scholarly journals DECIMER: towards deep learning for chemical image recognition

2020 ◽  
Vol 12 (1) ◽  
Author(s):  
Kohulan Rajan ◽  
Achim Zielesny ◽  
Christoph Steinbeck
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Open Data ◽  
Data Representation ◽  
Training Data ◽  
Training Time ◽  
Training Structures ◽  
Training Success ◽  
Traditional Approaches ◽  
Chemical Image

Abstract The automatic recognition of chemical structure diagrams from the literature is an indispensable component of workflows to re-discover information about chemicals and to make it available in open-access databases. Here we report preliminary findings in our development of Deep lEarning for Chemical ImagE Recognition (DECIMER), a deep learning method based on existing show-and-tell deep neural networks, which makes very few assumptions about the structure of the underlying problem. It translates a bitmap image of a molecule, as found in publications, into a SMILES. The training state reported here does not yet rival the performance of existing traditional approaches, but we present evidence that our method will reach a comparable detection power with sufficient training time. Training success of DECIMER depends on the input data representation: DeepSMILES are superior over SMILES and we have a preliminary indication that the recently reported SELFIES outperform DeepSMILES. An extrapolation of our results towards larger training data sizes suggests that we might be able to achieve near-accurate prediction with 50 to 100 million training structures. This work is entirely based on open-source software and open data and is available to the general public for any purpose.

scholarly journals DECIMER - Towards Deep Learning for Chemical Image Recognition

2020 ◽  
Author(s):  
Kohulan Rajan ◽  
Achim Zielesny ◽  
Christoph Steinbeck
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Open Data ◽  
Data Representation ◽  
Training Data ◽  
Training Time ◽  
Training Structures ◽  
Training Success ◽  
Traditional Approaches ◽  
Chemical Image

The automatic recognition of chemical structure diagrams from the literature is an indispensable component of workflows to re-discover information about chemicals and to make it available in open-access databases. Here we report preliminary findings in our development of DECIMER (Deep lEarning for Chemical ImagE Recognition), a deep learning method based on existing show-and-tell deep neural networks which makes very few assumptions about the structure of the underlying problem. The training state reported here does not yet rival the performance of existing traditional approaches, but we present evidence that our method will reach a comparable detection power with sufficient training time. Training success of DECIMER depends on the input data representation: DeepSMILES are clearly superior over SMILES and we have preliminary indication that the recently reported SELFIES outperform DeepSMILES. An extrapolation of our results towards larger training data sizes suggest that we might be able to achieve >90% accuracy with about 60 to 100 million training structures, so that training can be completed within several months on a single GPU. This work is completely based on open-source software and open data and is available to the general public for any purpose.

scholarly journals DECIMER - Towards Deep Learning for Chemical Image Recognition

2020 ◽  
Author(s):  
Kohulan Rajan ◽  
Achim Zielesny ◽  
Christoph Steinbeck
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Open Data ◽  
Data Representation ◽  
Training Data ◽  
Training Time ◽  
Training Structures ◽  
Training Success ◽  
Traditional Approaches ◽  
Chemical Image

The automatic recognition of chemical structure diagrams from the literature is an indispensable component of workflows to re-discover information about chemicals and to make it available in open-access databases. Here we report preliminary findings in our development of DECIMER (Deep lEarning for Chemical ImagE Recognition), a deep learning method based on existing show-and-tell deep neural networks which makes very few assumptions about the structure of the underlying problem. The training state reported here does not yet rival the performance of existing traditional approaches, but we present evidence that our method will reach a comparable detection power with sufficient training time. Training success of DECIMER depends on the input data representation: DeepSMILES are clearly superior over SMILES and we have preliminary indication that the recently reported SELFIES outperform DeepSMILES. An extrapolation of our results towards larger training data sizes suggest that we might be able to achieve >90% accuracy with about 60 to 100 million training structures, so that training can be completed within several months on a single GPU. This work is completely based on open-source software and open data and is available to the general public for any purpose.

scholarly journals DECIMER - Towards Deep Learning for Chemical Image Recognition

