scholarly journals Img2Mol - Accurate SMILES Recognition from Molecular Graphical Depictions

2021 ◽  
Author(s):  
Djork-Arné Clevert ◽  
Tuan Le ◽  
Robin Winter ◽  
Floriane Montanari
Keyword(s):  
Automatic Recognition ◽  
Molecular Structures ◽  
Challenging Problem ◽  
Fixed Size ◽  
Rigorous Evaluation ◽  
Neural Machine Translation ◽  
Neural Network Learning ◽  
Continuous Vector ◽  
Network Learning ◽  
Model Combining

<p>Automatic recognition of the molecular content of a molecule’s graphical depiction is an extremely challenging problem that remains largely unsolved despite decades of research. Recent advances in neural machine translation enable the auto-encoding of molecular structures in a continuous vector space of fixed size (latent representation) with low reconstruction errors. In this paper, we present a fast and accurate model combining a deep convolutional neural network learning from molecule depictions and a pre-trained decoder that translates the latent representation into the SMILES representation of the molecules. This combination allows to precisely infer a molecular structure from an image. Our rigorous evaluation show that Img2Mol is able to correctly translate up to 88% of the molecular depictions into their SMILES representation. A pretrained version of Img2Mol is made publicly available on GitHub for non-commercial users.</p>

scholarly journals Img2Mol - Accurate SMILES Recognition from Molecular Graphical Depictions

2021 ◽  
Author(s):  
Djork-Arné Clevert ◽  
Tuan Le ◽  
Robin Winter ◽  
Floriane Montanari
Keyword(s):  
Automatic Recognition ◽  
Molecular Structures ◽  
Challenging Problem ◽  
Fixed Size ◽  
Rigorous Evaluation ◽  
Neural Machine Translation ◽  
Neural Network Learning ◽  
Continuous Vector ◽  
Network Learning ◽  
Model Combining

<p>Automatic recognition of the molecular content of a molecule’s graphical depiction is an extremely challenging problem that remains largely unsolved despite decades of research. Recent advances in neural machine translation enable the auto-encoding of molecular structures in a continuous vector space of fixed size (latent representation) with low reconstruction errors. In this paper, we present a fast and accurate model combining a deep convolutional neural network learning from molecule depictions and a pre-trained decoder that translates the latent representation into the SMILES representation of the molecules. This combination allows to precisely infer a molecular structure from an image. Our rigorous evaluation show that Img2Mol is able to correctly translate up to 88% of the molecular depictions into their SMILES representation. A pretrained version of Img2Mol is made publicly available on GitHub for non-commercial users.</p>

scholarly journals Img2Mol - Accurate SMILES Recognition from Molecular Graphical Depictions

2021 ◽  
Author(s):  
Djork-Arné Clevert ◽  
Tuan Le ◽  
Robin Winter ◽  
Floriane Montanari
Keyword(s):  
Machine Translation ◽  
Automatic Recognition ◽  
Challenging Problem ◽  
Neural Machine Translation ◽  
Recent Advances

Automatic recognition of the molecular content of a molecule's graphical depiction is an extremely challenging problem that remains largely unsolved despite decades of research. Recent advances in neural machine translation...

Speed up Neural Network Learning by GPGPU

2011 ◽  
Vol 131 (11) ◽  
pp. 1889-1894
Author(s):  
Yuta Tsuchida ◽  
Michifumi Yoshioka
Keyword(s):  
Neural Network ◽  
Neural Network Learning ◽  
Network Learning ◽  
Speed Up

scholarly journals A Geometric Perspective on Information Plane Analysis

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 711
Author(s):  
Mina Basirat ◽  
Bernhard C. Geiger ◽  
Peter M. Roth
Keyword(s):  
Neural Network ◽  
Mutual Information ◽  
Geometric Interpretation ◽  
Neural Network Training ◽  
Neural Network Learning ◽  
Network Learning ◽  
Plane Analysis ◽  
Network Training ◽  
Hidden Layer ◽  
The Impact

Information plane analysis, describing the mutual information between the input and a hidden layer and between a hidden layer and the target over time, has recently been proposed to analyze the training of neural networks. Since the activations of a hidden layer are typically continuous-valued, this mutual information cannot be computed analytically and must thus be estimated, resulting in apparently inconsistent or even contradicting results in the literature. The goal of this paper is to demonstrate how information plane analysis can still be a valuable tool for analyzing neural network training. To this end, we complement the prevailing binning estimator for mutual information with a geometric interpretation. With this geometric interpretation in mind, we evaluate the impact of regularization and interpret phenomena such as underfitting and overfitting. In addition, we investigate neural network learning in the presence of noisy data and noisy labels.

LOCALLY IMPLEMENTABLE MATRIX FLOWS AND THEIR APPLICATION TO NEURAL NETWORK LEARNING

1994 ◽  
Vol 04 (01) ◽  
pp. 23-51 ◽  
Author(s):  
JEROEN DEHAENE ◽  
JOOS VANDEWALLE
Keyword(s):  
Neural Network ◽  
Signal Processing ◽  
Network Structure ◽  
Adaptive Signal Processing ◽  
External Signal ◽  
Neural Network Learning ◽  
Network Learning ◽  
Adaptive Signal

A number of matrix flows, based on isospectral and isodirectional flows, is studied and modified for the purpose of local implementability on a network structure. The flows converge to matrices with a predefined spectrum and eigenvectors which are determined by an external signal. The flows can be useful for adaptive signal processing applications and are applied to neural network learning.

Sign in / Sign up

Export Citation Format

Share Document