Co-transfer learning via joint transition probability graph based method

2012 ◽  
Author(s):  
Michael K. Ng ◽  
Qingyao Wu ◽  
Yunming Ye
Keyword(s):  
Transfer Learning ◽  
Transition Probability ◽  
Probability Graph

Novel Protein Sequence Comparison Method Based on Transition Probability Graph and Information Entropy

2020 ◽  
Vol 23 ◽  
Author(s):  
Zhaohui Qi ◽  
Xinlong Wen
Keyword(s):  
Amino Acids ◽  
Amino Acid ◽  
Information Entropy ◽  
Graphical Representation ◽  
Transition Probabilities ◽  
Transition Probability ◽  
Comparison Method ◽  
Sequencing Analysis ◽  
Probability Vector ◽  
Probability Graph

Aim and Objective: Sequence analysis is one of the foundations in bioinformatics. It is widely used to find out the feature metric hidden in the sequence. Otherwise, the graphical representation of biologic sequence is an important tool for sequencing analysis. This study is undertaken to find out a new graphical representation of biosequences. Materials and Methods: The transition probability is used to describe amino acid combinations of protein sequences. The combinations are composed of amino acids directly adjacent to each other or separated by multiple amino acids. The transition probability graph is built up by the transition probabilities of amino acid combinations. Next, a map is defined as a representation from transition probability graph to transition probability vector by k-order transition probability graph. Transition entropy vectors are developed by the transition probability vector and information entropy. Finally, the proposed method is applied to two separate applications, 499 HA genes of H1N1, and 95 coronaviruses. Results: By constructing a phylogenetic tree, we find that the results of each application are consistent with other studies. Conclusion: The graphical representation proposed in this article is a practical and correct method.

Energy Levels and Electromagnetic Transition of 90-94mo Nuclei Using Ibm-1

2020 ◽  
pp. 149-152
Keyword(s):  
Experimental Data ◽  
Transition Probability ◽  
Energy Levels ◽  
Dynamical Symmetry ◽  
Interacting Boson Model ◽  
Excitation Energies ◽  
Electromagnetic Transition ◽  
Boson Model ◽  
Energy States ◽  
Good Agreement

The energy states for the J , b , ɤ bands and electromagnetic transitions B (E2) values for even – even molybdenum 90 – 94 Mo nuclei are calculated in the present work of "the interacting boson model (IBM-1)" . The parameters of the equation of IBM-1 Hamiltonian are determined which yield the best excellent suit the experimental energy states . The positive parity of energy states are obtained by using IBS1. for program for even 90 – 94 Mo isotopes with bosons number 5 , 4 and 5 respectively. The" reduced transition probability B(E2)" of these neuclei are calculated and compared with the experimental data . The ratio of the excitation energies of the 41+ to 21+ states ( R4/2) are also calculated . The calculated and experimental (R4/2) values showed that the 90 – 94 Mo nuclei have the vibrational dynamical symmetry U(5). Good agreement was found from comparison between the calculated energy states and electric quadruple probabilities B(E2) transition of the 90–94Mo isotopes with the experimental data .

Regional household poverty and mobility analysis – a transition probability approach

2020 ◽  
Vol 63 (3) ◽  
pp. 286-302
Author(s):  
Damian Mowczan ◽  
Keyword(s):  
Transition Probability ◽  
General Level ◽  
Transition Matrices ◽  
Equivalent Unit ◽  
Central Statistical ◽  
Per Capita ◽  
Probability Matrices ◽  
General Mobility ◽  
One Year ◽  
The One

The main objective of this paper was to estimate and analyse transition-probability matrices for all 16 of Poland’s NUTS-2 level regions (voivodeship level). The analysis is conducted in terms of the transitions among six expenditure classes (per capita and per equivalent unit), focusing on poverty classes. The period of analysis was two years: 2015 and 2016. The basic aim was to identify both those regions in which the probability of staying in poverty was the highest and the general level of mobility among expenditure classes. The study uses a two-year panel sub-sample of unidentified unit data from the Central Statistical Office (CSO), specifically the data concerning household budget surveys. To account for differences in household size and demographic structure, the study used expenditures per capita and expenditures per equivalent unit simultaneously. To estimate the elements of the transition matrices, a classic maximum-likelihood estimator was used. The analysis used Shorrocks’ and Bartholomew’s mobility indices to assess the general mobility level and the Gini index to assess the inequality level. The results show that the one-year probability of staying in the same poverty class varies among regions and is lower for expenditures per equivalent units. The highest probabilities were identified in Podkarpackie (expenditures per capita) and Opolskie (expenditures per equivalent unit), and the lowest probabilities in Kujawsko-Pomorskie (expenditures per capita) and Małopolskie (expenditures per equivalent unit). The highest level of general mobility was noted in Małopolskie, for both categories of expenditures.

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

Deep Learning for text in limted data settings

2020 ◽  
Author(s):  
Pathikkumar Patel ◽  
Bhargav Lad ◽  
Jinan Fiaidhi
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Transfer Learning ◽  
Text Classification ◽  
State Of The Art ◽  
Time Series Forecasting ◽  
Text Data ◽  
Performance Levels

During the last few years, RNN models have been extensively used and they have proven to be better for sequence and text data. RNNs have achieved state-of-the-art performance levels in several applications such as text classification, sequence to sequence modelling and time series forecasting. In this article we will review different Machine Learning and Deep Learning based approaches for text data and look at the results obtained from these methods. This work also explores the use of transfer learning in NLP and how it affects the performance of models on a specific application of sentiment analysis.

Investigating Transfer Learning in the Urban Combat Testbed

2007 ◽  
Author(s):  
Nicholas A. Gorski ◽  
John E. Laird
Keyword(s):  
Transfer Learning
Sign in / Sign up

Export Citation Format

Share Document