LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 128

Search options

  1. Article: [Vaccination in Workplace and Compensation for Adverse Events - In the Pandemic of COVID-19 - (Corrigendum)].

    Suemitsu, Tatsunori / Miyazaki, Shogo / Sato, Kazuto / Hashimoto, Yutaro

    Journal of UOEH

    2023  Volume 45, Issue 2, Page(s) 141

    MeSH term(s) Humans ; Pandemics/prevention & control ; COVID-19/prevention & control ; Working Conditions ; Workplace ; Vaccination
    Language Japanese
    Publishing date 2023-05-23
    Publishing country Japan
    Document type Journal Article ; Published Erratum
    ZDB-ID 632724-2
    ISSN 2187-2864 ; 0387-821X
    ISSN (online) 2187-2864
    ISSN 0387-821X
    DOI 10.7888/juoeh.45.141
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  2. Article ; Online: Correction to: Asthma and Chronic Obstructive Pulmonary Disease Overlap According to the Japanese Respiratory Society Diagnostic Criteria: The Prospective, Observational ACO Japan Cohort Study.

    Hashimoto, Shu / Sorimachi, Ryoko / Jinnai, Tatsunori / Ichinose, Masakazu

    Advances in therapy

    2022  Volume 39, Issue 2, Page(s) 1096–1099

    Language English
    Publishing date 2022-01-06
    Publishing country United States
    Document type Published Erratum
    ZDB-ID 632651-1
    ISSN 1865-8652 ; 0741-238X
    ISSN (online) 1865-8652
    ISSN 0741-238X
    DOI 10.1007/s12325-021-01968-4
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  3. Book ; Online: Likelihood-Based Diffusion Language Models

    Gulrajani, Ishaan / Hashimoto, Tatsunori B.

    2023  

    Abstract: Despite a growing interest in diffusion-based language models, existing work has not shown that these models can attain nontrivial likelihoods on standard language modeling benchmarks. In this work, we take the first steps towards closing the likelihood ... ...

    Abstract Despite a growing interest in diffusion-based language models, existing work has not shown that these models can attain nontrivial likelihoods on standard language modeling benchmarks. In this work, we take the first steps towards closing the likelihood gap between autoregressive and diffusion-based language models, with the goal of building and releasing a diffusion model which outperforms a small but widely-known autoregressive model. We pursue this goal through algorithmic improvements, scaling laws, and increased compute. On the algorithmic front, we introduce several methodological improvements for the maximum-likelihood training of diffusion language models. We then study scaling laws for our diffusion models and find compute-optimal training regimes which differ substantially from autoregressive models. Using our methods and scaling analysis, we train and release Plaid 1B, a large diffusion language model which outperforms GPT-2 124M in likelihood on benchmark datasets and generates fluent samples in unconditional and zero-shot control settings.
    Keywords Computer Science - Computation and Language ; Computer Science - Machine Learning
    Publishing date 2023-05-30
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  4. Article: [Vaccination in Workplace and Compensation for Adverse Events].

    Suemitsu, Tatsunori / Miyazaki, Shogo / Sato, Kazuto / Hashimoto, Yutaro

    Journal of UOEH

    2022  Volume 44, Issue 2, Page(s) 177–184

    Abstract: Several types of SARS-Cov-2 vaccine have been quickly developed and officially approved for emergency use in accordance with the Pharmaceutical Act. Mass vaccination in workplaces in Japan was subsequently promoted, targeting health care workers and ... ...

    Abstract Several types of SARS-Cov-2 vaccine have been quickly developed and officially approved for emergency use in accordance with the Pharmaceutical Act. Mass vaccination in workplaces in Japan was subsequently promoted, targeting health care workers and senior citizens. We overviewed the pathophysiology of COVID-19 and reviewed reports containing fatal outcomes, compensation programs, and remedial measures for health damage after vaccinations, in relation to their relevant legislations. The Immunization Act was amended prior to the mass vaccination to authorize the indemnity agreement between the government and pharmaceutical companies to compensate for losses based on health damages after vaccination. Pursuant to the Civil Code and the State Redress Act, employers reserve the right to obtain reimbursement when they are liable to pay compensation for damages inflicted on a third party. There are no provisions to exclude healthcare workers and occupational health staff who participated in practical procedures from lawsuits and liability. We propose legislative reformation and careful contracts with responsible organizations concerned with emergency vaccinations in order to confront forthcoming new or re-emerging infections beyond this pandemic.
    MeSH term(s) COVID-19/prevention & control ; COVID-19 Vaccines/administration & dosage ; COVID-19 Vaccines/adverse effects ; Humans ; Japan ; Vaccination/adverse effects ; Vaccination/legislation & jurisprudence ; Workers' Compensation ; Workplace
    Chemical Substances COVID-19 Vaccines
    Language Japanese
    Publishing date 2022-06-03
    Publishing country Japan
    Document type Journal Article
    ZDB-ID 632724-2
    ISSN 2187-2864 ; 0387-821X
    ISSN (online) 2187-2864
    ISSN 0387-821X
    DOI 10.7888/juoeh.44.177
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  5. Book ; Online: Benchmarking Multi-Domain Active Learning on Image Classification

    Li, Jiayi / Taori, Rohan / Hashimoto, Tatsunori B.

