scholarly journals Developing and Evaluating Deep Neural Network-Based Denoising for Nanoparticle TEM Images with Ultra-Low Signal-to-Noise

2021 ◽  
pp. 1-17
Author(s):  
Joshua L. Vincent ◽  
Ramon Manzorro ◽  
Sreyas Mohan ◽  
Binh Tang ◽  
Dev Y. Sheth ◽  
...  
Keyword(s):  
Neural Network ◽  
Level Structure ◽  
Quantitative Measure ◽  
Pt Nanoparticles ◽  
Atomic Level ◽  
Ratio Test ◽  
Nanoparticle Surface ◽  
Noisy Observation ◽  
Gradient Based ◽  
Noisy Measurements

A deep convolutional neural network has been developed to denoise atomic-resolution transmission electron microscope image datasets of nanoparticles acquired using direct electron counting detectors, for applications where the image signal is severely limited by shot noise. The network was applied to a model system of CeO2-supported Pt nanoparticles. We leverage multislice image simulations to generate a large and flexible dataset for training the network. The proposed network outperforms state-of-the-art denoising methods on both simulated and experimental test data. Factors contributing to the performance are identified, including (a) the geometry of the images used during training and (b) the size of the network's receptive field. Through a gradient-based analysis, we investigate the mechanisms learned by the network to denoise experimental images. This shows that the network exploits both extended and local information in the noisy measurements, for example, by adapting its filtering approach when it encounters atomic-level defects at the nanoparticle surface. Extensive analysis has been done to characterize the network's ability to correctly predict the exact atomic structure at the nanoparticle surface. Finally, we develop an approach based on the log-likelihood ratio test that provides a quantitative measure of the agreement between the noisy observation and the atomic-level structure in the network-denoised image.

scholarly journals Neural network aided approximation and parameter inference of non-Markovian models of gene expression

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Qingchao Jiang ◽  
Xiaoming Fu ◽  
Shifu Yan ◽  
Runlai Li ◽  
Wenli Du ◽  
...  
Keyword(s):  
Neural Network ◽  
Stochastic Dynamics ◽  
Stochastic Simulations ◽  
Parameter Inference ◽  
Biochemical Processes ◽  
Markovian Models ◽  
The Neural Network ◽  
Large Numbers ◽  
Small Set ◽  
Noisy Measurements

AbstractNon-Markovian models of stochastic biochemical kinetics often incorporate explicit time delays to effectively model large numbers of intermediate biochemical processes. Analysis and simulation of these models, as well as the inference of their parameters from data, are fraught with difficulties because the dynamics depends on the system’s history. Here we use an artificial neural network to approximate the time-dependent distributions of non-Markovian models by the solutions of much simpler time-inhomogeneous Markovian models; the approximation does not increase the dimensionality of the model and simultaneously leads to inference of the kinetic parameters. The training of the neural network uses a relatively small set of noisy measurements generated by experimental data or stochastic simulations of the non-Markovian model. We show using a variety of models, where the delays stem from transcriptional processes and feedback control, that the Markovian models learnt by the neural network accurately reflect the stochastic dynamics across parameter space.

Gradient-based multi-focus image fusion method using convolution neural network

2021 ◽  
Vol 92 ◽  
pp. 107174
Author(s):  
Yang Zhou ◽  
Xiaomin Yang ◽  
Rongzhu Zhang ◽  
Kai Liu ◽  
Marco Anisetti ◽  
...  
Keyword(s):  
Neural Network ◽  
Image Fusion ◽  
Convolution Neural Network ◽  
Fusion Method ◽  
Gradient Based ◽  
Focus Image ◽  
Image Fusion Method

Hydrogen Storage in MgH2 Matrices: An Ab-Initio Study of Mg-MgH2 Interface

2008 ◽  
Vol 139 ◽  
pp. 23-28 ◽  
Author(s):  
Simone Giusepponi ◽  
Massimo Celino ◽  
Fabrizio Cleri ◽  
Amelia Montone
Keyword(s):  
Molecular Dynamics ◽  
Total Energy ◽  
Ab Initio ◽  
Atomic Hydrogen ◽  
Level Structure ◽  
Atomic Level ◽  
Work Of Adhesion ◽  
Ab Initio Study ◽  
Dynamics Method ◽  
Good Agreement

We studied the atomic-level structure of a model Mg-MgH2 interface by means of the Car-Parrinello molecular dynamics method (CPMD). The interface was characterized in terms of total energy calculations, and an estimate of the work of adhesion was given, in good agreement with experimental results on similar systems. Furthermore, the interface was studied in a range of temperatures of interest for the desorption of hydrogen. We determined the diffusivity of atomic hydrogen as a function of the temperature, and give an estimate of the desorption temperature.

scholarly journals Fpga Implementation of Precise Convolutional Neural Network for Extreme Learning Machine

2020 ◽  
Vol 9 (8) ◽  
pp. 470-480
Keyword(s):  
Neural Network ◽  
Receptive Field ◽  
Convolutional Neural Network ◽  
Computation Time ◽  
Field Approach ◽  
Pixel Array ◽  
Gradient Based ◽  
Feed Forward Neural Networks ◽  
Learning Machine ◽  
Hidden Layer

