scholarly journals Bias Free Multiobjective Active Learning for Materials Design and Discovery

2020 ◽  
Author(s):  
Kevin Maik Jablonka ◽  
Giriprasad Melpatti Jothiappan ◽  
Shefang Wang ◽  
Berend Smit ◽  
Brian Yoo
Keyword(s):  
Active Learning ◽  
De Novo ◽  
Learning Algorithm ◽  
Random Search ◽  
Search Space ◽  
Machine Learning Techniques ◽  
Pareto Optimal ◽  
Design Rules ◽  
Learning Techniques ◽  
Screening Approaches

<div>The design rules for materials are clear for applications with a single objective. For most applications, however, there are often multiple, sometimes competing objectives where there is no single best material, and the design rules change to finding the set of Pareto optimal materials. </div><div>In this work, we introduce an active learning algorithm that directly uses the Pareto dominance relation to compute the set of Pareto optimal materials with desirable accuracy. <br></div><div>We apply our algorithm to de novo polymer design with a prohibitively large search space.</div><div>Using molecular simulations, we compute key descriptors for dispersant applications and reduce the number of materials that need to be evaluated to reconstruct the Pareto front with a desired confidence by over 98% compared to random search.</div><div>This work showcases how simulation and machine learning techniques can be coupled to discover materials within a design space that would be intractable using conventional screening approaches.</div>

scholarly journals Bias Free Multiobjective Active Learning for Materials Design and Discovery

2020 ◽  
Author(s):  
Kevin Maik Jablonka ◽  
Giriprasad Melpatti Jothiappan ◽  
Shefang Wang ◽  
Berend Smit ◽  
Brian Yoo
Keyword(s):  
Active Learning ◽  
De Novo ◽  
Learning Algorithm ◽  
Random Search ◽  
Search Space ◽  
Machine Learning Techniques ◽  
Pareto Optimal ◽  
Design Rules ◽  
Learning Techniques ◽  
Screening Approaches

<div>The design rules for materials are clear for applications with a single objective. For most applications, however, there are often multiple, sometimes competing objectives where there is no single best material, and the design rules change to finding the set of Pareto optimal materials. </div><div>In this work, we introduce an active learning algorithm that directly uses the Pareto dominance relation to compute the set of Pareto optimal materials with desirable accuracy. <br></div><div>We apply our algorithm to de novo polymer design with a prohibitively large search space.</div><div>Using molecular simulations, we compute key descriptors for dispersant applications and reduce the number of materials that need to be evaluated to reconstruct the Pareto front with a desired confidence by over 98% compared to random search.</div><div>This work showcases how simulation and machine learning techniques can be coupled to discover materials within a design space that would be intractable using conventional screening approaches.</div>

scholarly journals Bias free multiobjective active learning for materials design and discovery

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Kevin Maik Jablonka ◽  
Giriprasad Melpatti Jothiappan ◽  
Shefang Wang ◽  
Berend Smit ◽  
Brian Yoo
Keyword(s):  
Active Learning ◽  
Pareto Front ◽  
De Novo ◽  
Learning Algorithm ◽  
Search Space ◽  
Machine Learning Techniques ◽  
Pareto Optimal ◽  
Design Rules ◽  
Learning Techniques ◽  
Screening Approaches

AbstractThe design rules for materials are clear for applications with a single objective. For most applications, however, there are often multiple, sometimes competing objectives where there is no single best material and the design rules change to finding the set of Pareto optimal materials. In this work, we leverage an active learning algorithm that directly uses the Pareto dominance relation to compute the set of Pareto optimal materials with desirable accuracy. We apply our algorithm to de novo polymer design with a prohibitively large search space. Using molecular simulations, we compute key descriptors for dispersant applications and drastically reduce the number of materials that need to be evaluated to reconstruct the Pareto front with a desired confidence. This work showcases how simulation and machine learning techniques can be coupled to discover materials within a design space that would be intractable using conventional screening approaches.

scholarly journals Inductive Design Exploration Method with Active Learning for Complex Design Problems

2018 ◽  
Vol 8 (12) ◽  
pp. 2418
Author(s):  
Sungwoo Jang ◽  
Hae-Jin Choi ◽  
Seung-Kyum Choi ◽  
Jae-Sung Oh
Keyword(s):  
Active Learning ◽  
Learning Algorithm ◽  
Design Method ◽  
Design Approach ◽  
Machine Learning Techniques ◽  
Sampling Effort ◽  
Design Exploration ◽  
Multiscale Materials ◽  
Complex Design ◽  
Learning Techniques

