Task-Specific Loss: A Teacher-Centered Approach to Transfer Learning Between Distinctly Structured Robotic Agents

2022 ◽  
pp. 166-186
Author(s):  
Mehdi Mounsif ◽  
Sébastien Lengagne ◽  
Benoit Thuilot ◽  
Lounis Adouane
Keyword(s):  
Transfer Learning ◽  
Specific Loss ◽  
Teacher Centered

Molecular Generation Targeting Desired Electronic Properties via Deep Generative Models

2019 ◽  
Author(s):  
Qi Yuan ◽  
Alejandro Santana-Bonilla ◽  
Martijn Zwijnenburg ◽  
Kim Jelfs
Keyword(s):  
Neural Network ◽  
Electronic Properties ◽  
Transfer Learning ◽  
Recurrent Neural Network ◽  
Chemical Space ◽  
Generative Models ◽  
Molecular Features ◽  
Donor Acceptor ◽  
Homo Lumo ◽  
Training Sets

<p>The chemical space for novel electronic donor-acceptor oligomers with targeted properties was explored using deep generative models and transfer learning. A General Recurrent Neural Network model was trained from the ChEMBL database to generate chemically valid SMILES strings. The parameters of the General Recurrent Neural Network were fine-tuned via transfer learning using the electronic donor-acceptor database from the Computational Material Repository to generate novel donor-acceptor oligomers. Six different transfer learning models were developed with different subsets of the donor-acceptor database as training sets. We concluded that electronic properties such as HOMO-LUMO gaps and dipole moments of the training sets can be learned using the SMILES representation with deep generative models, and that the chemical space of the training sets can be efficiently explored. This approach identified approximately 1700 new molecules that have promising electronic properties (HOMO-LUMO gap <2 eV and dipole moment <2 Debye), 6-times more than in the original database. Amongst the molecular transformations, the deep generative model has learned how to produce novel molecules by trading off between selected atomic substitutions (such as halogenation or methylation) and molecular features such as the spatial extension of the oligomer. The method can be extended as a plausible source of new chemical combinations to effectively explore the chemical space for targeted properties.</p>

Learning from a Neighbor: Adapting a Japanese Parser for Korean Through Feature Transfer Learning

2014 ◽  
Author(s):  
Hiroshi Kanayama ◽  
Youngja Park ◽  
Yuta Tsuboi ◽  
Dongmook Yi
Keyword(s):  
Transfer Learning

A Qur’anic Methodology for Integrating Knowledge and Education

2016 ◽  
Vol 32 (2) ◽  
pp. 1-30
Author(s):  
Sidek Bin Baba ◽  
Mohamad Johdi Salleh ◽  
Tareq M Zayed ◽  
Ridwan Harris
Keyword(s):  
University Students ◽  
Learning Process ◽  
Teaching Methods ◽  
School Students ◽  
Types Of Knowledge ◽  
Teaching Learning ◽  
Teacher Centered ◽  
Integrated Knowledge

Integrating knowledge and education has become a major issue in Malaysia in the context of globalization. This study develops a teacher-centered Qur’anic methodology based on the integration of acquired (‘aqlī) and revealed (naqlī) knowledge as regards content, as well as the integration of teachers’ role in a teaching-learning process designed to empower students to manage “self” and “system.” It further investigates the existing curriculum and institutional efforts to integrate these two types of knowledge, students’ understanding of the integrated knowledge and its learning process, as well as how the teachers and lecturers understand this integrated knowledge and apply it to their teaching methods. Data collected through interviews and surveys of participating school students and teachers, as well as university students and lecturers, revealed several issues that need to be addressed.

Sign in / Sign up

Export Citation Format

Share Document