Deep Artificial Neural Networks Research Articles

How Can (or Why Should) Process Engineering Aid the Screening and Discovery of Solid Sorbents for CO2 Capture?

ConspectusAdsorption using solid sorbents is emerging as a serious contender to amine-based liquid absorption for postcombustion CO2 capture. In the last 20+ years, significant efforts have been invested in developing adsorption processes for CO2 capture. In particular, significant efforts have been invested in developing new adsorbents for this application. These efforts have led to the generation of hundreds of thousands of (hypothetical and real) adsorbents, e.g., zeolites and metal-organic frameworks (MOFs). Identifying the right adsorbent for CO2 capture remains a challenging task. Most studies are focused on identifying adsorbents based on certain adsorption metrics. Recent studies have demonstrated that the performance of an adsorbent is intimately linked to the process in which it is deployed. Any meaningful screening should thus consider the complexity of the process. However, simulation and optimization of adsorption processes are computationally intensive, as they constitute the simultaneous propagation of heat and mass transfer fronts; the process is cyclic, and there are no straightforward design tools, thereby making large-scale process-informed screening of sorbents prohibitive.This Account discusses four papers that develop computational methods to incorporate process-based evaluation for both bottom-up (chemistry to engineering) screening problems and top-down (engineering to chemistry) inverse problems. We discuss the development of the machine-assisted adsorption process learning and emulation (MAPLE) framework, a surrogate model based on deep artificial neural networks (ANNs) that can predict process-level performance by considering both process and material inputs. The framework, which has been experimentally validated, allows for reliable, process-informed screening of large adsorbent databases. We then discuss how process engineering tools can be used beyond adsorbent screening, i.e., to estimate the practically achievable performance and cost limits of pressure vacuum swing adsorption (PVSA) processes should the ideal bespoke adsorbent be made. These studies show what conditions stand-alone PVSA processes are attractive and when they should not be considered. Finally, recent developments in physics-informed neural networks (PINNS) enable the rapid solution of complex partial differential equations, providing tools to potentially identify optimal cycle configurations. Ultimately, we provide areas where further developments are required and emphasize the need for strong collaborations between chemists and chemical engineers to move rapidly from discovery to field trials, as we do not have much time to fulfill commitments to net-zero targets.

From black box to clear box: A hypothesis testing framework for scalar regression problems using deep artificial neural networks

Despite the impressive predictive performance exhibited by deep learning across various domains, its application in research models within the social and behavioral sciences has been limited. Deep learning lacks human-accessible interpretability and does not provide statistical inferences. To address these limitations, this article presents a novel model-agnostic hypothesis testing framework tailored to scalar regression problems using deep artificial neural networks. The new framework not only determines each input variable’s direction of influence and statistical significance, but computes effect size measures akin to Cohen’s f2 in traditional ordinary least squares (OLS) regression models. Effect sizes are an important complement to null hypothesis significance testing by providing a practical significance measure that is independent of sample size considerations. To showcase the usefulness of the new framework, its application is demonstrated on both an artificial data set and a social survey using a Python sandbox implementation.

Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing

AbstractIn financial engineering, prices of financial products are computed approximately many times each trading day with (slightly) different parameters in each calculation. In many financial models such prices can be approximated by means of Monte Carlo (MC) simulations. To obtain a good approximation the MC sample size usually needs to be considerably large resulting in a long computing time to obtain a single approximation. A natural deep learning approach to reduce the computation time when new prices need to be calculated as quickly as possible would be to train an artificial neural network (ANN) to learn the function which maps parameters of the model and of the financial product to the price of the financial product. However, empirically it turns out that this approach leads to approximations with unacceptably high errors, in particular when the error is measured in the ‐norm, and it seems that ANNs are not capable to closely approximate prices of financial products in dependence on the model and product parameters in real life applications. This is not entirely surprising given the high‐dimensional nature of the problem and the fact that it has recently been proved for a large class of algorithms, including the deep learning approach outlined above, that such methods are in general not capable to overcome the curse of dimensionality for such approximation problems in the ‐norm. In this article we introduce a new numerical approximation strategy for parametric approximation problems including the parametric financial pricing problems described above and we illustrate by means of several numerical experiments that the introduced approximation strategy achieves a very high accuracy for a variety of high‐dimensional parametric approximation problems, even in the ‐norm. A central aspect of the approximation strategy proposed in this article is to combine MC algorithms with machine learning techniques to, roughly speaking, learn the random variables (LRV) in MC simulations. In other words, we employ stochastic gradient descent (SGD) optimization methods not to train parameters of standard ANNs but instead to learn random variables appearing in MC approximations. In that sense, the proposed LRV strategy has strong links to Quasi‐Monte Carlo (QMC) methods as well as to the field of algorithm learning. Our numerical simulations strongly indicate that the LRV strategy might indeed be capable to overcome the curse of dimensionality in the ‐norm in several cases where the standard deep learning approach has been proven not to be able to do so. This is not a contradiction to the established lower bounds mentioned above because this new LRV strategy is outside of the class of algorithms for which lower bounds have been established in the scientific literature. The proposed LRV strategy is of general nature and not only restricted to the parametric financial pricing problems described above, but applicable to a large class of approximation problems. In this article we numerically test the LRV strategy in the case of the pricing of European call options in the Black‐Scholes model with one underlying asset, in the case of the pricing of European worst‐of basket put options in the Black‐Scholes model with three underlying assets, in the case of the pricing of European average put options in the Black‐Scholes model with three underlying assets and knock‐in barriers, as well as in the case of stochastic Lorentz equations. For these examples the LRV strategy produces highly convincing numerical results when compared with standard MC simulations, QMC simulations using Sobol sequences, SGD‐trained shallow ANNs, and SGD‐trained deep ANNs.

Standard-based personalized healthcare delivery for kidney illness using deep learning

Motivation and objective. Predictive analytics is an active area of research in healthcare. It aims to provide better services to the patient and helps the medical practitioners to know what particular treatment would be suitable for a patient based on their past data. Deep learning is an emerging branch of machine learning in which deep artificial neural networks are used to learn a specific pattern for mapping input to output. It has revolutionized predictive analytics by achieving far better accuracy than conventional learning models. This paper aims to analyze the effect of deep learning on a standardized electronic health records dataset by diagnosing kidney-related diseases. Approach. The current study uses a general modularized deep learning architecture called encoder-combiner-decoder (ECD), which offers a robust framework. The model’s performance is enhanced by the availability of variations and extensions to the basic ECD architecture, corresponding to respective input and output feature types. The openEHR benchmark dataset (ORBDA) is used to train the model. It is a real-world dataset that has been provided by the Brazilian Public Health System through the SUS (DATASUS) Database Department of Informatics. Results. In the current research, the model trained using deep learning on the part of this benchmark dataset can help in diagnosing kidney-related illnesses. The evaluation metrics show high precision, recall, and F1 score for kidney-related diseases, meaning that they can be identified almost every time. Significance. The model is a novel attempt to analyze a standardized healthcare dataset that can be deployed in medical institutions in order for its performance to be evaluated by a medical professional.

Enhancing EDM Machining Precision through Deep Cryogenically Treated Electrodes and ANN Modelling Approach.

The critical applications of difficult-to-machine Inconel 617 (IN617) compel the process to be accurate enough that the requirement of tight tolerances can be met. Electric discharge machining (EDM) is commonly engaged in its machining. However, the intrinsic issue of over/undercut in EDM complicates the achievement of accurately machined profiles. Therefore, the proficiency of deep cryogenically treated (DCT) copper (Cu) and brass electrodes under modified dielectrics has been thoroughly investigated to address the issue. A complete factorial design was implemented to machine a 300 μm deep impression on IN617. The machining ability of DCT electrodes averagely gave better dimensional accuracy as compared to non-DCT electrodes by 13.5% in various modified dielectric mediums. The performance of DCT brass is 29.7% better overall compared to the average value of overcut (OC) given by DCT electrodes. Among the non-treated (NT) electrodes, the performance of Cu stands out when employing a Kerosene-Span-20 modified dielectric. In comparison to Kerosene-Tween-80, the value of OC is 33.3% less if Kerosene-Span-20 is used as a dielectric against the aforementioned NT electrode. Finally, OC's nonlinear and complex phenomena are effectively modeled by an artificial neural network (ANN) with good prediction accuracy, thereby eliminating the need for experiments.