The design of multiscale materials and products has necessitated an inductive and robust design approach to ensure satisfying the performance goals for complex engineering problems. Inductive design exploration method is a performance-driven design approach that explores feasible design spaces while considering the effect of uncertainty that leads to performance variability. However, the existing design method suffers from high computational costs for pre-defined sample data, which sacrifices the accuracy of solution spaces. In this study, we present an improved implementation of the inductive design exploration method by applying the active learning algorithm that is mainly used in machine learning techniques. The purpose of this study is to minimize the sampling effort while maintaining reasonable accuracy in the exploration of design spaces, thereby alleviating computational burden. The capabilities of the improved method are highlighted and demonstrated via a design problem of the blast resistant sandwich panel.

scholarly journals Comparison of Machine Learning algorithm for COVID-19 Death Risk Prediction

2021 ◽  
Author(s):  
Praveeen Anandhanathan ◽  
Priyanka Gopalan
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Nearest Neighbour ◽  
Decision Tree Algorithm ◽  
The Past ◽  
Random Forest Method ◽  
Learning Techniques ◽  
The World

Abstract Coronavirus disease (COVID-19) is spreading across the world. Since at first it has appeared in Wuhan, China in December 2019, it has become a serious issue across the globe. There are no accurate resources to predict and find the disease. So, by knowing the past patients’ records, it could guide the clinicians to fight against the pandemic. Therefore, for the prediction of healthiness from symptoms Machine learning techniques can be implemented. From this we are going to analyse only the symptoms which occurs in every patient. These predictions can help clinicians in the easier manner to cure the patients. Already for prediction of many of the diseases, techniques like SVM (Support vector Machine), Fuzzy k-Means Clustering, Decision Tree algorithm, Random Forest Method, ANN (Artificial Neural Network), KNN (k-Nearest Neighbour), Naïve Bayes, Linear Regression model are used. As we haven’t faced this disease before, we can’t say which technique will give the maximum accuracy. So, we are going to provide an efficient result by comparing all the such algorithms in RStudio.

scholarly journals DEVELOPMENT OF A MACHINE LEARNING ALGORITHM TO PREDICT AUTHOR’S AGE FROM TEXT

2020 ◽  
Vol 7 (10) ◽  
pp. 380-389
Author(s):  
Asogwa D.C ◽  
Anigbogu S.O ◽  
Anigbogu G.N ◽  
Efozia F.N
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Learning Algorithm ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Machine Learning Algorithm ◽  
Age Group ◽  
Political Views ◽  
Learning Techniques ◽  
Age Prediction

Author's age prediction is the task of determining the author's age by studying the texts written by them. The prediction of author’s age can be enlightening about the different trends, opinions social and political views of an age group. Marketers always use this to encourage a product or a service to an age group following their conveyed interests and opinions. Methodologies in natural language processing have made it possible to predict author’s age from text by examining the variation of linguistic characteristics. Also, many machine learning algorithms have been used in author’s age prediction. However, in social networks, computational linguists are challenged with numerous issues just as machine learning techniques are performance driven with its own challenges in realistic scenarios. This work developed a model that can predict author's age from text with a machine learning algorithm (Naïve Bayes) using three types of features namely, content based, style based and topic based. The trained model gave a prediction accuracy of 80%.

scholarly journals Development of Agriculture Chatbot using Machine Learning Techniques

2019 ◽  
Vol 9 (2S) ◽  
pp. 24-28
Keyword(s):  
Question Answering ◽  
Learning Algorithm ◽  
Related Question ◽  
Machine Learning Techniques ◽  
Meaningful Information ◽  
Related Information ◽  
Exact Answer ◽  
Deep Learning Algorithm ◽  
The People ◽  
Learning Techniques

Agriculture data is a main source of country’s economic growth. It is important to provide agriculture related information to all the people who are involved in agriculture activities as and when required. This meaningful information is used by people who supply services to agriculture domain and to take some correct decision related to agriculture to apply for their field. The solutions to this problem are given by the efficient interaction of computer with human. Chatbot system provides ability to extract the exact answer to the queries posed by farmers. The proposed system is called as Agriculture Chatbot system or even it is called as Question-Answering system for agriculture domain, where farmer is asking the agriculture related question which fetches the precise answers for the asked questions by farmers in natural language and processes the query using RNN (Recurrent Neural Network) deep learning algorithm to extract correct answer.

scholarly journals SoK: Privacy-Preserving Collaborative Tree-based Model Learning

