan, Marie / Loh, Charlotte / Jones, Stephen / Oware, Agyepong / Urankar, Kathryn / Roderick, Marion / Majumdar, Anirban

Journal of neuromuscular diseases

2021 Volume 8, Issue 6, Page(s) 1089–1095

Abstract: Here, we describe a five year old girl with congenital HIV who had a six-week onset of rapidly deteriorating mobility and progressive proximal muscle weakness, associated with a raised Creatine Kinase (CK) level of 4330 U/L [25-200 U/L], subsequently ... ...

Abstract	Here, we describe a five year old girl with congenital HIV who had a six-week onset of rapidly deteriorating mobility and progressive proximal muscle weakness, associated with a raised Creatine Kinase (CK) level of 4330 U/L [25-200 U/L], subsequently diagnosed with an inflammatory myositis. Potential causes were investigated by paediatric neurology and immunology teams. Her viral load had been undetectable over the preceding two years, excluding a primary HIV myositis. While MRI scanning did not show evidence of definite myositis, a muscle biopsy showed evidence of an inflammatory process, comprising a moderate endomysial, perimysial and perivascular mononuclear (CD8 + T cell) infiltrate with increased MHC expression. No particular features of dermatomyositis or immune-mediated necrotising myopathy were identified and there were no features of an inclusion body myositis.Given the absence of active HIV infection, the role of anti-retroviral medications was considered. She had had a recent switch in medication, from twice daily Raltegravir (an Integrase Strand Transfer Inhibitor, INSTI) to once daily Dolutegravir (an INSTI) while continuing on an established daily protocol of Abacavir and Lamivudine (Nucleoside Reverse Transcriptase Inhibitors). Changing the Dolutegravir back to Raltegravir, in combination with continuing Lamivudine and Abacavir for two months made no difference to her weakness or CK levels. Moreover, this drug regimen had been well-tolerated over the preceding 19 month period. Changing the anti-retroviral regime completely to a single drug class (Protease Inhibitors) of Ritonavir and Darunavir, resulted in a dramatic improvement in her symptomatology. Within ten days she regained the ability to stand and walk, with a reduction in her CK from 1700 U/L at time of switch to 403 U/L [25-200]. This case highlights the potential risk of developing inflammatory myositis from anti-retrovirals even 19 months into treatment.
MeSH term(s)	Anti-Retroviral Agents/adverse effects ; Antiretroviral Therapy, Highly Active/adverse effects ; Child, Preschool ; Female ; HIV Infections/drug therapy ; Humans ; Lamivudine/adverse effects ; Myositis/etiology ; Raltegravir Potassium/adverse effects ; Viral Load
Chemical Substances	Anti-Retroviral Agents ; Lamivudine (2T8Q726O95) ; Raltegravir Potassium (43Y000U234)
Language	English
Publishing date	2021-06-20
Publishing country	Netherlands
Document type	Case Reports ; Journal Article ; Review
ISSN	2214-3602
ISSN (online)	2214-3602
DOI	10.3233/JND-210669
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

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.

Article ; Online: Diabetic ketoacidosis in pediatric patients with type 1- and type 2 diabetes during the COVID-19 pandemic.

Loh, Charlotte / Weihe, Paul / Kuplin, Nicole / Placzek, Kerstin / Weihrauch-Blüher, Susann

Metabolism: clinical and experimental

2021 Volume 122, Page(s) 154842

Abstract: Background: COVID-19 pandemic caused families to stay home and cancel everyday activities. Hospital admissions decreased, affecting changes in diagnoses and management of chronic disease in children.: Aims: We analyzed how the first lockdown ... ...