ROOD-MRI: Benchmarking the robustness of deep learning segmentation models to out-of-distribution and corrupted data in MRI

Deep artificial neural networks (DNNs) have moved to the forefront of medical image analysis due to their success in classification, segmentation, and detection challenges. A principal challenge in large-scale deployment of DNNs in neuroimage analysis is the potential for shifts in signal-to-noise ratio, contrast, resolution, and presence of artifacts from site to site due to variances in scanners and acquisition protocols. DNNs are famously susceptible to these distribution shifts in computer vision. Currently, there are no benchmarking platforms or frameworks to assess the robustness of new and existing models to specific distribution shifts in MRI, and accessible multi-site benchmarking datasets are still scarce or task-specific. To address these limitations, we propose ROOD-MRI: a novel platform for benchmarking the Robustness of DNNs to Out-Of-Distribution (OOD) data, corruptions, and artifacts in MRI. This flexible platform provides modules for generating benchmarking datasets using transforms that model distribution shifts in MRI, implementations of newly derived benchmarking metrics for image segmentation, and examples for using the methodology with new models and tasks. We apply our methodology to hippocampus, ventricle, and white matter hyperintensity segmentation in several large studies, providing the hippocampus dataset as a publicly available benchmark. By evaluating modern DNNs on these datasets, we demonstrate that they are highly susceptible to distribution shifts and corruptions in MRI. We show that while data augmentation strategies can substantially improve robustness to OOD data for anatomical segmentation tasks, modern DNNs using augmentation still lack robustness in more challenging lesion-based segmentation tasks. We finally benchmark U-Nets and vision transformers, finding robustness susceptibility to particular classes of transforms across architectures. The presented open-source platform enables generating new benchmarking datasets and comparing across models to study model design that results in improved robustness to OOD data and corruptions in MRI.

核検知及び核セキュリティ事案初動対応を支援する深層ニューラルネットワークを用いた核種判定アルゴリズム

Rapid and precise radioisotope identification in the scene of nuclear detection and nuclear security incidents is one of the challenging issues for the prompt response to the detection alarm or the incidents. A radioisotope identification algorithm using a deep artificial neural network model applicable to handheld γ-ray detectors has been proposed in the present paper. The proposed algorithm automatically identifies gamma-emitting radioisotopes based on the count contribution ratio (CCR) from each of them estimated by the deep artificial neural network model trained by simulated γ-ray spectra. The automated radioisotope identification algorithm can support first responders of nuclear detection and nuclear security incidents without sufficient experience and knowledge in radiation measurement. The authors tested the performance of the proposed algorithm using two different types of deep artificial neural network models in application to handheld detectors having high or low energy resolution. The proposed algorithm showed high performance in identifying artificial radioisotopes for actually measured γ-ray spectra. It was also confirmed that the algorithm is applicable to identifying 235U and automated uranium categorization by analyzing estimated CCRs by the deep artificial neural network models. The authors also compared the performance of the proposed algorithm with a conventional radioisotope identification method and discussed promising ways to improve the performance of the algorithm using the deep artificial neural network.

The deep arbitrary polynomial chaos neural network or how Deep Artificial Neural Networks could benefit from data-driven homogeneous chaos theory

