scholarly journals Materials property prediction for limited datasets enabled by feature selection and joint learning with MODNet

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Pierre-Paul De Breuck ◽  
Geoffroy Hautier ◽  
Gian-Marco Rignanese
Keyword(s):  
Network Models ◽  
Learning Approaches ◽  
Vibrational Entropy ◽  
Joint Learning ◽  
Training Time ◽  
Test Error ◽  
Single Target ◽  
Current Graph ◽  
Absolute Test ◽  
Selection Of

AbstractIn order to make accurate predictions of material properties, current machine-learning approaches generally require large amounts of data, which are often not available in practice. In this work, MODNet, an all-round framework, is presented which relies on a feedforward neural network, the selection of physically meaningful features, and when applicable, joint-learning. Next to being faster in terms of training time, this approach is shown to outperform current graph-network models on small datasets. In particular, the vibrational entropy at 305 K of crystals is predicted with a mean absolute test error of 0.009 meV/K/atom (four times lower than previous studies). Furthermore, joint learning reduces the test error compared to single-target learning and enables the prediction of multiple properties at once, such as temperature functions. Finally, the selection algorithm highlights the most important features and thus helps to understand the underlying physics.

Machine learning approaches to understand and predict rate constants for organic processes in mixtures containing ionic liquids

2021 ◽  
Vol 23 (4) ◽  
pp. 2742-2752
Author(s):  
Tamar L. Greaves ◽  
Karin S. Schaffarczyk McHale ◽  
Raphael F. Burkart-Radke ◽  
Jason B. Harper ◽  
Tu C. Le
Keyword(s):  
Machine Learning ◽  
Ionic Liquids ◽  
Rate Constants ◽  
Learning Approaches ◽  
Learning Models ◽  
Organic Reaction ◽  
Machine Learning Models ◽  
Selection Of

Machine learning models were developed for an organic reaction in ionic liquids and validated on a selection of ionic liquids.

New active learning algorithms for near-infrared spectroscopy in agricultural applications

2021 ◽  
Vol 69 (4) ◽  
pp. 297-306
Author(s):  
Julius Krause ◽  
Maurice Günder ◽  
Daniel Schulz ◽  
Robin Gruna
Keyword(s):  
Active Learning ◽  
Near Infrared ◽  
Agricultural Products ◽  
Training Data ◽  
Calibration Model ◽  
Learning Approaches ◽  
Training Samples ◽  
Agricultural Applications ◽  
Selection Of

Abstract The selection of training data determines the quality of a chemometric calibration model. In order to cover the entire parameter space of known influencing parameters, an experimental design is usually created. Nevertheless, even with a carefully prepared Design of Experiment (DoE), redundant reference analyses are often performed during the analysis of agricultural products. Because the number of possible reference analyses is usually very limited, the presented active learning approaches are intended to provide a tool for better selection of training samples.

scholarly journals Shift Invariant Dictionary Learning for Human Action Recognition

2019 ◽  
Vol 9 (2) ◽  
pp. 2107-2111
Keyword(s):  
Sparse Representation ◽  
Action Recognition ◽  
Dictionary Learning ◽  
Human Action Recognition ◽  
Human Action ◽  
Signal Denoising ◽  
Learning Approaches ◽  
Training Time ◽  
Initial Stage ◽  
Shift Invariance

Sparse representation is an emerging topic among researchers. The method to represent the huge volume of dense data as sparse data is much needed for various fields such as classification, compression and signal denoising. The base of the sparse representation is dictionary learning. In most of the dictionary learning approaches, the dictionary is learnt based on the input training signals which consumes more time. To solve this issue, the shift-invariant dictionary is used for action recognition in this work. Shift-Invariant Dictionary (SID) is that the dictionary is constructed in the initial stage with shift-invariance of initial atoms. The advantage of the proposed SID based action recognition method is that it requires minimum training time and achieves highest accuracy.

scholarly journals Fault Diagnosis of Transmission Line using Feed Forward Neural Network

2019 ◽  
Vol 8 (9S2) ◽  
pp. 263-268
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Transmission Lines ◽  
Field Work ◽  
Neural Nets ◽  
Feed Forward Neural Network ◽  
Training Time ◽  
Optimum Result ◽  
Human Effort ◽  
Selection Of

