Hyper Parameter Optimization of CRNN for Printed Devanagari Script Recognition using Taguchi's Method

Article Computer Science, Interdisciplinary Applications

A Statistical Design of Experiments Approach to Machine Learning Model Selection in Engineering Applications

T. Munger et al.

Summary: An important issue in machine learning is model selection for engineering applications, where external parameters such as feature engineering can significantly impact model performance. This article introduces a statistical design of experiment approach, based on the Taguchi method, to efficiently explore the experimental space and optimize model selection for real-world problems.

JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINEERING (2021)

Add to Collection

Article Instruments & Instrumentation

Hyperparameter Optimization of Deep Learning Networks for Classification of Breast Histopathology Images

Cheng-Jian Lin et al.

Summary: A novel method of hyperparameter optimization of deep learning networks was proposed to classify breast tumors as malignant or benign, showing a high accuracy rate of 83.19% in the experimental results. This method can aid in the success of early breast cancer treatment.

SENSORS AND MATERIALS (2021)

Add to Collection

Article Engineering, Multidisciplinary

Multi-task learning for pre-processing of printed Devanagari document images with hyper-parameter optimization of the deep architecture using Taguchi method

Shaheera Saba Mohd Naseem Akhter et al.

Summary: The study introduces a transfer learning-based multi-task deep learning architecture for preprocessing Devanagari document images, which can simultaneously handle three preprocessing tasks and outperforms traditional image processing methods, demonstrating excellent performance in experiments.

SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES (2021)

Add to Collection

Article Computer Science, Artificial Intelligence