Artificial Intelligence and Machine learning have been widely used in various fields of mathematical computing, physical modeling, computational science, communication science, and stochastic analysis. Approaches based on Deep Artificial Neural Networks (DANN) are very popular in our days. Depending on the learning task, the exact form of DANNs is determined via their multi-layer architecture, activation functions and the so-called loss function. However, for a majority of deep learning approaches based on DANNs, the kernel structure of neural signal processing remains the same, where the node response is encoded as a linear superposition of neural activity, while the non-linearity is triggered by the activation functions. In the current paper, we suggest to analyze the neural signal processing in DANNs from the point of view of homogeneous chaos theory as known from polynomial chaos expansion (PCE). From the PCE perspective, the (linear) response on each node of a DANN could be seen as a 1st degree multi-variate polynomial of single neurons from the previous layer, i.e. linear weighted sum of monomials. From this point of view, the conventional DANN structure relies implicitly (but erroneously) on a Gaussian distribution of neural signals. Additionally, this view revels that by design DANNs do not necessarily fulfill any orthogonality or orthonormality condition for a majority of data-driven applications. Therefore, the prevailing handling of neural signals in DANNs could lead to redundant representation as any neural signal could contain some partial information from other neural signals. To tackle that challenge, we suggest to employ the data-driven generalization of PCE theory known as arbitrary polynomial chaos (aPC) to construct a corresponding multi-variate orthonormal representations on each node of a DANN. Doing so, we generalize the conventional structure of DANNs to Deep arbitrary polynomial chaos neural networks (DaPC NN). They decompose the neural signals that travel through the multi-layer structure by an adaptive construction of data-driven multi-variate orthonormal bases for each layer. Moreover, the introduced DaPC NN provides an opportunity to go beyond the linear weighted superposition of single neurons on each node. Inheriting fundamentals of PCE theory, the DaPC NN offers an additional possibility to account for high-order neural effects reflecting simultaneous interaction in multi-layer networks. Introducing the high-order weighted superposition on each node of the network mitigates the necessity to introduce non-linearity via activation functions and, hence, reduces the room for potential subjectivity in the modeling procedure. Although the current DaPC NN framework has no theoretical restrictions on the use of activation functions. The current paper also summarizes relevant properties of DaPC NNs inherited from aPC as analytical expressions for statistical quantities and sensitivity indexes on each node. We also offer an analytical form of partial derivatives that could be used in various training algorithms. Technically, DaPC NNs require similar training procedures as conventional DANNs, and all trained weights determine automatically the corresponding multi-variate data-driven orthonormal bases for all layers of DaPC NN. The paper makes use of three test cases to illustrate the performance of DaPC NN, comparing it with the performance of the conventional DANN and also with plain aPC expansion. Evidence of convergence over the training data size against validation data sets demonstrates that the DaPC NN outperforms the conventional DANN systematically. Overall, the suggested re-formulation of the kernel network structure in terms of homogeneous chaos theory is not limited to any particular architecture or any particular definition of the loss function. The DaPC NN Matlab Toolbox is available online and users are invited to adopt it for own needs.

SoK: Membership Inference is Harder Than Previously Thought

Membership Inference Attacks (MIAs) can be conducted based on specific settings/assumptions and experience different limitations. In this paper, first, we provide a systematization of knowledge for all representative MIAs found in the literature. Second, we empirically evaluate and compare the MIA success rates achieved on Machine Learning (ML) models trained with some of the most common generalization techniques. Third, we examine the contribution of potential data leaks to successful MIAs. Fourth, we examine if the depth of Artificial Neural Networks (ANNs) affects MIA success rate and to what extent. For the experimental analysis, we focus solely on well-generalizable target models (various architectures trained on multiple datasets), having only black-box access to them. Our results suggest the following: (a) MIAs on well-generalizable targets suffer from significant limitations which undermine their practicality, (b) common generalization techniques result in ML models which are comparably robust against MIAs, (c) data leaks, although effective for overfitted models, do not facilitate MIAs in case of well-generalizable targets, (d) deep ANN architectures are not more vulnerable to MIAs compared to shallower ones or the opposite, and (e) well-generalizable models can be robust against MIAs even when not achieving state-of-the-art performance.

Deep Spiking Neural Networks with High Representation Similarity Model Visual Pathways of Macaque and Mouse