    2023  

    Abstract: Active learning aims to enhance model performance by strategically labeling informative data points. While extensively studied, its effectiveness on large-scale, real-world datasets remains underexplored. Existing research primarily focuses on single- ... ...

    Abstract Active learning aims to enhance model performance by strategically labeling informative data points. While extensively studied, its effectiveness on large-scale, real-world datasets remains underexplored. Existing research primarily focuses on single-source data, ignoring the multi-domain nature of real-world data. We introduce a multi-domain active learning benchmark to bridge this gap. Our benchmark demonstrates that traditional single-domain active learning strategies are often less effective than random selection in multi-domain scenarios. We also introduce CLIP-GeoYFCC, a novel large-scale image dataset built around geographical domains, in contrast to existing genre-based domain datasets. Analysis on our benchmark shows that all multi-domain strategies exhibit significant tradeoffs, with no strategy outperforming across all datasets or all metrics, emphasizing the need for future research.
    Keywords Computer Science - Machine Learning ; Computer Science - Computer Vision and Pattern Recognition
    Publishing date 2023-12-01
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  6. Book ; Online: Evaluating Self-Supervised Learning via Risk Decomposition

    Dubois, Yann / Hashimoto, Tatsunori / Liang, Percy

    2023  

    Abstract: Self-supervised learning (SSL) pipelines differ in many design choices such as the architecture, augmentations, or pretraining data. Yet SSL is typically evaluated using a single metric: linear probing on ImageNet. This does not provide much insight into ...

    Abstract Self-supervised learning (SSL) pipelines differ in many design choices such as the architecture, augmentations, or pretraining data. Yet SSL is typically evaluated using a single metric: linear probing on ImageNet. This does not provide much insight into why or when a model is better, now how to improve it. To address this, we propose an SSL risk decomposition, which generalizes the classical supervised approximation-estimation decomposition by considering errors arising from the representation learning step. Our decomposition consists of four error components: approximation, representation usability, probe generalization, and encoder generalization. We provide efficient estimators for each component and use them to analyze the effect of 30 design choices on 169 SSL vision models evaluated on ImageNet. Our analysis gives valuable insights for designing and using SSL models. For example, it highlights the main sources of error and shows how to improve SSL in specific settings (full- vs few-shot) by trading off error components. All results and pretrained models are at https://github.com/YannDubs/SSL-Risk-Decomposition.

    Comment: Oral at ICML 2023
    Keywords Computer Science - Machine Learning ; Computer Science - Artificial Intelligence ; Statistics - Machine Learning
    Subject code 006
    Publishing date 2023-02-06
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  7. Book ; Online: Stochastic Amortization

    Covert, Ian / Kim, Chanwoo / Lee, Su-In / Zou, James / Hashimoto, Tatsunori

    A Unified Approach to Accelerate Feature and Data Attribution

    2024  

    Abstract: Many tasks in explainable machine learning, such as data valuation and feature attribution, perform expensive computation for each data point and can be intractable for large datasets. These methods require efficient approximations, and learning a ... ...

    Abstract Many tasks in explainable machine learning, such as data valuation and feature attribution, perform expensive computation for each data point and can be intractable for large datasets. These methods require efficient approximations, and learning a network that directly predicts the desired output, which is commonly known as amortization, is a promising solution. However, training such models with exact labels is often intractable; we therefore explore training with noisy labels and find that this is inexpensive and surprisingly effective. Through theoretical analysis of the label noise and experiments with various models and datasets, we show that this approach significantly accelerates several feature attribution and data valuation methods, often yielding an order of magnitude speedup over existing approaches.
    Keywords Computer Science - Machine Learning
    Publishing date 2024-01-28
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  8. Book ; Online: Robust Distortion-free Watermarks for Language Models

    Kuditipudi, Rohith / Thickstun, John / Hashimoto, Tatsunori / Liang, Percy

    2023  

    Abstract: We propose a methodology for planting watermarks in text from an autoregressive language model that are robust to perturbations without changing the distribution over text up to a certain maximum generation budget. We generate watermarked text by mapping ...