Abstract	Background: COVID-19 pandemic caused families to stay home and cancel everyday activities. Hospital admissions decreased, affecting changes in diagnoses and management of chronic disease in children. Aims: We analyzed how the first lockdown influenced clinical presentation and manifestation of children with diabetes mellitus (DM) in a German University Hospital. Methods: During March 15th and October 11th 2020, data on general patient information, clinical symptoms and on lab results related to diabetic ketoacidosis (DKA) were analyzed in children (0-18 years) who presented with new onset of DM or poor metabolic control of known DM. All data including frequency and severity of DKA were compared to data from patients who presented in 2019. Results: Data from 125 participants with DM were evaluated (2020: n = 52; 2019: n = 73). In 2020, twelve patients (23.1%) were diagnosed with new onset DM, two of them with type2 diabetes, and 66.7% presented with DKA including both patients T2DM. In 2019, 24.5% of patients had new onset DM, and 50% of them presented with DKA. In 2020, patients with new onset DM were younger, presented with more severe symptoms of DKA and had to stay longer in hospital compared to 2019. In 2020, six children (50%) with new onset DM were <6 years, whereas in 2019 most children with new onset DM were adolescents (n = 7, 38.9%). Conclusion: COVID-19 lockdown aggravated complications of diabetes onset and therapy management, including severity and frequency of DKA. It underlines the need of health education for early DKA diagnosis to early identify children at risk.
MeSH term(s)	Adolescent ; Adult ; COVID-19/complications ; COVID-19/epidemiology ; Child ; Diabetes Mellitus, Type 1/complications ; Diabetes Mellitus, Type 2/complications ; Diabetic Ketoacidosis/complications ; Female ; Humans ; Male ; Pandemics ; Young Adult
Language	English
Publishing date	2021-07-30
Publishing country	United States
Document type	Journal Article
ZDB-ID	80230-x
ISSN	1532-8600 ; 0026-0495
ISSN (online)	1532-8600
ISSN	0026-0495
DOI	10.1016/j.metabol.2021.154842
Database	MEDical Literature Analysis and Retrieval System OnLINE

Full text online

Accessible to users with ZB MED library card

In stock of ZB MED Cologne/Königswinter

Uc I Zs.316: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 2021: Bestellungen von Artikeln über das Online-Bestellformular
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾

Book ; Online: Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science

Loh, Charlotte / Christensen, Thomas / Dangovski, Rumen / Kim, Samuel / Soljacic, Marin

2021

Abstract	Deep learning techniques have been increasingly applied to the natural sciences, e.g., for property prediction and optimization or material discovery. A fundamental ingredient of such approaches is the vast quantity of labelled data needed to train the model; this poses severe challenges in data-scarce settings where obtaining labels requires substantial computational or labor resources. Here, we introduce surrogate- and invariance-boosted contrastive learning (SIB-CL), a deep learning framework which incorporates three ``inexpensive'' and easily obtainable auxiliary information sources to overcome data scarcity. Specifically, these are: 1)~abundant unlabeled data, 2)~prior knowledge of symmetries or invariances and 3)~surrogate data obtained at near-zero cost. We demonstrate SIB-CL's effectiveness and generality on various scientific problems, e.g., predicting the density-of-states of 2D photonic crystals and solving the 3D time-independent Schrodinger equation. SIB-CL consistently results in orders of magnitude reduction in the number of labels needed to achieve the same network accuracies. Comment: 21 pages, 10 figures
Keywords	Computer Science - Machine Learning ; Condensed Matter - Materials Science ; Physics - Applied Physics ; Physics - Optics
Subject code	006
Publishing date	2021-10-15
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

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.

Book ; Online: Multi-Symmetry Ensembles

Loh, Charlotte / Han, Seungwook / Sudalairaj, Shivchander / Dangovski, Rumen / Xu, Kai / Wenzel, Florian / Soljacic, Marin / Srivastava, Akash

Improving Diversity and Generalization via Opposing Symmetries

2023

Abstract: Deep ensembles (DE) have been successful in improving model performance by learning diverse members via the stochasticity of random initialization. While recent works have attempted to promote further diversity in DE via hyperparameters or regularizing ... ...