Deep artificial neural networks (ANNs) play a major role in modeling the visual pathways of primate and rodent. However, they highly simplify the computational properties of neurons compared to their biological counterparts. Instead, Spiking Neural Networks (SNNs) are more biologically plausible models since spiking neurons encode information with time sequences of spikes, just like biological neurons do. However, there is a lack of studies on visual pathways with deep SNNs models. In this study, we model the visual cortex with deep SNNs for the first time, and also with a wide range of state-of-the-art deep CNNs and ViTs for comparison. Using three similarity metrics, we conduct neural representation similarity experiments on three neural datasets collected from two species under three types of stimuli. Based on extensive similarity analyses, we further investigate the functional hierarchy and mechanisms across species. Almost all similarity scores of SNNs are higher than their counterparts of CNNs with an average of 6.6%. Depths of the layers with the highest similarity scores exhibit little differences across mouse cortical regions, but vary significantly across macaque regions, suggesting that the visual processing structure of mice is more regionally homogeneous than that of macaques. Besides, the multi-branch structures observed in some top mouse brain-like neural networks provide computational evidence of parallel processing streams in mice, and the different performance in fitting macaque neural representations under different stimuli exhibits the functional specialization of information processing in macaques. Taken together, our study demonstrates that SNNs could serve as promising candidates to better model and explain the functional hierarchy and mechanisms of the visual system.

A PLS – SEM study to test the role of Social media in influencing Purchase Intention

In light of the growing importance of social networking marketing (SMM) to the profitability of tiny and medium-sized businesses (SMEs) and the relatively modest adoption rate of SMM among SMEs, this study seeks to determine which factors influence SMEs’ adoption of SMM. This study, unlike the majority of others, proposed a two-stage analysis combining the partial least squares (PLS) method with an artificial intelligence technique called an artificial neural network (ANN). Using a deep ANN architecture, the proposed model can make predictions with a 91% success rate. The marketing rate of social networking site adoption was found to be significantly affected by the strength of the relationship between perceived efficiency, user approval of use, perceived expenses, and encouragement from upper management, beneficial conditions, and vendor pressure. The findings of this study contribute to the expanding body of literature on online advertising by shedding light on the role played by technological, corporate, and ecological (TOE) variables in consumers’ adoption of social media promotional activities. Investment choices in digital marketing in comparable and non-competitive industries can benefit from the study’s findings, which can be used by policymakers as well as managers of SMM and consumer behavior.

Recognition of weeds in corn crops: System with convolutional neural networks

This work proposes weed classification solutions in corn crops using Deep Artificial Neural Networks. The InceptionV3, MobileNetV2 and Adapted MobileNetV2 Convolutional Neural Network architectures were used to extract features from the images. The research problem refers to the question “Does the use of Artificial Neural Networks present good performance for visual analysis in the recognition of weeds in corn crops?”. In this way, the research was based on the analysys of image recognition methods and techniques with Artificial Neural Networks and organizing a database with images of corn crops, training and comparing the accuracy results and analyzing the behavior of different architectures on the dataset. Among the models, the one with the highest accuracy was InceptionV3, with 98%, demonstrating the ability of the technologies used in this work to become realistic for applications in crops, in order to help farmers to increase productivity in their crops.

On the Omnipresence of Spurious Local Minima in Certain Neural Network Training Problems

AbstractWe study the loss landscape of training problems for deep artificial neural networks with a one-dimensional real output whose activation functions contain an affine segment and whose hidden layers have width at least two. It is shown that such problems possess a continuum of spurious (i.e., not globally optimal) local minima for all target functions that are not affine. In contrast to previous works, our analysis covers all sampling and parameterization regimes, general differentiable loss functions, arbitrary continuous nonpolynomial activation functions, and both the finite- and infinite-dimensional setting. It is further shown that the appearance of the spurious local minima in the considered training problems is a direct consequence of the universal approximation theorem and that the underlying mechanisms also cause, e.g., $$L^p$$ L p -best approximation problems to be ill-posed in the sense of Hadamard for all networks that do not have a dense image. The latter result also holds without the assumption of local affine linearity and without any conditions on the hidden layers.

Risk assessment models of power transmission lines undergoing heavy ice at mountain zones based on numerical model and machine learning

To deliver the cleaner energy, such as water, wind and solar power, from the remote mountainous areas to the power load areas, overhead power transmission lines are widely employed around the world. It is not an easy job to guarantee the safety of the long distance power transmission with hundreds or even thousands of kilometers of lines, especially crossing heavy ice zones at mountains. In this work, a numerical model to simulate the static and dynamic responses of transmission lines undergoing heavy ice is proposed and validated. Using the model, parameter study under different line sections depending on the mountain terrains, height difference and tension in conductors is carried out. It is obtained that the ice-induced dynamic characteristics of transmission lines at mountain zones are highly different with those of traditional design standard, with more complicated and dangerous. Therefore, to assess the risk level of transmission lines at mountain zones, the numerical model is used to gather the big dataset. Then, five machine learning-based models, including three tree-based and two artificial neural network (ANN)-based models, are developed and compared to find the optimal one. It is found that the multi-layer feed-forward deep ANN (MLF-DNN)-based model behaves optimal with the best evaluation scores. Based on the models, the predominant input parameters to affect the risk level are obtained and some suggestions to improve the ice resistance for the design and operation of transmission lines at mountain zones are proposed.

