Hyperparameter Selection

Dernoncourt, Franck; Nemati, Shamim; Kassis, Elias Baedorf; Ghassemi, Mohammad M.

doi:10.1007/978-3-319-43742-2_29

Cited by 9 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML models are often considered a black box that are difficult to interpret how the model arrives at its prediction 42 . Since the goal of this paper is not only to study the risk factors associated with mortality but also to compare the outputs of the two modeling techniques, the ML model was not optimized for performance using hyperparameter tuning and this could yield further improvements 43 . If fully optimized and implemented in clinical practice, ML models could provide a suitable method to help identify a patient's prognosis and drive pre‐emptive interventions and/or care planning efforts.…”

Section: Discussionmentioning

confidence: 99%

“… 42 Since the goal of this paper is not only to study the risk factors associated with mortality but also to compare the outputs of the two modeling techniques, the ML model was not optimized for performance using hyperparameter tuning and this could yield further improvements. 43 If fully optimized and implemented in clinical practice, ML models could provide a suitable method to help identify a patient's prognosis and drive pre‐emptive interventions and/or care planning efforts. Additionally, MONDO database is undergoing an update with most recent data and additional data points being captured.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting mortality risk in dialysis: Assessment of risk factors using traditional and advanced modeling techniques within the Monitoring Dialysis Outcomes initiative

Chaudhuri

Larkin

Guedes

et al. 2022

Hemodialysis International

View full text Add to dashboard Cite

Introduction: Several factors affect the survival of End Stage Kidney Disease (ESKD) patients on dialysis. Machine learning (ML) models may help tackle multivariable and complex, often non-linear predictors of adverse clinical events in ESKD patients. In this study, we used advanced ML method as well as a traditional statistical method to develop and compare the risk factors for mortality prediction model in hemodialysis (HD) patients. Materials and Methods: We included data HD patients who had data across a baseline period of at least 1 year and 1 day in the internationally representative Monitoring Dialysis Outcomes (MONDO) Initiative dataset. Twenty-three input parameters considered in the model were chosen in an a priori manner. The prediction model used 1 year baseline data to predict death in the following 3 years. The dataset was randomly split into 80% training data and 20% testing data for model development. Two different modeling techniques were used to build the mortality prediction model. Findings: A total of 95,142 patients were included in the analysis sample. The area under the receiver operating curve (AUROC) of the model on the test data with XGBoost ML model was 0.84 on the training data and 0.80 on the test data. AUROC of the logistic regression model was 0.73 on training data and 0.75 on test data. Four out of the top five predictors were common to both modeling strategies.Discussion: In the internationally representative MONDO data for HD patients, we describe the development of a ML model and a traditional statistical model that was suitable for classification of a prevalent HD patient's 3-year risk of death. While both models had a reasonably high AUROC, the ML model was able to identify levels of hematocrit (HCT) as an important risk factor in mortality. If implemented in clinical practice, such proof-of-concept models could be used to provide pre-emptive care for HD patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Predicting mortality risk in dialysis: Assessment of risk factors using traditional and advanced modeling techniques within the Monitoring Dialysis Outcomes initiative

Chaudhuri

Larkin

Guedes

et al. 2022

Hemodialysis International

View full text Add to dashboard Cite

show abstract

“…(1) Fix the number of random seeds to ensure that the model is reproducible. (2) Preset the value range of three parameters based on experience (Dernoncourt et al, 2016). (3) Iterate over the values of each parameter and save the corresponding model parameters and model accuracy.…”

Section: Bridge Temperature Prediction Based On the Lstm Modelmentioning

confidence: 99%

Bridge temperature prediction method based on long short-term memory neural networks and shared meteorological data

Zhou,

Wang,

Chen

2024

Advances in Structural Engineering

View full text Add to dashboard Cite

Temperature is an important load factor affecting the structural performances of bridges. The rapid acquisition of bridge temperature data is significant for bridge temperature effect analysis and assessment. On the bases of ground meteorological shared big data, a bridge temperature prediction method based on long short-term memory (LSTM) neural network is proposed. The proposed method is used to investigate the key issues of data preprocessing, model input feature selection, time-length determination, and hyper-parameter preference. Moreover, the proposed method relies on the maximum information coefficient to quantify the strongly correlated features and uses a two-layer deep LSTM neural network to improve the model’s time series information utilization and prediction capability. The constructed neural grid model is experimentally studied and verified based on the long-term measured data of the scaled bridge model in an outdoor environment. Comparative assessment with other typical time series models, such as NARX, RNN, and GRU, demonstrate that the LSTM neural network model exhibits the best generalization ability and highest temperature prediction accuracy, with a maximum absolute error of approximately 2°C and relative error below 5%. The engineering applicability and effectiveness of LSTM for bridge temperature prediction are verified.

show abstract

“…Recently, a more systematic approach based on Bayesian optimization with Gaussian process (GP) [16] has been shown to be effective in automatically tuning the hyperparameters of machine learning algorithms, such as latent dirichlet allocation, SVMs, convolutional neural networks [15], and deep belief networks [17], as well as tuning the hyperparameters that features may have [18,19]. In this approach, the model's performance for each hyperparameter combination is modeled as a sample from a GP, resulting in a tractable posterior distribution given previous experiments.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Optimizing neural network hyperparameters with Gaussian processes for dialog act classification

Dernoncourt¹,

Lee²

2016

2016 IEEE Spoken Language Technology Workshop (SLT)

Self Cite

View full text Add to dashboard Cite

Systems based on artificial neural networks (ANNs) have achieved state-of-the-art results in many natural language processing tasks. Although ANNs do not require manually engineered features, ANNs have many hyperparameters to be optimized. The choice of hyperparameters significantly impacts models' performances. However, the ANN hyperparameters are typically chosen by manual, grid, or random search, which either requires expert experiences or is computationally expensive. Recent approaches based on Bayesian optimization using Gaussian processes (GPs) is a more systematic way to automatically pinpoint optimal or near-optimal machine learning hyperparameters. Using a previously published ANN model yielding state-of-the-art results for dialog act classification, we demonstrate that optimizing hyperparameters using GP further improves the results, and reduces the computational time by a factor of 4 compared to a random search. Therefore it is a useful technique for tuning ANN models to yield the best performances for natural language processing tasks.

show abstract

Hyperparameter Selection

Cited by 9 publications

References 11 publications

Predicting mortality risk in dialysis: Assessment of risk factors using traditional and advanced modeling techniques within the Monitoring Dialysis Outcomes initiative

Predicting mortality risk in dialysis: Assessment of risk factors using traditional and advanced modeling techniques within the Monitoring Dialysis Outcomes initiative

Bridge temperature prediction method based on long short-term memory neural networks and shared meteorological data

Optimizing neural network hyperparameters with Gaussian processes for dialog act classification

Contact Info

Product

Resources

About