2020 ◽  
Author(s):  
Kohulan Rajan ◽  
Achim Zielesny ◽  
Christoph Steinbeck
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Open Data ◽  
Data Representation ◽  
Training Data ◽  
Training Time ◽  
Training Structures ◽  
Training Success ◽  
Traditional Approaches ◽  
Chemical Image

The automatic recognition of chemical structure diagrams from the literature is an indispensable component of workflows to re-discover information about chemicals and to make it available in open-access databases. Here we report preliminary findings in our development of DECIMER (Deep lEarning for Chemical ImagE Recognition), a deep learning method based on existing show-and-tell deep neural networks which makes very few assumptions about the structure of the underlying problem. The training state reported here does not yet rival the performance of existing traditional approaches, but we present evidence that our method will reach a comparable detection power with sufficient training time. Training success of DECIMER depends on the input data representation: DeepSMILES are clearly superior over SMILES and we have preliminary indication that the recently reported SELFIES outperform DeepSMILES. An extrapolation of our results towards larger training data sizes suggest that we might be able to achieve >90% accuracy with about 60 to 100 million training structures, so that training can be completed within several months on a single GPU. This work is completely based on open-source software and open data and is available to the general public for any purpose.

scholarly journals Batch Effect Removal via Batch-Free Encoding

2018 ◽  
Author(s):  
Uri Shaham
Keyword(s):  
Deep Learning ◽  
Biological Properties ◽  
Batch Effect ◽  
Training Data ◽  
Rna Seq ◽  
Batch Effects ◽  
Training Time ◽  
Learning Techniques ◽  
Downstream Analysis ◽  
Biological Patterns

AbstractBiological measurements often contain systematic errors, also known as “batch effects”, which may invalidate downstream analysis when not handled correctly. The problem of removing batch effects is of major importance in the biological community. Despite recent advances in this direction via deep learning techniques, most current methods may not fully preserve the true biological patterns the data contains. In this work we propose a deep learning approach for batch effect removal. The crux of our approach is learning a batch-free encoding of the data, representing its intrinsic biological properties, but not batch effects. In addition, we also encode the systematic factors through a decoding mechanism and require accurate reconstruction of the data. Altogether, this allows us to fully preserve the true biological patterns represented in the data. Experimental results are reported on data obtained from two high throughput technologies, mass cytometry and single-cell RNA-seq. Beyond good performance on training data, we also observe that our system performs well on test data obtained from new patients, which was not available at training time. Our method is easy to handle, a publicly available code can be found at https://github.com/ushaham/BatchEffectRemoval2018.

scholarly journals Human-Like Sketch Object Recognition via Analogical Learning

2019 ◽  
Vol 33 ◽  
pp. 1336-1343
Author(s):  
Kezhen Chen ◽  
Irina Rabkina ◽  
Matthew D. McLure ◽  
Kenneth D. Forbus
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Object Recognition ◽  
Image Recognition ◽  
Visual Representations ◽  
Learning Systems ◽  
Training Data ◽  
Adversarial Examples ◽  
Analogical Learning

Deep learning systems can perform well on some image recognition tasks. However, they have serious limitations, including requiring far more training data than humans do and being fooled by adversarial examples. By contrast, analogical learning over relational representations tends to be far more data-efficient, requiring only human-like amounts of training data. This paper introduces an approach that combines automatically constructed qualitative visual representations with analogical learning to tackle a hard computer vision problem, object recognition from sketches. Results from the MNIST dataset and a novel dataset, the Coloring Book Objects dataset, are provided. Comparison to existing approaches indicates that analogical generalization can be used to identify sketched objects from these datasets with several orders of magnitude fewer examples than deep learning systems require.

scholarly journals Examining Deep Learning Architectures for Crime Classification and Prediction

Forecasting ◽  
2021 ◽  
Vol 3 (4) ◽  
pp. 741-762
Author(s):  
Panagiotis Stalidis ◽  
Theodoros Semertzidis ◽  
Petros Daras
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Open Data ◽  
Training Data ◽  
Crime Prediction ◽  
Crime Types ◽  
Improved Performance ◽  
Learning Architectures ◽  
And Training ◽  
Crime Classification

