scholarly journals Generative Models for Labeling Multi-object Configurations in Images

2006 ◽  
pp. 362-381 ◽  
Author(s):  
Yali Amit ◽  
Alain Trouvé
Keyword(s):  
Generative Models

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>

Networks

2018 ◽  
Author(s):  
Mark Newman
Keyword(s):  
Biological Networks ◽  
Generative Models ◽  
The Internet ◽  
Network Data ◽  
Computer Algorithms ◽  
Graph Models ◽  
Random Graph Models ◽  
The Social ◽  
Spectral Algorithms ◽  
Wide Availability

The study of networks, including computer networks, social networks, and biological networks, has attracted enormous interest in recent years. The rise of the Internet and the wide availability of inexpensive computers have made it possible to gather and analyse network data on an unprecendented scale, and the development of new theoretical tools has allowed us to extract knowledge from networks of many different kinds. The study of networks is broadly interdisciplinary and developments have occurred in many fields, including mathematics, physics, computer and information sciences, biology, and the social science. This book brings together the most important breakthroughts in each of these fields and presents them in a unified fashion, highlighting the strong interconnections between work in different areas. Topics covered include the measurement of networks; methods for analysing network data, including methods developed in physics, statistics, and sociology; fundamentals of graph theory; computer algorithms, including spectral algorithms and community detection; mathematical models of networks such as random graph models and generative models; and models of processes taking place on networks.

scholarly journals Automatic Labeled Dialogue Generation for Nursing Record Systems

2020 ◽  
Vol 10 (3) ◽  
pp. 62
Author(s):  
Tittaya Mairittha ◽  
Nattaya Mairittha ◽  
Sozo Inoue
Keyword(s):  
Data Augmentation ◽  
Short Term Memory ◽  
Generative Models ◽  
Abstract Knowledge ◽  
Augmentation Techniques ◽  
Nursing Record ◽  
Long Short Term Memory ◽  
The Individual ◽  
High Level ◽  
Embedding Methods

The integration of digital voice assistants in nursing residences is becoming increasingly important to facilitate nursing productivity with documentation. A key idea behind this system is training natural language understanding (NLU) modules that enable the machine to classify the purpose of the user utterance (intent) and extract pieces of valuable information present in the utterance (entity). One of the main obstacles when creating robust NLU is the lack of sufficient labeled data, which generally relies on human labeling. This process is cost-intensive and time-consuming, particularly in the high-level nursing care domain, which requires abstract knowledge. In this paper, we propose an automatic dialogue labeling framework of NLU tasks, specifically for nursing record systems. First, we apply data augmentation techniques to create a collection of variant sample utterances. The individual evaluation result strongly shows a stratification rate, with regard to both fluency and accuracy in utterances. We also investigate the possibility of applying deep generative models for our augmented dataset. The preliminary character-based model based on long short-term memory (LSTM) obtains an accuracy of 90% and generates various reasonable texts with BLEU scores of 0.76. Secondly, we introduce an idea for intent and entity labeling by using feature embeddings and semantic similarity-based clustering. We also empirically evaluate different embedding methods for learning good representations that are most suitable to use with our data and clustering tasks. Experimental results show that fastText embeddings produce strong performances both for intent labeling and on entity labeling, which achieves an accuracy level of 0.79 and 0.78 f1-scores and 0.67 and 0.61 silhouette scores, respectively.

scholarly journals Contextualizing genetic risk score for disease screening and rare variant discovery

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Dan Zhou ◽  
Dongmei Yu ◽  
Jeremiah M. Scharf ◽  
Carol A. Mathews ◽  
Lauren McGrath ◽  
...  
Keyword(s):  
Complex Traits ◽  
Genetic Basis ◽  
Clinical Decision Making ◽  
Genetic Risk Score ◽  
Sufficient Conditions ◽  
Clinical Decision ◽  
Generative Models ◽  
Variant Discovery ◽  
Models Of Disease ◽  
The Uk

AbstractStudies of the genetic basis of complex traits have demonstrated a substantial role for common, small-effect variant polygenic burden (PB) as well as large-effect variants (LEV, primarily rare). We identify sufficient conditions in which GWAS-derived PB may be used for well-powered rare pathogenic variant discovery or as a sample prioritization tool for whole-genome or exome sequencing. Through extensive simulations of genetic architectures and generative models of disease liability with parameters informed by empirical data, we quantify the power to detect, among cases, a lower PB in LEV carriers than in non-carriers. Furthermore, we uncover clinically useful conditions wherein the risk derived from the PB is comparable to the LEV-derived risk. The resulting summary-statistics-based methodology (with publicly available software, PB-LEV-SCAN) makes predictions on PB-based LEV screening for 36 complex traits, which we confirm in several disease datasets with available LEV information in the UK Biobank, with important implications on clinical decision-making.

