scholarly journals Network Bending: Expressive Manipulation of Generative Models in Multiple Domains

Entropy ◽  
2021 ◽  
Vol 24 (1) ◽  
pp. 28
Author(s):  
Terence Broad ◽  
Frederic Fol Leymarie ◽  
Mick Grierson
Keyword(s):  
Neural Network ◽  
Generative Models ◽  
Generative Model ◽  
Direct Manipulation ◽  
New Approach ◽  
Generative Process ◽  
Spatial Similarity ◽  
Broad Array ◽  
Multiple Domains ◽  
Novel Algorithm

This paper presents the network bending framework, a new approach for manipulating and interacting with deep generative models. We present a comprehensive set of deterministic transformations that can be inserted as distinct layers into the computational graph of a trained generative neural network and applied during inference. In addition, we present a novel algorithm for analysing the deep generative model and clustering features based on their spatial activation maps. This allows features to be grouped together based on spatial similarity in an unsupervised fashion. This results in the meaningful manipulation of sets of features that correspond to the generation of a broad array of semantically significant features of the generated results. We outline this framework, demonstrating our results on deep generative models for both image and audio domains. We show how it allows for the direct manipulation of semantically meaningful aspects of the generative process as well as allowing for a broad range of expressive outcomes.

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>

New Approach for 3D Mesh Retrieval Using Artificial Neural Network and Histogram of Features

2018 ◽  
Vol 10 (2) ◽  
pp. 84-94 ◽  
Author(s):  
M. Pershina ◽  
V.S. Bouksim ◽  
K. Arhid ◽  
F.R. Zakani ◽  
M. Aboulfatah ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
New Approach ◽  
3D Mesh ◽  
Artificial Neural

Equivariant Adversarial Network for Image-to-image Translation

2021 ◽  
Vol 17 (2s) ◽  
pp. 1-14
Author(s):  
Masoumeh Zareapoor ◽  
Jie Yang
Keyword(s):  
State Of The Art ◽  
Generative Models ◽  
Generative Model ◽  
Target Domain ◽  
Adversarial Network ◽  
Proposed Model ◽  
Image Translation ◽  
Great Performance ◽  
Representative Model ◽  
The Ideal

Image-to-Image translation aims to learn an image from a source domain to a target domain. However, there are three main challenges, such as lack of paired datasets, multimodality, and diversity, that are associated with these problems and need to be dealt with. Convolutional neural networks (CNNs), despite of having great performance in many computer vision tasks, they fail to detect the hierarchy of spatial relationships between different parts of an object and thus do not form the ideal representative model we look for. This article presents a new variation of generative models that aims to remedy this problem. We use a trainable transformer, which explicitly allows the spatial manipulation of data within training. This differentiable module can be augmented into the convolutional layers in the generative model, and it allows to freely alter the generated distributions for image-to-image translation. To reap the benefits of proposed module into generative model, our architecture incorporates a new loss function to facilitate an effective end-to-end generative learning for image-to-image translation. The proposed model is evaluated through comprehensive experiments on image synthesizing and image-to-image translation, along with comparisons with several state-of-the-art algorithms.

scholarly journals Fine-tuning of a generative neural network for designing multi-target compounds

2021 ◽  
Author(s):  
Thomas Blaschke ◽  
Jürgen Bajorath
Keyword(s):  
Neural Network ◽  
Small Molecules ◽  
De Novo ◽  
Pharmaceutical Research ◽  
Generative Models ◽  
Fine Tuning ◽  
Data Sets ◽  
Single Target ◽  
Fine Tune ◽  
Target Activity

AbstractExploring the origin of multi-target activity of small molecules and designing new multi-target compounds are highly topical issues in pharmaceutical research. We have investigated the ability of a generative neural network to create multi-target compounds. Data sets of experimentally confirmed multi-target, single-target, and consistently inactive compounds were extracted from public screening data considering positive and negative assay results. These data sets were used to fine-tune the REINVENT generative model via transfer learning to systematically recognize multi-target compounds, distinguish them from single-target or inactive compounds, and construct new multi-target compounds. During fine-tuning, the model showed a clear tendency to increasingly generate multi-target compounds and structural analogs. Our findings indicate that generative models can be adopted for de novo multi-target compound design.