A feedforward deep neural network for predicting the state-of-charge of lithium-ion battery in electric vehicles

This study proposes a feedforward deep neural network to predict the parameters of the lithium-ion battery in electric vehicles. Correlation analysis is used to select the candidate parameters for the proposed model with no categorical variable. A direct feedforward deep artificial neural network is developed to predict a battery’s charge state and develop the proposed inverse model. The predicted state-of-charge of the direct model is combined with four virtual functions to form the input variables for the proposed inverse model. Furthermore, virtual functions are incorporated to enhance the predicting capability of the proposed inverse function model. The predicted multi-output variables of the proposed inverse model are speed, mileage, voltage, velocity, and state-of-charge. The proposed inverse model is superior to the feedforward deep neural network previously proposed in the literature because of its multiple output capabilities. Also, the proposed model makes decision-making easier when used for the design simulation than the single-output deep neural networks, which predict the state-of-charge of a battery only. The mean square error is used as the metric for accurate measurement. During the simulation by the proposed inverse model (with virtual functions), accuracy was 44.43 times higher than the traditional inverse deep neural network model. Redefined parameters were used to verify the findings of the model. This result suggests that incorporating virtual functions into a deep neural network model’s inverse model can improve the accuracy of battery and electric vehicle parameter predictions.

A deep neural network for electrical resistance calibration of self-sensing carbon fiber polymer composites compatible with edge computing structural monitoring hardware electronics

The self-sensing ability of materials, in particular carbon fiber polymer composites (SSCFPC), is a must-have requirement when designing a structural monitoring network for remote assessment of structural serviceability. This work presents a study using an Artificial Deep Neural Network (ADNN) wherein is evaluated the electrical resistance (R) output of specimens subjected to an unchanged deformation state of 2.86% strain for prolonged periods of time. Six ADNN architectures are evaluated with varying numbers of neurons on pre-defined hidden layers, sharing the same four data inputs and one output. The dataset is based on 3276 data points collected during the experimental campaign of an innovative electrode design embedded in SSCFPC specimens. The effect of the number of iterations and the architecture of the neural network is investigated in proposed ADNN models. Simple moving average, and moving Standard Deviation, σ M , are determined and plotted in terms of z-score to assist in performance evaluation of proposed ADNN models. The optimal ADNN architecture is found among six proposed architectures and for each of the four SSCFPC mixtures. Results show the proposed model architectures are able to predict values of R with greater accuracy than traditional regression mathematical methods when traditional statistical coefficients are used. However, when analyzing data in a time-series manner, results show further research is needed to achieve optimal accuracy results. The analysis presented focused on the structural monitoring network infrastructure and hardware electronics compatibility for further development of this type of SSCFPC as a self-sensing composite material with ability of automatic calibration and suitable for real-time data acquisition and artificial intelligence modeling.

An Application of Machine Learning Algorithms on the Prediction of the Damage Level of Rubble-Mound Breakwaters

Abstract The stability analysis of breakwaters is very important to have a safe and economic design of these coastal protective structures and the damage level is one of the most important parameters in this context. In the recent past, machine learning techniques showed immense potential in transforming many industries and processes, for making them more efficient and accurate. In this study, five advanced machine learning algorithms, support vector regression, random forest, Adaboost, gradient boosting, and deep artificial neural network, were employed and analyzed on estimation of the damage level of rubble-mound breakwaters. A large experimental dataset, considering almost every stability variable with their whole ranges, was used in this purpose. Also, a detailed feature analysis is presented to have an insight into the relations between these variables. It was found that the present study had overcome all of the limitations of existing studies related to this field and delivered the highest level of accuracy.