Feed-forward neural networks can be trained based on a gradient-descent based backpropagation algorithm. But, these algorithms require more computation time. Extreme Learning Machines (ELM’s) are time-efficient, and they are less complicated than the conventional gradient-based algorithm. In previous years, an SRAM based convolutional neural network using a receptive – field Approach was proposed. This neural network was used as an encoder for the ELM algorithm and was implemented on FPGA. But, this neural network used an inaccurate 3-stage pipelined parallel adder. Hence, this neural network generates imprecise stimuli to the hidden layer neurons. This paper presents an implementation of precise convolutional neural network for encoding in the ELM algorithm based on the receptive - field approach at the hardware level. In the third stage of the pipelined parallel adder, instead of approximating the output by using one 2-input 15-bit adder, one 4-input 14-bit adder is used. Also, an additional weighted pixel array block is used. This weighted pixel array improves the accuracy of generating 128 weighted pixels. This neural network was simulated using ModelSim-Altera 10.1d and synthesized using Quartus II 13.0 sp1. This neural network is implemented on Cyclone V FPGA and used for pattern recognition applications. Although this design consumes slightly more hardware resources, this design is more accurate compared to previously existing encoders

scholarly journals Inverse design of grating couplers using the policy gradient method from reinforcement learning

Nanophotonics ◽  
2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Sean Hooten ◽  
Raymond G. Beausoleil ◽  
Thomas Van Vaerenbergh
Keyword(s):  
Neural Network ◽  
Reinforcement Learning ◽  
Gradient Method ◽  
Photonic Devices ◽  
Inverse Design ◽  
Grating Couplers ◽  
Electromagnetic Devices ◽  
Policy Gradient ◽  
Gradient Based ◽  
Local Gradient

Abstract We present a proof-of-concept technique for the inverse design of electromagnetic devices motivated by the policy gradient method in reinforcement learning, named PHORCED (PHotonic Optimization using REINFORCE Criteria for Enhanced Design). This technique uses a probabilistic generative neural network interfaced with an electromagnetic solver to assist in the design of photonic devices, such as grating couplers. We show that PHORCED obtains better performing grating coupler designs than local gradient-based inverse design via the adjoint method, while potentially providing faster convergence over competing state-of-the-art generative methods. As a further example of the benefits of this method, we implement transfer learning with PHORCED, demonstrating that a neural network trained to optimize 8° grating couplers can then be re-trained on grating couplers with alternate scattering angles while requiring >10× fewer simulations than control cases.

Exploring the influence of atomic level structure, porosity, and stability of bismuth(iii) coordination polymers on electrocatalytic CO2 reduction

2021 ◽  
Author(s):  
Sara Frank ◽  
Erik Svensson Grape ◽  
Espen Drath Bøjesen ◽  
Rasmus Larsen ◽  
Paolo Lamagni ◽  
...  
Keyword(s):  
Coordination Polymers ◽  
Chemical Stability ◽  
Level Structure ◽  
Co2 Reduction ◽  
Atomic Level

The study maps out the dependence of porosity, bismuth-to-carbon ratio and chemical stability of bismuth-based MOFs on electrocatalytic CO2 reduction.

Weights Direct Determination of Feedforward Neural Networks without Iterative BP-Training

2010 ◽  
pp. 197-225 ◽  
Author(s):  
Yunong Zhang ◽  
Ning Tan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Direct Determination ◽  
Bp Neural Networks ◽  
Learning Rates ◽  
The Neural Network ◽  
Gradient Based ◽  
Artificial Neural ◽  
Output Behavior

Artificial neural networks (ANN), especially with error back-propagation (BP) training algorithms, have been widely investigated and applied in various science and engineering fields. However, the BP algorithms are essentially gradient-based iterative methods, which adjust the neural-network weights to bring the network input/output behavior into a desired mapping by taking a gradient-based descent direction. This kind of iterative neural-network (NN) methods has shown some inherent weaknesses, such as, 1) the possibility of being trapped into local minima, 2) the difficulty in choosing appropriate learning rates, and 3) the inability to design the optimal or smallest NN-structure. To resolve such weaknesses of BP neural networks, we have asked ourselves a special question: Could neural-network weights be determined directly without iterative BP-training? The answer appears to be YES, which is demonstrated in this chapter with three positive but different examples. In other words, a new type of artificial neural networks with linearly-independent or orthogonal activation functions, is being presented, analyzed, simulated and verified by us, of which the neural-network weights and structure could be decided directly and more deterministically as well (in comparison with usual conventional BP neural networks).

A Benchmark of Structural Variant Analysis Tools for Next Generation Sequencing Data

2013 ◽  
Vol 2 (4) ◽  
pp. 86-98
Author(s):  
Chatzinikolaou Panagiotis ◽  
Makris Christos ◽  
Dimitrios Vlachakis ◽  
Sophia Kossida
Keyword(s):  
Next Generation Sequencing ◽  
Level Structure ◽  
Atomic Level ◽  
Protein Sequencing ◽  
Next Generation Sequencing Data ◽  
Next Generation ◽  
Sequencing Data ◽  
Variant Analysis ◽  
Generation Sequencing

In language of genetics and biochemistry, sequencing is the determination of an unbranched biopolymer's primary structure. A sequence is a symbolic linear depiction, result of sequencing. This sequence is a succinct summary of the most of the sequenced molecule's atomic-level structure. (Most known is DNA-sequencing, RNA-sequencing, Protein-sequencing and Next-Generation-sequencing)

Sign in / Sign up

Export Citation Format

Share Document