Neural Network Generative Models for Radio Frequency Data

2021 ◽  
Author(s):  
Joseph Carmack ◽  
Amit Bhatia ◽  
Josh Robinson ◽  
John Majewski ◽  
Scott Kuzdeba
Keyword(s):  
Neural Network ◽  
Radio Frequency ◽  
Generative Models ◽  
Frequency Data

A New Approach to Machinery Monitoring and Diagnostics Using Self-Organizing Maps

1995 ◽  
Author(s):  
Siyu Zhang ◽  
R. Ganesan ◽  
T. S. Sankar
Keyword(s):  
Neural Network ◽  
Service Life ◽  
Trend Analysis ◽  
New Approach ◽  
Machine System ◽  
Network Algorithm ◽  
On Line ◽  
Neural Network Algorithm ◽  
Monitoring And Diagnostics ◽  
Self Organizing

Abstract The problem of estimating an unknown multivariate function from on-line vibration measurements, for determining the conditions of a machine system and for estimating its service life is considered. This problem is formulated into a multiple-index based trend analysis problem and the corresponding indices for trend analysis are extracted from the on-line vibration data. Selection of these indices is based on the simultaneous consideration of commonly-observed faults or malfunctions in the machine system being monitored. A neural network algorithm that has been developed by the present authors for multiple-index based regression is adapted to perform the trend analysis of a machine system. Applications of this neural network algorithm to the condition monitoring and life estimation of both a bearing system as well as a gearbox are fully demonstrated. The efficiency and computational supremacy of the new algorithm are established through comparing with the performance of Self-Organizing Mapping (SOM) and Constrained Topological Mapping (CTM) algorithms. Further, the usefulness of multiple-index based trend analysis in precisely predicting the condition and service life of a machine system is clearly demonstrated. Using on-line vibration signal to constitute the set of variables for trend analysis, and employing the newly-developed self-organizing neural algorithm for performing the trend analysis, a new approach is developed for machinery monitoring and diagnostics.

scholarly journals Deep neural network for orthogonal frequency division multiplexing systems without cyclic prefix transmission

2018 ◽  
Vol 189 ◽  
pp. 04016
Author(s):  
Viet-Hung Nguyen ◽  
Minh-Tuan Nguyen ◽  
Yong-Hwa Kim
Keyword(s):  
Neural Network ◽  
Orthogonal Frequency Division Multiplexing ◽  
Deep Neural Network ◽  
Cyclic Prefix ◽  
Wireless Transmission ◽  
Frequency Division Multiplexing ◽  
Frequency Division ◽  
Ofdm System ◽  
New Approach ◽  
Multiplexing Systems

Orthogonal frequency division multiplexing (OFDM) is widely used in wired or wireless transmission systems. In the structure of OFDM, a cycle prefix (CP) has been exploited to avoid the effects of inter-symbol interference (ISI) and inter-carrier interference (ICI). This paper proposes a new approach to transmit the signals without CP transmission. Using the deep neural network, the proposed OFDM system transmits data without the CP. Simulation results show that the proposed scheme can estimate the CP at the receiver and overcome the effect of ISI.

scholarly journals Monte Carlo and Reconstruction Membership Inference Attacks against Generative Models

2019 ◽  
Vol 2019 (4) ◽  
pp. 232-249 ◽  
Author(s):  
Benjamin Hilprecht ◽  
Martin Härterich ◽  
Daniel Bernau
Keyword(s):  
Data Privacy ◽  
Information Leakage ◽  
Generative Models ◽  
Generative Model ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Data Sets ◽  
Success Rates ◽  
Model Quality ◽  
Type Formalization

Abstract We present two information leakage attacks that outperform previous work on membership inference against generative models. The first attack allows membership inference without assumptions on the type of the generative model. Contrary to previous evaluation metrics for generative models, like Kernel Density Estimation, it only considers samples of the model which are close to training data records. The second attack specifically targets Variational Autoencoders, achieving high membership inference accuracy. Furthermore, previous work mostly considers membership inference adversaries who perform single record membership inference. We argue for considering regulatory actors who perform set membership inference to identify the use of specific datasets for training. The attacks are evaluated on two generative model architectures, Generative Adversarial Networks (GANs) and Variational Autoen-coders (VAEs), trained on standard image datasets. Our results show that the two attacks yield success rates superior to previous work on most data sets while at the same time having only very mild assumptions. We envision the two attacks in combination with the membership inference attack type formalization as especially useful. For example, to enforce data privacy standards and automatically assessing model quality in machine learning as a service setups. In practice, our work motivates the use of GANs since they prove less vulnerable against information leakage attacks while producing detailed samples.

Sign in / Sign up

Export Citation Format

Share Document