scholarly journals Generative Models for Relief Perspective Architectures

2021 ◽  
Author(s):  
Leonardo Baglioni ◽  
Federico Fallavollita
Keyword(s):  
Research Methodology ◽  
Affine Space ◽  
Three Dimensional ◽  
Generative Models ◽  
Linear Perspective ◽  
Dimensional Structure ◽  
Three Dimensional Structure ◽  
Present Essay ◽  
Santa Maria

AbstractThe present essay investigates the potential of generative representation applied to the study of relief perspective architectures realized in Italy between the sixteenth and seventeenth centuries. In arts, and architecture in particular, relief perspective is a three-dimensional structure able to create the illusion of great depths in small spaces. A method of investigation applied to the case study of the Avila Chapel in Santa Maria in Trastevere in Rome (Antonio Gherardi 1678) is proposed. The research methodology can be extended to other cases and is based on the use of a Relief Perspective Camera, which can create both a linear perspective and a relief perspective. Experimenting mechanically and automatically the perspective transformations from the affine space to the illusory space and vice versa has allowed us to see the case study in a different light.

scholarly journals The encoding of stochastic regularities is facilitated by action-effect predictions

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Betina Korka ◽  
Erich Schröger ◽  
Andreas Widmann
Keyword(s):  
Coding Theory ◽  
Predictive Coding ◽  
Event Related Potentials ◽  
Random Order ◽  
Generative Models ◽  
Higher Order ◽  
Action Effect ◽  
Related Potentials ◽  
Sensory Prediction ◽  
Action Intention

AbstractOur brains continuously build and update predictive models of the world, sources of prediction being drawn for example from sensory regularities and/or our own actions. Yet, recent results in the auditory system indicate that stochastic regularities may not be easily encoded when a rare medium pitch deviant is presented between frequent high and low pitch standard sounds in random order, as reflected in the lack of sensory prediction error event-related potentials [i.e., mismatch negativity (MMN)]. We wanted to test the implication of the predictive coding theory that predictions based on higher-order generative models—here, based on action intention, are fed top-down in the hierarchy to sensory levels. Participants produced random sequences of high and low pitch sounds by button presses in two conditions: In a “specific” condition, one button produced high and the other low pitch sounds; in an “unspecific” condition, both buttons randomly produced high or low-pitch sounds. Rare medium pitch deviants elicited larger MMN and N2 responses in the “specific” compared to the “unspecific” condition, despite equal sound probabilities. These results thus demonstrate that action-effect predictions can boost stochastic regularity-based predictions and engage higher-order deviance detection processes, extending previous notions on the role of action predictions at sensory levels.

Generative Adversarial Networks (GANs)

2021 ◽  
Vol 54 (3) ◽  
pp. 1-42
Author(s):  
Divya Saxena ◽  
Jiannong Cao
Keyword(s):  
Optimization Technique ◽  
Generative Models ◽  
Generative Adversarial Networks ◽  
Network Architectures ◽  
Research Directions ◽  
Research Issues ◽  
Design And Optimization ◽  
Adversarial Networks ◽  
Comprehensive Survey ◽  
Selection Of

Generative Adversarial Networks (GANs) is a novel class of deep generative models that has recently gained significant attention. GANs learn complex and high-dimensional distributions implicitly over images, audio, and data. However, there exist major challenges in training of GANs, i.e., mode collapse, non-convergence, and instability, due to inappropriate design of network architectre, use of objective function, and selection of optimization algorithm. Recently, to address these challenges, several solutions for better design and optimization of GANs have been investigated based on techniques of re-engineered network architectures, new objective functions, and alternative optimization algorithms. To the best of our knowledge, there is no existing survey that has particularly focused on the broad and systematic developments of these solutions. In this study, we perform a comprehensive survey of the advancements in GANs design and optimization solutions proposed to handle GANs challenges. We first identify key research issues within each design and optimization technique and then propose a new taxonomy to structure solutions by key research issues. In accordance with the taxonomy, we provide a detailed discussion on different GANs variants proposed within each solution and their relationships. Finally, based on the insights gained, we present promising research directions in this rapidly growing field.

Sign in / Sign up

Export Citation Format

Share Document