scholarly journals Towards a Generic Neural Network Architecture for Approximating Tone Mapping Algorithms

2021 ◽  
Vol 2021 (1) ◽  
pp. 93-96
Jake McVey ◽  
Graham Finlayson

Tone curves are a key feature in any image processing pipeline, and are used to change the pixel values of an input image to find an output image that looks better. Perhaps the most widely deployed tone curve algorithm is Contrast Limited Histogram Equalisation (CLHE). CLHE is an iterative algorithm that tone maps an input image so that the histogram of the output is (approximately) maximally uniform subject to the constraint that the tone curve has bounded slope (neither too large or too small).In this paper, we build upon a neural network framework [1] that was recently developed to deliver CLHE in fewer iterations (each layer in the neural network is analogous to a single iteration of CLHE, but the network has fewer layers than the number of iterations needed by CLHE). The key contribution of this paper is to show that the same network architecture can be used to implement a more complex (and more powerful) tone mapping algorithm. Experiments validate our method.

2020 ◽  
Vol 44 (5) ◽  
pp. 737-745
A. Sheshkus ◽  
A. Chirvonaya ◽  
D. Matveev ◽  
D. Nikolaev ◽  
V.L. Arlazarov

In this paper, we suggest a new neural network architecture for vanishing point detection in images. The key element is the use of the direct and transposed fast Hough transforms separated by convolutional layer blocks with standard activation functions. It allows us to get the answer in the coordinates of the input image at the output of the network and thus to calculate the coordinates of the vanishing point by simply selecting the maximum. Besides, it was proved that calculation of the transposed fast Hough transform can be performed using the direct one. The use of integral operators enables the neural network to rely on global rectilinear features in the image, and so it is ideal for detecting vanishing points. To demonstrate the effectiveness of the proposed architecture, we use a set of images from a DVR and show its superiority over existing methods. Note, in addition, that the proposed neural network architecture essentially repeats the process of direct and back projection used, for example, in computed tomography.

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Oleksii VASYLIEV ◽  

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

2021 ◽  
Vol 12 (6) ◽  
pp. 1-21
Jayant Gupta ◽  
Carl Molnar ◽  
Yiqun Xie ◽  
Joe Knight ◽  
Shashi Shekhar

Spatial variability is a prominent feature of various geographic phenomena such as climatic zones, USDA plant hardiness zones, and terrestrial habitat types (e.g., forest, grasslands, wetlands, and deserts). However, current deep learning methods follow a spatial-one-size-fits-all (OSFA) approach to train single deep neural network models that do not account for spatial variability. Quantification of spatial variability can be challenging due to the influence of many geophysical factors. In preliminary work, we proposed a spatial variability aware neural network (SVANN-I, formerly called SVANN ) approach where weights are a function of location but the neural network architecture is location independent. In this work, we explore a more flexible SVANN-E approach where neural network architecture varies across geographic locations. In addition, we provide a taxonomy of SVANN types and a physics inspired interpretation model. Experiments with aerial imagery based wetland mapping show that SVANN-I outperforms OSFA and SVANN-E performs the best of all.

Raghuram Mandyam Annasamy ◽  
Katia Sycara

Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these networks seem to learn, are far behind. In this paper we propose an interpretable neural network architecture for Q-learning which provides a global explanation of the model’s behavior using key-value memories, attention and reconstructible embeddings. With a directed exploration strategy, our model can reach training rewards comparable to the state-of-the-art deep Q-learning models. However, results suggest that the features extracted by the neural network are extremely shallow and subsequent testing using out-of-sample examples shows that the agent can easily overfit to trajectories seen during training.

2019 ◽  
Vol 12 (S10) ◽  
Jie Hao ◽  
Youngsoon Kim ◽  
Tejaswini Mallavarapu ◽  
Jung Hun Oh ◽  
Mingon Kang