Abstract	Deep ensembles (DE) have been successful in improving model performance by learning diverse members via the stochasticity of random initialization. While recent works have attempted to promote further diversity in DE via hyperparameters or regularizing loss functions, these methods primarily still rely on a stochastic approach to explore the hypothesis space. In this work, we present Multi-Symmetry Ensembles (MSE), a framework for constructing diverse ensembles by capturing the multiplicity of hypotheses along symmetry axes, which explore the hypothesis space beyond stochastic perturbations of model weights and hyperparameters. We leverage recent advances in contrastive representation learning to create models that separately capture opposing hypotheses of invariant and equivariant functional classes and present a simple ensembling approach to efficiently combine appropriate hypotheses for a given task. We show that MSE effectively captures the multiplicity of conflicting hypotheses that is often required in large, diverse datasets like ImageNet. As a result of their inherent diversity, MSE improves classification performance, uncertainty quantification, and generalization across a series of transfer tasks. Comment: Camera Ready Revision. ICML 2023
Keywords	Computer Science - Machine Learning ; Computer Science - Artificial Intelligence ; Computer Science - Computer Vision and Pattern Recognition
Subject code	006
Publishing date	2023-03-04
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

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.

Book ; Online: Multimodal Learning for Crystalline Materials

Moro, Viggo / Loh, Charlotte / Dangovski, Rumen / Ghorashi, Ali / Ma, Andrew / Chen, Zhuo / Lu, Peter Y. / Christensen, Thomas / Soljačić, Marin

2023

Abstract: Artificial intelligence (AI) has revolutionized the field of materials science by improving the prediction of properties and accelerating the discovery of novel materials. In recent years, publicly available material data repositories containing data for ...

Abstract	Artificial intelligence (AI) has revolutionized the field of materials science by improving the prediction of properties and accelerating the discovery of novel materials. In recent years, publicly available material data repositories containing data for various material properties have grown rapidly. In this work, we introduce Multimodal Learning for Crystalline Materials (MLCM), a new method for training a foundation model for crystalline materials via multimodal alignment, where high-dimensional material properties (i.e. modalities) are connected in a shared latent space to produce highly useful material representations. We show the utility of MLCM on multiple axes: (i) MLCM achieves state-of-the-art performance for material property prediction on the challenging Materials Project database; (ii) MLCM enables a novel, highly accurate method for inverse design, allowing one to screen for stable material with desired properties; and (iii) MLCM allows the extraction of interpretable emergent features that may provide insight to material scientists. Further, we explore several novel methods for aligning an arbitrary number of modalities, improving upon prior art in multimodal learning that focuses on bimodal alignment. Our work brings innovations from the ongoing AI revolution into the domain of materials science and identifies materials as a testbed for the next generation of AI. Comment: 11 pages, 3 figures
Keywords	Computer Science - Machine Learning ; Condensed Matter - Materials Science
Subject code	670
Publishing date	2023-11-30
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

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.

Book ; Online: Deep Learning for Bayesian Optimization of Scientific Problems with High-Dimensional Structure

Kim, Samuel / Lu, Peter Y. / Loh, Charlotte / Smith, Jamie / Snoek, Jasper / Soljačić, Marin

2021

Abstract: Bayesian optimization (BO) is a popular paradigm for global optimization of expensive black-box functions, but there are many domains where the function is not completely a black-box. The data may have some known structure (e.g. symmetries) and/or the ... ...