The implementation of neural network for the fault diagnosis is to improve the dependability of the proposed scheme by providing a more accurate, faster diagnosis relaying scheme as compared with the conventional relaying schemes. It is important to improve the relaying schemes regarding the shortcoming of the system and increase the dependability of the system by using the proposed relaying scheme. It also provide more accurate, faster relaying scheme. It also gives selective schemes as compared to conventional system. The techniques for survey employed some methods for the collection of data which involved a literature review of journals, from review on books, newspaper, magazines as well as field work, additional data was collected from researchers who are working in this field. To achieve optimum result we have to improve following things: (i) Training time, (ii) Selection of training vector, (iii) Upgrading of trained neural nets and integration of technologies. AI with its promise of adaptive training and generalization deserves scope. As a result we obtain a system which is more reliable, more accurate, and faster, has more dependability as well as it will selective according to the proposed relaying scheme as compare to the conventional relaying scheme. This system helps us to reduce the shortcoming like major faults which we faced in the complex system of transmission lines which will helps in reducing human effort, saves cost for maintaining the transmission system.

scholarly journals A DESCRIPTIVE STUDY ON FACTORS AFFECTING THE USE OF LEARNING APPROACH AMONG ACCOUNTING EDUCATION STUDENTS AT UNIVERSITAS NEGERI MEDAN

2020 ◽  
Vol 4 (1) ◽  
pp. 14
Author(s):  
Iis Sundari ◽  
Lianti Lianti ◽  
Hidaya Tul Karima ◽  
Yulita Triadiarti ◽  
Tapi Rumondang Siregar
Keyword(s):  
Learning Strategies ◽  
Learning Style ◽  
Descriptive Analysis ◽  
Accounting Education ◽  
Learning Approach ◽  
Learning Material ◽  
Learning Approaches ◽  
Education Students ◽  
Factors Affecting ◽  
Selection Of

Understanding of learning material, especially accounting material, has an impact on the achievement of students' learning outcomes. The research aims to look at the factors that influence the learning approach of Unimed accounting education students. This research was carried out in the FE UNIMED using questionnaires distributed to students of the Accounting Education Program batch of 2015 and 2016, amounting 60 and 68 students from each batch. The selection of batches is based on the type of curriculum applied to each batch, namely the Indonesian National Qualification Framework (abbreviated as KKNI) for 2016 and the non-KKNI for 2015. The approach used in this study was a qualitative approach, with the analysis used was descriptive statistical analysis on factors such as interest, motivation, learning style, anxiety, institutional, and learning strategies. The descriptive analysis shows that except for the interest indicating that non-KKNI students have a higher interest in applying a variety of learning approaches of Non-KKNI students than their KKNI peers, other factors are similar between students from two batches.  Keywords: Interest; Motivation; Learning Style; Anxiety; Institutional. 

scholarly journals Soft Threshold Ternary Networks

2020 ◽  
Author(s):  
Weixiang Xu ◽  
Xiangyu He ◽  
Tianli Zhao ◽  
Qinghao Hu ◽  
Peisong Wang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Mobile Devices ◽  
State Of The Art ◽  
Performance Gap ◽  
Training Time ◽  
Current State ◽  
The Arts ◽  
Soft Threshold ◽  
And Storage ◽  
Selection Of

Large neural networks are difficult to deploy on mobile devices because of intensive computation and storage. To alleviate it, we study ternarization, a balance between efficiency and accuracy that quantizes both weights and activations into ternary values. In previous ternarized neural networks, a hard threshold Δ is introduced to determine quantization intervals. Although the selection of Δ greatly affects the training results, previous works estimate Δ via an approximation or treat it as a hyper-parameter, which is suboptimal. In this paper, we present the Soft Threshold Ternary Networks (STTN), which enables the model to automatically determine quantization intervals instead of depending on a hard threshold. Concretely, we replace the original ternary kernel with the addition of two binary kernels at training time, where ternary values are determined by the combination of two corresponding binary values. At inference time, we add up the two binary kernels to obtain a single ternary kernel. Our method dramatically outperforms current state-of-the-arts, lowering the performance gap between full-precision networks and extreme low bit networks. Experiments on ImageNet with AlexNet (Top-1 55.6%), ResNet-18 (Top-1 66.2%) achieves new state-of-the-art.