2021 ◽  
Vol 2021 (3) ◽  
pp. 182-203
Author(s):  
Sylvain Chatel ◽  
Apostolos Pyrgelis ◽  
Juan Ramón Troncoso-Pastoriza ◽  
Jean-Pierre Hubaux
Keyword(s):  
Learning Algorithm ◽  
Information Leakage ◽  
Privacy Preserving ◽  
Machine Learning Techniques ◽  
Model Learning ◽  
Protection Mechanism ◽  
Knowledge Based ◽  
Learning Techniques ◽  
Efficient Machine ◽  
First Time

Abstract Tree-based models are among the most efficient machine learning techniques for data mining nowadays due to their accuracy, interpretability, and simplicity. The recent orthogonal needs for more data and privacy protection call for collaborative privacy-preserving solutions. In this work, we survey the literature on distributed and privacy-preserving training of tree-based models and we systematize its knowledge based on four axes: the learning algorithm, the collaborative model, the protection mechanism, and the threat model. We use this to identify the strengths and limitations of these works and provide for the first time a framework analyzing the information leakage occurring in distributed tree-based model learning.

Supervised Machine Learning for Plants Identification Based on Images of Their Leaves

2020 ◽  
pp. 1314-1330 ◽  
Author(s):  
Mohamed Elhadi Rahmani ◽  
Abdelmalek Amine ◽  
Reda Mohamed Hamou
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Texture Feature ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Nearest Neighbour ◽  
Curve Shape ◽  
Distance Curve ◽  
Shape Signature ◽  
Learning Techniques

Botanists study in general the characteristics of leaves to give to each plant a scientific name; such as shape, margin...etc. This paper proposes a comparison of supervised plant identification using different approaches. The identification is done according to three different features extracted from images of leaves: a fine-scale margin feature histogram, a Centroid Contour Distance Curve shape signature and an interior texture feature histogram. First represent each leaf by one feature at a time in, then represent leaves by two features, and each leaf was represented by the three features. After that, the authors classified the obtained vectors using different supervised machine learning techniques; the used techniques are Decision tree, Naïve Bayes, K-nearest neighbour, and neural network. Finally, they evaluated the classification using cross validation. The main goal of this work is studying the influence of representation of leaves' images on the identification of plants, and also studying the use of supervised machine learning algorithm for plant leaves classification.

Optimization of Evolutionary Algorithm Using Machine Learning Techniques for Pattern Mining in Transactional Database

2020 ◽  
pp. 173-200
Author(s):  
Logeswaran K. ◽  
Suresh P. ◽  
Savitha S. ◽  
Prasanna Kumar K. R.
Keyword(s):  
Evolutionary Algorithm ◽  
Pattern Mining ◽  
Fitness Function ◽  
Search Space ◽  
Machine Learning Techniques ◽  
Dynamic Selection ◽  
Learning Techniques ◽  
Optimal Function ◽  
High Utility ◽  
Mining Algorithms

In recent years, the data analysts are facing many challenges in high utility itemset (HUI) mining from given transactional database using existing traditional techniques. The challenges in utility mining algorithms are exponentially growing search space and the minimum utility threshold appropriate to the given database. To overcome these challenges, evolutionary algorithm-based techniques can be used to mine the HUI from transactional database. However, testing each of the supporting functions in the optimization problem is very inefficient and it increases the time complexity of the algorithm. To overcome this drawback, reinforcement learning-based approach is proposed for improving the efficiency of the algorithm, and the most appropriate fitness function for evaluation can be selected automatically during execution of an algorithm. Furthermore, during the optimization process when distinct functions are skillful, dynamic selection of current optimal function is done.

scholarly journals Using Machine Learning for Decreasing State Uncertainty in Planning

2020 ◽  
Vol 69 ◽  
pp. 765-806
Author(s):  
Senka Krivic ◽  
Michael Cashmore ◽  
Daniele Magazzeni ◽  
Sandor Szedmak ◽  
Justus Piater
Keyword(s):  
Machine Learning ◽  
Active Learning ◽  
Learning Process ◽  
The State ◽  
Machine Learning Techniques ◽  
Planning Problem ◽  
Planning Techniques ◽  
Novel Approach ◽  
Learning Techniques ◽  
State Uncertainty

We present a novel approach for decreasing state uncertainty in planning prior to solving the planning problem. This is done by making predictions about the state based on currently known information, using machine learning techniques. For domains where uncertainty is high, we define an active learning process for identifying which information, once sensed, will best improve the accuracy of predictions. We demonstrate that an agent is able to solve problems with uncertainties in the state with less planning effort compared to standard planning techniques. Moreover, agents can solve problems for which they could not find valid plans without using predictions. Experimental results also demonstrate that using our active learning process for identifying information to be sensed leads to gathering information that improves the prediction process.

Sign in / Sign up

Export Citation Format

Share Document