Abstract 544: Evaluating The Diagnostic Ability Of Six Different Artificial Neural Networks From The Subcellular Microenvironment To The Clinical Manifestation

Peripheral arterial disease (PAD) is affecting a large number of patients in the USA and worldwide. The natural history of the disease leads to detrimental clinical implications including walking disability, pain and eventually limb loss. The clinical management of the disease is largely based on clinical criteria (e.g. pain, tissue loss). We have prepared muscle biopsy specimens from patients with PAD versus control subjects and utilizing electron-microscopy we captured in the subcellular level the mitochondrial architecture changes. Using the acquired data as input we tested the ability of six structurally different artificial neural networks (ANNs) to identify PAD patients. For the study we acquired human tissue biopsies from the gastrocnemius muscle. The specimens were processed and cut as ultrathin sections (70 nm) for analysis using a JEM1010 transmission electron microscope. The images were used to generate an image preprocessing database of 992 images and subsequently a custom python-based code was developed with Keras - TensorFlow platforms in order to perform the ANN analysis. We implementing six different deep artificial neural network architectures namely, VGG-19 , ResNet50 , Densenet201 , InceptionV3 , InceptionsResnetV2 and EfficientNetB7.The diagnostic accuracy was found to be respectively: VGG-19 0.81%, ResNet50 0.75%, Densenet201 0.81%, InceptionV3 0.79%, InceptionsResnetV2 0.78% and EfficientNetB7 0.87%.This study presents data for the ability of simple and more advanced ANNs to perform diagnostic predictions based on electron microscopy images of intracellular organelles. The ability to take advantage of applied artificial intelligence technologies and serve this information for clinical decision making could be a pathway for improved patient care. The presented work established insight in some of the currently available deep artificial neural networks, applied in a daily clinical problem and their ability to harness biological information. Our goal is to stimulate the development of higher computational capacity artificial intelligence systems in order to assist clinicians and support improved guidelines geared towards individualized precision medicine.

Deep Learning Jaringan Saraf Tiruan Untuk Pemecahan Masalah Deteksi Penyakit Daun Apel

Diseases on apple leaves are becoming a major issue for apple growers since they can cause the crop to fail. Due to the diversity of diseases that can affect apple leaves, it can be challenging for farmers to determine the cause of leaf damage. The purpose of this research is to evaluate a convolutional neural network (CNN) method for its potential use in solving the problem of apple leaf disease identification. Four types of illness are dealt with: normal, multi-illness, rusty, and scabby. Many methods, such as data preparation and a preset VGG-16 artificial neural network (CNN) architecture, are recommended for use in the deep artificial neural network processing method. The most precise outcomes occurred when the beta parameter value was set to 2 = 0.999 at Ephoch to 85/100 with an accuracy of 0.7582, and when the epsilon parameter value was set to 1e-07 at Ephoch to 32/100 with an accuracy of 0.7582 with the best accuracy.

Natralization without associationist reduction: a brief rebuttal to Yoshimi

AbstractYoshimi has attempted to defuse my argument concerning the identification of network abstraction with empiricist abstraction - thus entailing psychologism - by claiming that the argument does not generalize from the example of simple feed-forward networks. I show that such details of networks are logically irrelevant to the nature of the abstractive process they employ. This is ultimately because deep artificial neural networks (ANNs) and dynamical systems theory applied to the mind (DST) are both associationisms - that is, empiricist theories that derive the principles of thought from the causal history of the organism/system. On this basis, I put forward a new aspect of the old argument by noting that ANNs & DST are the causal bases of the phenomena of passive synthesis, whereas the language of thought hypothesis (LOT) and the symbolic computational theory of mind (CTM) are the causal bases of the phenomena of active synthesis. If the phenomena of active synthesis are not distinct in kind from and are thus reducible to those of passive synthesis, psychologism results. Yoshimi’s program, insofar as it denies this fundamental phenomenological distinction, is revealed to be the true anti-pluralist program, by essentially denying the causal efficacy of the mechanistic foundations of active synthesis by referring phenomenology exclusively to associationism for its causal foundation.