Molecular Modeling Techniques Applied to the Design of Multitarget Drugs: Methods and Applications

2021 ◽  
Vol 21 ◽  
Author(s):  
Larissa Henriques Evangelista Castro ◽  
Carlos Mauricio R. Sant'Anna
Keyword(s):  
Drug Design ◽  
Similar Efficacy ◽  
Learning Approaches ◽  
Resistance Development ◽  
Multifactorial Diseases ◽  
Target Drug ◽  
Single Target ◽  
Modeling Techniques ◽  
Computer Based ◽  
New Challenges

: Multifactorial diseases, such as cancer and diabetes present a challenge for the traditional “one-target, one disease” paradigm due to their complex pathogenic mechanisms. Although a combination of drugs can be used, a multitarget drug may be a better choice face of its efficacy, lower adverse effects and lower chance of resistance development. The computer-based design of these multitarget drugs can explore the same techniques used for single-target drug design, but the difficulties associated to the obtention of drugs that are capable of modulating two or more targets with similar efficacy impose new challenges, whose solutions involve the adaptation of known techniques and also to the development of new ones, including machine-learning approaches. In this review, some SBDD and LBDD techniques for the multitarget drug design are discussed, together with some cases where the application of such techniques led to effective multitarget ligands.

scholarly journals Semi‐supervised joint learning for longitudinal clinical events classification using neural network models

Stat ◽  
2020 ◽  
Vol 9 (1) ◽  
Author(s):  
Weijing Tang ◽  
Jiaqi Ma ◽  
Akbar K. Waljee ◽  
Ji Zhu
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Neural Network Models ◽  
Joint Learning ◽  
Clinical Events

scholarly journals Comparison of Implicit vs. Explicit Regime Identification in Machine Learning Methods for Solar Irradiance Prediction

Energies ◽  
2020 ◽  
Vol 13 (3) ◽  
pp. 689 ◽  
Author(s):  
Tyler McCandless ◽  
Susan Dettling ◽  
Sue Ellen Haupt
Keyword(s):  
Machine Learning ◽  
Solar Power ◽  
Network Models ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Validation Dataset ◽  
Prediction Errors ◽  
Learning Approaches ◽  
Power Prediction ◽  
Neural Network Models

This work compares the solar power forecasting performance of tree-based methods that include implicit regime-based models to explicit regime separation methods that utilize both unsupervised and supervised machine learning techniques. Previous studies have shown an improvement utilizing a regime-based machine learning approach in a climate with diverse cloud conditions. This study compares the machine learning approaches for solar power prediction at the Shagaya Renewable Energy Park in Kuwait, which is in an arid desert climate characterized by abundant sunshine. The regime-dependent artificial neural network models undergo a comprehensive parameter and hyperparameter tuning analysis to minimize the prediction errors on a test dataset. The final results that compare the different methods are computed on an independent validation dataset. The results show that the tree-based methods, the regression model tree approach, performs better than the explicit regime-dependent approach. These results appear to be a function of the predominantly sunny conditions that limit the ability of an unsupervised technique to separate regimes for which the relationship between the predictors and the predictand would differ for the supervised learning technique.

scholarly journals Learning to Teach Reinforcement Learning Agents

2017 ◽  
Vol 1 (1) ◽  
pp. 21-42 ◽  
Author(s):  
Anestis Fachantidis ◽  
Matthew Taylor ◽  
Ioannis Vlahavas
Keyword(s):  
Reinforcement Learning ◽  
Learning Algorithm ◽  
Relevant Literature ◽  
Learning Approaches ◽  
Training Time ◽  
Factors Affecting ◽  
Learning Agents ◽  
Best Teachers ◽  
Previous Learning ◽  
Advice Quality

In this article, we study the transfer learning model of action advice under a budget. We focus on reinforcement learning teachers providing action advice to heterogeneous students playing the game of Pac-Man under a limited advice budget. First, we examine several critical factors affecting advice quality in this setting, such as the average performance of the teacher, its variance and the importance of reward discounting in advising. The experiments show that the best performers are not always the best teachers and reveal the non-trivial importance of the coefficient of variation (CV) as a statistic for choosing policies that generate advice. The CV statistic relates variance to the corresponding mean. Second, the article studies policy learning for distributing advice under a budget. Whereas most methods in the relevant literature rely on heuristics for advice distribution, we formulate the problem as a learning one and propose a novel reinforcement learning algorithm capable of learning when to advise or not. The proposed algorithm is able to advise even when it does not have knowledge of the student’s intended action and needs significantly less training time compared to previous learning approaches. Finally, in this article, we argue that learning to advise under a budget is an instance of a more generic learning problem: Constrained Exploitation Reinforcement Learning.

Sign in / Sign up

Export Citation Format

Share Document