In this paper, a detailed study on crime classification and prediction using deep learning architectures is presented. We examine the effectiveness of deep learning algorithms in this domain and provide recommendations for designing and training deep learning systems for predicting crime areas, using open data from police reports. Having time-series of crime types per location as training data, a comparative study of 10 state-of-the-art methods against 3 different deep learning configurations is conducted. In our experiments with 5 publicly available datasets, we demonstrate that the deep learning-based methods consistently outperform the existing best-performing methods. Moreover, we evaluate the effectiveness of different parameters in the deep learning architectures and give insights for configuring them to achieve improved performance in crime classification and finally crime prediction.

scholarly journals Performance of chemical structure string representations for chemical image recognition using transformers

2022 ◽  
Author(s):  
Kohulan Rajan ◽  
Christoph Steinbeck ◽  
Achim Zielesny
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Chemical Structure ◽  
Chemical Image

The use of molecular string representations for deep learning in chemistry has been steadily increasing in recent years. The complexity of existing string representations, and the difficulty in creating meaningful...

scholarly journals DECIMER 1.0: deep learning for chemical image recognition using transformers

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Kohulan Rajan ◽  
Achim Zielesny ◽  
Christoph Steinbeck
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Chemical Structure ◽  
Learning Approaches ◽  
Chemical Structures ◽  
Structure Recognition ◽  
Best Fitting ◽  
Preliminary Communication ◽  
Computational Intelligence Methods ◽  
Chemical Image

AbstractThe amount of data available on chemical structures and their properties has increased steadily over the past decades. In particular, articles published before the mid-1990 are available only in printed or scanned form. The extraction and storage of data from those articles in a publicly accessible database are desirable, but doing this manually is a slow and error-prone process. In order to extract chemical structure depictions and convert them into a computer-readable format, Optical Chemical Structure Recognition (OCSR) tools were developed where the best performing OCSR tools are mostly rule-based. The DECIMER (Deep lEarning for Chemical ImagE Recognition) project was launched to address the OCSR problem with the latest computational intelligence methods to provide an automated open-source software solution. Various current deep learning approaches were explored to seek a best-fitting solution to the problem. In a preliminary communication, we outlined the prospect of being able to predict SMILES encodings of chemical structure depictions with about 90% accuracy using a dataset of 50–100 million molecules. In this article, the new DECIMER model is presented, a transformer-based network, which can predict SMILES with above 96% accuracy from depictions of chemical structures without stereochemical information and above 89% accuracy for depictions with stereochemical information.

A Broad Transfer Learning Algorithm for Classification of Bearing Faults

2020 ◽  
Author(s):  
Guokai Liu ◽  
Liang Gao ◽  
Weiming Shen ◽  
Andrew Kusiak
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Manufacturing Industry ◽  
Domain Adaptation ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Training Data ◽  
Training Time ◽  
Bearing Faults

Abstract Condition monitoring and fault diagnosis are of great interest to the manufacturing industry. Deep learning algorithms have shown promising results in equipment prognostics and health management. However, their success has been hindered by excessive training time. In addition, deep learning algorithms face the domain adaptation dilemma encountered in dynamic application environments. The emerging concept of broad learning addresses the training time and the domain adaptation issue. In this paper, a broad transfer learning algorithm is proposed for the classification of bearing faults. Data of the same frequency is used to construct one- and two-dimensional training data sets to analyze performance of the broad transfer and deep learning algorithms. A broad learning algorithm contains two main layers, an augmented feature layer and a classification layer. The broad learning algorithm with a sparse auto-encoder is employed to extract features. The optimal solution of a redefined cost function with a limited sample size to ten per class in the target domain offers the classifier of broad learning domain adaptation capability. The effectiveness of the proposed algorithm has been demonstrated on a benchmark dataset. Computational experiments have demonstrated superior efficiency and accuracy of the proposed algorithm over the deep learning algorithms tested.

Sign in / Sign up

Export Citation Format

Share Document