Abstract Background Understanding the complex biological mechanisms of cancer patient survival using genomic and clinical data is vital, not only to develop new treatments for patients, but also to improve survival prediction. However, highly nonlinear and high-dimension, low-sample size (HDLSS) data cause computational challenges to applying conventional survival analysis. Results We propose a novel biologically interpretable pathway-based sparse deep neural network, named Cox-PASNet, which integrates high-dimensional gene expression data and clinical data on a simple neural network architecture for survival analysis. Cox-PASNet is biologically interpretable where nodes in the neural network correspond to biological genes and pathways, while capturing the nonlinear and hierarchical effects of biological pathways associated with cancer patient survival. We also propose a heuristic optimization solution to train Cox-PASNet with HDLSS data. Cox-PASNet was intensively evaluated by comparing the predictive performance of current state-of-the-art methods on glioblastoma multiforme (GBM) and ovarian serous cystadenocarcinoma (OV) cancer. In the experiments, Cox-PASNet showed out-performance, compared to the benchmarking methods. Moreover, the neural network architecture of Cox-PASNet was biologically interpreted, and several significant prognostic factors of genes and biological pathways were identified. Conclusions Cox-PASNet models biological mechanisms in the neural network by incorporating biological pathway databases and sparse coding. The neural network of Cox-PASNet can identify nonlinear and hierarchical associations of genomic and clinical data to cancer patient survival. The open-source code of Cox-PASNet in PyTorch implemented for training, evaluation, and model interpretation is available at:

Manish Kumar ◽  
Devendra P. Garg

Design of an efficient fuzzy logic controller involves the optimization of parameters of fuzzy sets and proper choice of rule base. There are several techniques reported in recent literature that use neural network architecture and genetic algorithms to learn and optimize a fuzzy logic controller. This paper presents methodologies to learn and optimize fuzzy logic controller parameters that use learning capabilities of neural network. Concepts of model predictive control (MPC) have been used to obtain optimal signal to train the neural network via backpropagation. The strategies developed have been applied to control an inverted pendulum and results have been compared for two different fuzzy logic controllers developed with the help of neural networks. The first neural network emulates a PD controller, while the second controller is developed based on MPC. The proposed approach can be applied to learn fuzzy logic controller parameter online via the use of dynamic backpropagation. The results show that the Neuro-Fuzzy approaches were able to learn rule base and identify membership function parameters accurately.

2021 ◽  
Vol 11 (1) ◽  
Francisco J. Bravo Sanchez ◽  
Md Rahat Hossain ◽  
Nathan B. English ◽  
Steven T. Moore

AbstractThe use of autonomous recordings of animal sounds to detect species is a popular conservation tool, constantly improving in fidelity as audio hardware and software evolves. Current classification algorithms utilise sound features extracted from the recording rather than the sound itself, with varying degrees of success. Neural networks that learn directly from the raw sound waveforms have been implemented in human speech recognition but the requirements of detailed labelled data have limited their use in bioacoustics. Here we test SincNet, an efficient neural network architecture that learns from the raw waveform using sinc-based filters. Results using an off-the-shelf implementation of SincNet on a publicly available bird sound dataset (NIPS4Bplus) show that the neural network rapidly converged reaching accuracies of over 65% with limited data. Their performance is comparable with traditional methods after hyperparameter tuning but they are more efficient. Learning directly from the raw waveform allows the algorithm to select automatically those elements of the sound that are best suited for the task, bypassing the onerous task of selecting feature extraction techniques and reducing possible biases. We use publicly released code and datasets to encourage others to replicate our results and to apply SincNet to their own datasets; and we review possible enhancements in the hope that algorithms that learn from the raw waveform will become useful bioacoustic tools.

2016 ◽  
Vol 12 (2) ◽  
pp. 61-64 ◽  
Vitaly M Tatyankin

An approach to the formation of an efficient pattern recognition algorithm. Under efficiency, understood as a zero error, resulting in the identification of the images on the test sample. As a test sample is considered an open database of images of handwritten digits MNIST.

This paper describes the use of a novel gradient based recurrent neural network to perform Capon spectral estimation. Nowadays, in the fastest algorithm proposed by Marple et al., the computational burden still remains significant in the calculation of the autoregressive (AR) Parameters. In this paper we propose to use a gradient based neural network to compute the AR parameters by solving the Yule-Walker equations. Furthermore, to reduce the complexity of the neural network architecture, the weights matrixinputs vector product is performed efficiently using the fast Fourier transform. Simulation results show that proposed neural network and its simplified architecture lead to the same results as the original method which prove the correctness of the proposed scheme.

Krasimir Ognyanov Slavyanov

This article offers a neural network method for automatic classification of Inverse Synthetic Aperture Radar objects represented in images with high level of post-receive optimization. A full explanation of the procedures of two-layer neural network architecture creating and training is described. The classification in the recognition stage is proposed, based on several main classes or sets of flying objects. The classification sets are designed according to distinctive specifications in the structural models of the aircrafts. The neural network is experimentally simulated in MATLAB environment. Numerical results of the experiments carried, prove the correct classification of the objects in ISAR optimized images.

Sign in / Sign up

Export Citation Format

Share Document