Abstract	Bayesian optimization (BO) is a popular paradigm for global optimization of expensive black-box functions, but there are many domains where the function is not completely a black-box. The data may have some known structure (e.g. symmetries) and/or the data generation process may be a composite process that yields useful intermediate or auxiliary information in addition to the value of the optimization objective. However, surrogate models traditionally employed in BO, such as Gaussian Processes (GPs), scale poorly with dataset size and do not easily accommodate known structure. Instead, we use Bayesian neural networks, a class of scalable and flexible surrogate models with inductive biases, to extend BO to complex, structured problems with high dimensionality. We demonstrate BO on a number of realistic problems in physics and chemistry, including topology optimization of photonic crystal materials using convolutional neural networks, and chemical property optimization of molecules using graph neural networks. On these complex tasks, we show that neural networks often outperform GPs as surrogate models for BO in terms of both sampling efficiency and computational cost. Comment: 32 pages, 16 figures; published in TMLR
Keywords	Computer Science - Machine Learning ; Physics - Applied Physics ; Physics - Chemical Physics ; Physics - Computational Physics ; Physics - Optics
Subject code	006
Publishing date	2021-04-23
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

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.

Book ; Online: Constructive Assimilation

Han, Ligong / Han, Seungwook / Sudalairaj, Shivchander / Loh, Charlotte / Dangovski, Rumen / Deng, Fei / Agrawal, Pulkit / Metaxas, Dimitris / Karlinsky, Leonid / Weng, Tsui-Wei / Srivastava, Akash

Boosting Contrastive Learning Performance through View Generation Strategies

2023

Abstract: Transformations based on domain expertise (expert transformations), such as random-resized-crop and color-jitter, have proven critical to the success of contrastive learning techniques such as SimCLR. Recently, several attempts have been made to replace ... ...

Abstract	Transformations based on domain expertise (expert transformations), such as random-resized-crop and color-jitter, have proven critical to the success of contrastive learning techniques such as SimCLR. Recently, several attempts have been made to replace such domain-specific, human-designed transformations with generated views that are learned. However for imagery data, so far none of these view-generation methods has been able to outperform expert transformations. In this work, we tackle a different question: instead of replacing expert transformations with generated views, can we constructively assimilate generated views with expert transformations? We answer this question in the affirmative and propose a view generation method and a simple, effective assimilation method that together improve the state-of-the-art by up to ~3.6% on three different datasets. Importantly, we conduct a detailed empirical study that systematically analyzes a range of view generation and assimilation methods and provides a holistic picture of the efficacy of learned views in contrastive representation learning. Comment: Accepted at Generative Models for Computer Vision Workshop 2023
Keywords	Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Machine Learning
Subject code	004
Publishing date	2023-04-02
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

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.

Book ; Online: Equivariant Contrastive Learning

Dangovski, Rumen / Jing, Li / Loh, Charlotte / Han, Seungwook / Srivastava, Akash / Cheung, Brian / Agrawal, Pulkit / Soljačić, Marin

2021

Abstract: In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge. In fact, the property of invariance is a ... ...

Abstract	In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge. In fact, the property of invariance is a trivial instance of a broader class called equivariance, which can be intuitively understood as the property that representations transform according to the way the inputs transform. Here, we show that rather than using only invariance, pre-training that encourages non-trivial equivariance to some transformations, while maintaining invariance to other transformations, can be used to improve the semantic quality of representations. Specifically, we extend popular SSL methods to a more general framework which we name Equivariant Self-Supervised Learning (E-SSL). In E-SSL, a simple additional pre-training objective encourages equivariance by predicting the transformations applied to the input. We demonstrate E-SSL's effectiveness empirically on several popular computer vision benchmarks, e.g. improving SimCLR to 72.5% linear probe accuracy on ImageNet. Furthermore, we demonstrate usefulness of E-SSL for applications beyond computer vision; in particular, we show its utility on regression problems in photonics science. Our code, datasets and pre-trained models are available at https://github.com/rdangovs/essl to aid further research in E-SSL. Comment: Camera Ready Revision. ICLR 2022. Discussion: https://openreview.net/forum?id=gKLAAfiytI Code: https://github.com/rdangovs/essl
Keywords	Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Machine Learning ; Electrical Engineering and Systems Science - Image and Video Processing ; Physics - Applied Physics
Subject code	006
Publishing date	2021-10-28
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

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

Full text online

More links

Kategorien

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

Full text online

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED