scholarly journals An Approach to Hyperparameter Optimization for the Objective Function in Machine Learning

Electronics ◽  
2019 ◽  
Vol 8 (11) ◽  
pp. 1267 ◽  
Author(s):  
Yonghoon Kim ◽  
and Mokdong Chung
Keyword(s):  
Machine Learning ◽  
Learning Process ◽  
Learning Rate ◽  
Bayesian Optimization ◽  
Learning Performance ◽  
Batch Size ◽  
Critical Problem ◽  
Hyperparameter Optimization ◽  
Training Performance ◽  
And Performance

In machine learning, performance is of great value. However, each learning process requires much time and effort in setting each parameter. The critical problem in machine learning is determining the hyperparameters, such as the learning rate, mini-batch size, and regularization coefficient. In particular, we focus on the learning rate, which is directly related to learning efficiency and performance. Bayesian optimization using a Gaussian Process is common for this purpose. In this paper, based on Bayesian optimization, we attempt to optimize the hyperparameters automatically by utilizing a Gamma distribution, instead of a Gaussian distribution, to improve the training performance of predicting image discrimination. As a result, our proposed method proves to be more reasonable and efficient in the estimation of learning rate when training the data, and can be useful in machine learning.

scholarly journals Gaze awareness and metacognitive suggestions by a pedagogical conversational agent: an experimental investigation on interventions to support collaborative learning process and performance

2020 ◽  
Vol 15 (4) ◽  
pp. 469-498 ◽  
Author(s):  
Yugo Hayashi
Keyword(s):  
Collaborative Learning ◽  
Real Time ◽  
Learning Process ◽  
Common Ground ◽  
Learning Performance ◽  
Conversational Agent ◽  
Learning Gains ◽  
Computer Supported Collaborative Learning ◽  
Collaborative Process ◽  
And Performance

AbstractResearch on collaborative learning has revealed that peer-collaboration explanation activities facilitate reflection and metacognition and that establishing common ground and successful coordination are keys to realizing effective knowledge-sharing in collaborative learning tasks. Studies on computer-supported collaborative learning have investigated how awareness tools can facilitate coordination within a group and how the use of external facilitation scripts can elicit elaborated knowledge during collaboration. However, the separate and joint effects of these tools on the nature of the collaborative process and performance have rarely been investigated. This study investigates how two facilitation methods—coordination support via learner gaze-awareness feedback and metacognitive suggestion provision via a pedagogical conversational agent (PCA)—are able to enhance the learning process and learning gains. Eighty participants, organized into dyads, were enrolled in a 2 × 2 between-subject study. The first and second factors were the presence of real-time gaze feedback (no vs. visible gaze) and that of a suggestion-providing PCA (no vs. visible agent), respectively. Two evaluation methods were used: namely, dialog analysis of the collaborative process and evaluation of learning gains. The real-time gaze feedback and PCA suggestions facilitated the coordination process, while gaze was relatively more effective in improving the learning gains. Learners in the Gaze-feedback condition achieved superior learning gains upon receiving PCA suggestions. A successful coordination/high learning performance correlation was noted solely for learners receiving visible gaze feedback and PCA suggestions simultaneously (visible gaze/visible agent). This finding has the potential to yield improved collaborative processes and learning gains through integration of these two methods as well as contributing towards design principles for collaborative-learning support systems more generally.

scholarly journals Hyperparameter Importance Analysis based on N-RReliefF Algorithm

2019 ◽  
Vol 14 (4) ◽  
pp. 557-573 ◽  
Author(s):  
Yunlei Sun ◽  
Huiquan Gong ◽  
Yucong Li ◽  
Dalin Zhang
Keyword(s):  
Machine Learning ◽  
Bayesian Optimization ◽  
Great Success ◽  
Random Forest Algorithm ◽  
Bayesian Optimization Algorithm ◽  
Svm Algorithm ◽  
Importance Analysis ◽  
Hyperparameter Selection ◽  
And Performance ◽  
Influence Degree

Hyperparameter selection has always been the key to machine learning. The Bayesian optimization algorithm has recently achieved great success, but it has certain constraints and limitations in selecting hyperparameters. In response to these constraints and limitations, this paper proposed the N-RReliefF algorithm, which can evaluate the importance of hyperparameters and the importance weights between hyperparameters. The N-RReliefF algorithm estimates the contribution of a single hyperparameter to the performance according to the influence degree of each hyperparameter on the performance and calculates the weight of importance between the hyperparameters according to the improved normalization formula. The N-RReliefF algorithm analyses the hyperparameter configuration and performance set generated by Bayesian optimization, and obtains the important hyperparameters in random forest algorithm and SVM algorithm. The experimental results verify the effectiveness of the N-RReliefF algorithm.

scholarly journals School of the Future: A Comprehensive Study on the Effectiveness of Augmented Reality as a Tool for Primary School Children’s Education

2021 ◽  
Vol 11 (11) ◽  
pp. 5277
Author(s):  
Afnan ◽  
Khan Muhammad ◽  
Noman Khan ◽  
Mi-Young Lee ◽  
Ali Imran ◽  
...  
Keyword(s):  
Augmented Reality ◽  
Primary School ◽  
Learning Process ◽  
School Level ◽  
Learning Performance ◽  
School Students ◽  
Learning Methods ◽  
English Alphabet ◽  
And Performance ◽  
Methods Of Learning

With the emerging technologies of augmented reality (AR) and virtual reality (VR), the learning process in today’s classroom is much more effective and motivational. Overlaying virtual content into the real world makes learning methods attractive and entertaining for students while performing activities. AR techniques make the learning process easy, and fun as compared to traditional methods. These methods lack focused learning and interactivity between the educational content. To make learning effective, we propose to use handheld marker-based AR technology for primary school students. We developed a set of four applications based on students’ academic course of primary school level for learning purposes of the English alphabet, decimal numbers, animals and birds, and an AR Globe for knowing about different countries around the world. These applications can be played wherever and whenever a user wants without Internet connectivity, subject to the availability of a tablet or mobile device and the required target images. These applications have performance evaluation quizzes (PEQs) for testing students’ learning progress. Our study investigates the effectiveness of AR-based learning materials in terms of learning performance, motivation, attitude, and behavior towards different methods of learning. Our activity results favor AR-based learning techniques where students’ learning motivation and performance are enhanced compared to the non-AR learning methods.

scholarly journals Efficient Automatic CASH via Rising Bandits

2020 ◽  
Vol 34 (04) ◽  
pp. 4763-4771
Author(s):  
Yang Li ◽  
Jiawei Jiang ◽  
Jinyang Gao ◽  
Yingxia Shao ◽  
Ce Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Online Algorithm ◽  
Automatic Machine ◽  
Bayesian Optimization ◽  
Algorithm Selection ◽  
Hyperparameter Optimization ◽  
Alternating Optimization ◽  
Optimization Framework ◽  
Low Efficiency ◽  
Combined Algorithm

The Combined Algorithm Selection and Hyperparameter optimization (CASH) is one of the most fundamental problems in Automatic Machine Learning (AutoML). The existing Bayesian optimization (BO) based solutions turn the CASH problem into a Hyperparameter Optimization (HPO) problem by combining the hyperparameters of all machine learning (ML) algorithms, and use BO methods to solve it. As a result, these methods suffer from the low-efficiency problem due to the huge hyperparameter space in CASH. To alleviate this issue, we propose the alternating optimization framework, where the HPO problem for each ML algorithm and the algorithm selection problem are optimized alternately. In this framework, the BO methods are used to solve the HPO problem for each ML algorithm separately, incorporating a much smaller hyperparameter space for BO methods. Furthermore, we introduce Rising Bandits, a CASH-oriented Multi-Armed Bandits (MAB) variant, to model the algorithm selection in CASH. This framework can take the advantages of both BO in solving the HPO problem with a relatively small hyperparameter space and the MABs in accelerating the algorithm selection. Moreover, we further develop an efficient online algorithm to solve the Rising Bandits with provably theoretical guarantees. The extensive experiments on 30 OpenML datasets demonstrate the superiority of the proposed approach over the competitive baselines.

Predicting Fuel Consumptions and Exhaust Gas Emissions for LNG Carriers via Machine Learning with Hyperparameter Optimization

2021 ◽  
Author(s):  
Chenxi Ji
Keyword(s):  
Machine Learning ◽  
Random Search ◽  
Bayesian Optimization ◽  
Exhaust Gas ◽  
Hyperparameter Optimization ◽  
Marine Fuel ◽  
Validation Data ◽  
Gas Emissions ◽  
Sustainable Solutions ◽  
Exhaust Gas Emissions

The prediction of marine fuel consumption and ship exhaust gas emissions are indispensable to evaluating ship sustainable performance under current shipping fuel standards. Big data with evolved machine learning techniques have been proved to be an effective way to contain uncertainties for ship activities. This work collects the latest global LNG carrier fleet with 435 data points and attempts to predict the marine fuel consumptions and ship-resulted global warming potential (GWP) gas emissions, including CO2, CH4, N2O, and black carbon aerosols. Gaussian process regression and ensemble machine learning approaches, to achieve this goal, are employed to infer the relationship between predictors (i.e., dimensional parameters, machinery parameters, and tonnage) and response variables (fuel consumptions and GWP exhaust gas emissions), providing exceptional insight into ship sustainable solutions. To improve the prediction accuracy, the hyperparameter optimization analysis via random search and Bayesian optimization is adopted to find the optimal machine learning model. The appealing results are in line with the validation data, illustrating high effectiveness and robustness of the proposed machine learning models. The procedure established in this study presents a novel approach for accelerating the research and development of sustainable shipping fuels under normal ship activities.

scholarly journals Flipped classroom: Pedagogical model necessary to improve the participation of the students during the learning process

2020 ◽  
Vol 8 (1) ◽  
Author(s):  
Ricardo-Adán Salas-Rueda
Keyword(s):  
Machine Learning ◽  
Learning Process ◽  
Flipped Classroom ◽  
Data Science ◽  
School Activities ◽  
School Year ◽  
Business Course ◽  
And Performance ◽  
Teaching Learning ◽  
The Impact

Nowadays, teachers can transform the organization and realization of school activities before, during and after the face-to-face sessions through the flipped classroom. The objective of this mixed research is to analyze the impact of the flipped classroom in the teaching-learning process on statistics considering data science and machine learning (linear regression). The sample consists of 61 students who took the Statistical Instrumentation for Business course during the 2018 school year. This research proposes the consultation of the YouTube videos before the class, performance of the collaborative exercises and use of the spreadsheet to check the results during the class and performance of the laboratory practices through the spreadsheet after the class. The results of machine learning (70%, 80% and 90% of training) indicate that the participation of the students before, during and after the class positively influences the assimilation of knowledge and development of mathematical skills about the frequencies and measures of central tendency. On the other hand, the decision tree technique identifies 6 predictive models on the use of the flipped classroom. Also, the students of the Statistical Instrumentation for Business course are motivated and satisfied to use the technological tools in the Introduction to statistics Unit. Finally, the flipped classroom allows the construction of new educational spaces and creation of creative activities before, during and after the class that favor the participation of the students during the learning process.

scholarly journals EEG-Based Tool for Prediction of University Students’ Cognitive Performance in the Classroom

2021 ◽  
Vol 11 (6) ◽  
pp. 698
Author(s):  
Mauricio A. Ramírez-Moreno ◽  
Mariana Díaz-Padilla ◽  
Karla D. Valenzuela-Gómez ◽  
Adriana Vargas-Martínez ◽  
Juan C. Tudón-Martínez ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Performance ◽  
Learning Tool ◽  
Learning Modalities ◽  
Learning Tasks ◽  
Group A ◽  
Electroencephalographic Signals ◽  
And Performance ◽  
Video Group ◽  
Machine Learning Tool

This study presents a neuroengineering-based machine learning tool developed to predict students’ performance under different learning modalities. Neuroengineering tools are used to predict the learning performance obtained through two different modalities: text and video. Electroencephalographic signals were recorded in the two groups during learning tasks, and performance was evaluated with tests. The results show the video group obtained a better performance than the text group. A correlation analysis was implemented to find the most relevant features to predict students’ performance, and to design the machine learning tool. This analysis showed a negative correlation between students’ performance and the (theta/alpha) ratio, and delta power, which are indicative of mental fatigue and drowsiness, respectively. These results indicate that users in a non-fatigued and well-rested state performed better during learning tasks. The designed tool obtained 85% precision at predicting learning performance, as well as correctly identifying the video group as the most efficient modality.

scholarly journals Do self-created metacognitive prompts promote short- and long-term effects in computer-based learning environments?

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Katharina Engelmann ◽  
Maria Bannert ◽  
Nadine Melzner
Keyword(s):  
Learning Environments ◽  
Learning Process ◽  
Learning Performance ◽  
Long Term Effects ◽  
Learning Session ◽  
Computer Based Learning ◽  
Metacognitive Prompts ◽  
Computer Based ◽  
And Performance ◽  
Computer Based Learning Environments

AbstractStudents must engage in self-regulated learning in computer-based learning environments; however, many students experience difficulties in doing so. Therefore, this study aims to investigate self-created metacognitive prompts as a means of supporting students in their learning process and improving their learning performance. We conducted an experimental study with a between-subject design. The participants learned with self-created metacognitive prompts (n = 28) or without prompts (n = 29) in a hypermedia learning environment for 40 min while thinking aloud. In a second learning session (stability test), all participants learned about a different topic without prompts. The results showed no clear effect of the self-created metacognitive prompts on the learning process and performance. A deeper analysis revealed that students’ prompt utilization had a significant effect on performance in the second learning session. This study contributes to the research investigating how students can be supported in ways that enhance their learning process and performance.

Sign in / Sign up

Export Citation Format

Share Document