371 |
Transformer-based Model for Molecular Property Prediction with Self-Supervised Transfer LearningLin, Lyu January 2020 (has links)
Molecular property prediction has a vast range of applications in the chemical industry. A powerful molecular property prediction model can promote experiments and production processes. The idea behind this degree program lies in the use of transfer learning to predict molecular properties. The project is divided into two parts. The first part is to build and pre-train the model. The model, which is constructed with pure attention-based Transformer Layer, is pre-trained through a Masked Edge Recovery task with large-scale unlabeled data. Then, the performance of this pre- trained model is tested with different molecular property prediction tasks and finally verifies the effectiveness of transfer learning.The results show that after self-supervised pre-training, this model shows its excellent generalization capability. It is possible to be fine-tuned with a short period and performs well in downstream tasks. And the effectiveness of transfer learning is reflected in the experiment as well. The pre-trained model not only shortens the task- specific training time but also obtains better performance and avoids overfitting due to too little training data for molecular property prediction. / Prediktion av molekylers egenskaper har en stor mängd tillämpningar inom kemiindustrin. Kraftfulla metoder för att predicera molekylära egenskaper kan främja vetenskapliga experiment och produktionsprocesser. Ansatsen i detta arbete är att använda överförd inlärning (eng. transfer learning) för att predicera egenskaper hos molekyler. Projektet är indelat i två delar. Den första delen fokuserar på att utveckla och förträna en modell. Modellen består av Transformer-lager med attention- mekanismer och förtränas genom att återställa maskerade kanter i molekylgrafer från storskaliga mängder icke-annoterad data. Efteråt utvärderas prestandan hos den förtränade modellen i en mängd olika uppgifter baserade på prediktion av molekylegenskaper vilket bekräftar fördelen med överförd inlärning.Resultaten visar att modellen efter självövervakad förträning besitter utmärkt förmåga till att generalisera. Den kan finjusteras med liten tidskostnad och presterar väl i specialiserade uppgifter. Effektiviteten hos överförd inlärning visas också i experimenten. Den förtränade modellen förkortar inte bara tiden för uppgifts-specifik inlärning utan uppnår även bättre prestanda och undviker att övertränas på grund otillräckliga mängder data i uppgifter för prediktion av molekylegenskaper.
|
372 |
AIRS: a Resource Limited Artificial Immune ClassifierWatkins, Andrew B 14 December 2001 (has links)
The natural immune system embodies a wealth of information processing capabilities that can be exploited as a metaphor for the development of artificial immune systems. Chief among these features is the ability to recognize previously encountered substances and to generalize beyond recognition in order to provide appropriate responses to pathogens not seen before. This thesis presents a new supervised learning paradigm, resource limited artificial immune classifiers, inspired by mechanisms exhibited in natural and artificial immune systems. The key abstractions gleaned from these immune systems include resource competition, clonal selection, affinity maturation, and memory cell retention. A discussion of the progenitors of this work is offered. This work provides a thorough explication of a resource limited artifical immune classification algorithm, named AIRS (Artificial Immune Recognition System). Experimental results on both simulated data sets and real world machine learning benchmarks demonstrate the effectiveness of the AIRS algorithm as a classification technique.
|
373 |
Gravitropic Signal Transduction: A Systems Approach to Gene DiscoveryShen, Kaiyu 12 June 2014 (has links)
No description available.
|
374 |
Deep-learning Approaches to Object Recognition from 3D DataChen, Zhiang 30 August 2017 (has links)
No description available.
|
375 |
Rethinking Document Classification: A Pilot for the Application of Text Mining Techniques To Enhance Standardized Assessment Protocols for Critical Care Medical Team Transfer of CareWalker, Briana Shanise 09 June 2017 (has links)
No description available.
|
376 |
Semi-supervised Ensemble Learning Methods for Enhanced Prognostics and Health ManagementShi, Zhe 15 May 2018 (has links)
No description available.
|
377 |
AN ALL-ATTRIBUTES APPROACH TO SUPERVISED LEARNINGVANCE, DANNY W. January 2006 (has links)
No description available.
|
378 |
Land Cover Change Across an Urban-Rural Transect in Southern Ohio, 1988-2008Walsh, Steven 18 August 2009 (has links)
No description available.
|
379 |
OPTIMAL FEATURE SUBSET SELECTION ALGORITHMS FOR UNSUPERVISED LEARNINGWU, CHEN January 2000 (has links)
No description available.
|
380 |
Identification of Uniform Class Regions using Perceptron TrainingSamuel, Nikhil J. 15 October 2015 (has links)
No description available.
|
Page generated in 0.0533 seconds