    Abstract We propose a methodology for planting watermarks in text from an autoregressive language model that are robust to perturbations without changing the distribution over text up to a certain maximum generation budget. We generate watermarked text by mapping a sequence of random numbers -- which we compute using a randomized watermark key -- to a sample from the language model. To detect watermarked text, any party who knows the key can align the text to the random number sequence. We instantiate our watermark methodology with two sampling schemes: inverse transform sampling and exponential minimum sampling. We apply these watermarks to three language models -- OPT-1.3B, LLaMA-7B and Alpaca-7B -- to experimentally validate their statistical power and robustness to various paraphrasing attacks. Notably, for both the OPT-1.3B and LLaMA-7B models, we find we can reliably detect watermarked text ($p \leq 0.01$) from $35$ tokens even after corrupting between $40$-$50\%$ of the tokens via random edits (i.e., substitutions, insertions or deletions). For the Alpaca-7B model, we conduct a case study on the feasibility of watermarking responses to typical user instructions. Due to the lower entropy of the responses, detection is more difficult: around $25\%$ of the responses -- whose median length is around $100$ tokens -- are detectable with $p \leq 0.01$, and the watermark is also less robust to certain automated paraphrasing attacks we implement.
    Keywords Computer Science - Machine Learning ; Computer Science - Computation and Language ; Computer Science - Cryptography and Security
    Subject code 410
    Publishing date 2023-07-28
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  9. Book ; Online: One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention

    Mahankali, Arvind / Hashimoto, Tatsunori B. / Ma, Tengyu

    2023  

    Abstract: Recent works have empirically analyzed in-context learning and shown that transformers trained on synthetic linear regression tasks can learn to implement ridge regression, which is the Bayes-optimal predictor, given sufficient capacity [Aky\"urek et al., ...

    Abstract Recent works have empirically analyzed in-context learning and shown that transformers trained on synthetic linear regression tasks can learn to implement ridge regression, which is the Bayes-optimal predictor, given sufficient capacity [Aky\"urek et al., 2023], while one-layer transformers with linear self-attention and no MLP layer will learn to implement one step of gradient descent (GD) on a least-squares linear regression objective [von Oswald et al., 2022]. However, the theory behind these observations remains poorly understood. We theoretically study transformers with a single layer of linear self-attention, trained on synthetic noisy linear regression data. First, we mathematically show that when the covariates are drawn from a standard Gaussian distribution, the one-layer transformer which minimizes the pre-training loss will implement a single step of GD on the least-squares linear regression objective. Then, we find that changing the distribution of the covariates and weight vector to a non-isotropic Gaussian distribution has a strong impact on the learned algorithm: the global minimizer of the pre-training loss now implements a single step of $\textit{pre-conditioned}$ GD. However, if only the distribution of the responses is changed, then this does not have a large effect on the learned algorithm: even when the response comes from a more general family of $\textit{nonlinear}$ functions, the global minimizer of the pre-training loss still implements a single step of GD on a least-squares linear regression objective.
    Keywords Computer Science - Machine Learning
    Subject code 519
    Publishing date 2023-07-07
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  10. Book ; Online: Navigating the Grey Area

    Zhou, Kaitlyn / Jurafsky, Dan / Hashimoto, Tatsunori

    How Expressions of Uncertainty and Overconfidence Affect Language Models

    2023  

    Abstract: The increased deployment of LMs for real-world tasks involving knowledge and facts makes it important to understand model epistemology: what LMs think they know, and how their attitudes toward that knowledge are affected by language use in their inputs. ... ...

    Abstract The increased deployment of LMs for real-world tasks involving knowledge and facts makes it important to understand model epistemology: what LMs think they know, and how their attitudes toward that knowledge are affected by language use in their inputs. Here, we study an aspect of model epistemology: how epistemic markers of certainty, uncertainty, or evidentiality like "I'm sure it's", "I think it's", or "Wikipedia says it's" affect models, and whether they contribute to model failures. We develop a typology of epistemic markers and inject 50 markers into prompts for question answering. We find that LMs are highly sensitive to epistemic markers in prompts, with accuracies varying more than 80%. Surprisingly, we find that expressions of high certainty result in a 7% decrease in accuracy as compared to low certainty expressions; similarly, factive verbs hurt performance, while evidentials benefit performance. Our analysis of a popular pretraining dataset shows that these markers of uncertainty are associated with answers on question-answering websites, while markers of certainty are associated with questions. These associations may suggest that the behavior of LMs is based on mimicking observed language use, rather than truly reflecting epistemic uncertainty.

    Comment: EMNLP 2023 (Oral)
    Keywords Computer Science - Computation and Language ; Computer Science - Artificial Intelligence
    Subject code 400
    Publishing date 2023-02-26
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

To top