Conventional Feedforward Neural Networks Research Articles

Adopting Graph Neural Networks to Analyze Human-Object Interactions for Inferring Activities of Daily Living.

Human Activity Recognition (HAR) refers to a field that aims to identify human activities by adopting multiple techniques. In this field, different applications, such as smart homes and assistive robots, are introduced to support individuals in their Activities of Daily Living (ADL) by analyzing data collected from various sensors. Apart from wearable sensors, the adoption of camera frames to analyze and classify ADL has emerged as a promising trend for achieving the identification and classification of ADL. To accomplish this, the existing approaches typically rely on object classification with pose estimation using the image frames collected from cameras. Given the existence of inherent correlations between human-object interactions and ADL, further efforts are often needed to leverage these correlations for more effective and well justified decisions. To this end, this work proposes a framework where Graph Neural Networks (GNN) are adopted to explicitly analyze human-object interactions for more effectively recognizing daily activities. By automatically encoding the correlations among various interactions detected through some collected relational data, the framework infers the existence of different activities alongside their corresponding environmental objects. As a case study, we use the Toyota Smart Home dataset to evaluate the proposed framework. Compared with conventional feed-forward neural networks, the results demonstrate significantly superior performance in identifying ADL, allowing for the classification of different daily activities with an accuracy of 0.88. Furthermore, the incorporation of encoded information from relational data enhances object-inference performance compared to the GNN without joint prediction, increasing accuracy from 0.71 to 0.77.

Enhancing Electrical Load Prediction Using a Bidirectional LSTM Neural Network

Precise anticipation of electrical demand holds crucial importance for the optimal operation of power systems and the effective management of energy markets within the domain of energy planning. This study builds on previous research focused on the application of artificial neural networks to achieve accurate electrical load forecasting. In this paper, an improved methodology is introduced, centering around bidirectional Long Short-Term Memory (LSTM) neural networks (NN). The primary aim of the proposed bidirectional LSTM network is to enhance predictive performance by capturing intricate temporal patterns and interdependencies within time series data. While conventional feed-forward neural networks are suitable for standalone data points, energy consumption data are characterized by sequential dependencies, necessitating the incorporation of memory-based concepts. The bidirectional LSTM model is designed to furnish the prediction framework with the capacity to assimilate and leverage information from both preceding and forthcoming time steps. This augmentation significantly bolsters predictive capabilities by encapsulating the contextual understanding of the data. Extensive testing of the bidirectional LSTM network is performed using multiple datasets, and the results demonstrate significant improvements in accuracy and predictive capabilities compared to the previous simpleRNN-based framework. The bidirectional LSTM successfully captures underlying patterns and dependencies in electrical load data, achieving superior performance as gauged by metrics such as root mean square error (RMSE) and mean absolute error (MAE). The proposed framework outperforms previous models, achieving a remarkable RMSE, attesting to its remarkable capacity to forecast impending load with precision. This extended study contributes to the field of electrical load prediction by leveraging bidirectional LSTM neural networks to enhance forecasting accuracy. Specifically, the BiLSTM’s MAE of 0.122 demonstrates remarkable accuracy, outperforming the RNN (0.163), LSTM (0.228), and GRU (0.165) by approximately 25%, 46%, and 26%, in the best variation of all networks, at the 24-h time step, while the BiLSTM’s RMSE of 0.022 is notably lower than that of the RNN (0.033), LSTM (0.055), and GRU (0.033), respectively. The findings highlight the significance of incorporating bidirectional memory and advanced neural network architectures for precise energy consumption prediction. The proposed bidirectional LSTM framework has the potential to facilitate more efficient energy planning and market management, supporting decision-making processes in power systems.

A multi-task network approach for calculating discrimination-free insurance prices

In applications of predictive modeling, such as insurance pricing, indirect or proxy discrimination is an issue of major concern. Namely, there exists the possibility that protected policyholder characteristics are implicitly inferred from non-protected ones by predictive models and are thus having an undesirable (and possibly illegal) impact on prices. A technical solution to this problem relies on building a best-estimate model using all policyholder characteristics (including protected ones) and then averaging out the protected characteristics for calculating individual prices. However, such an approach requires full knowledge of policyholders’ protected characteristics, which may in itself be problematic. Here, we address this issue by using a multi-task neural network architecture for claim predictions, which can be trained using only partial information on protected characteristics and produces prices that are free from proxy discrimination. We demonstrate the proposed method on both synthetic data and a real-world motor claims dataset, in which proxy discrimination can be observed. In both examples we find that the predictive accuracy of the multi-task network is comparable to a conventional feed-forward neural network, when the protected information is available for at least half of the insurance policies. However, the multi-task network has superior performance in the case when the protected information is known for less than half of the insurance policyholders.

Robust machine learning modeling for predictive control using Lipschitz-Constrained Neural Networks

Neural networks (NNs) have emerged as a state-of-the-art method for modeling nonlinear systems in model predictive control (MPC). However, the robustness of NNs, in terms of sensitivity to small input perturbations, remains a critical challenge for practical applications. To address this, we develop Lipschitz-Constrained Neural Networks (LCNNs) for modeling nonlinear systems and derive rigorous theoretical results to demonstrate their effectiveness in approximating Lipschitz functions, reducing input sensitivity, and preventing over-fitting. Specifically, we first prove a universal approximation theorem to show that LCNNs using SpectralDense layers can approximate any 1-Lipschitz target function. Then, we prove a probabilistic generalization error bound for LCNNs using SpectralDense layers by using their empirical Rademacher complexity. Finally, the LCNNs are incorporated into the MPC scheme, and a chemical process example is utilized to show that LCNN-based MPC outperforms MPC using conventional feedforward NNs in the presence of training data noise.

Adaptive Capture Control of a Continuum Manipulator With Self-Powered Sensors

Perception is an essential component of an intelligent autonomous system. However, the traditional sensors used in robotics and industrial are limited when considering high mobility, wide distribution, and possible wireless operation of the sensors in sensor networks. The self-powered sensing solves the most shackling issue in the current sensing field, thus enabling many previously unattainable application scenarios. In this paper, a novel variable-length continuum manipulator with self-powered sensors is designed, and an adaptive capture control scheme based on deep learning prediction is proposed for the envelope grasp of a fixed cylinder target and the hook grasp of a ring target moving in a small range. First, adaptive capture parameters of the manipulator are generated according to a target’s size and position. Then, deep neural networks are utilized to accurately predict the bending angle of the manipulator with a large displacement motion at the tip of the continuum manipulator. Finally, based on the feedback data from the driving motor’s built-in angular velocity sensor on the continuum manipulator, a set of capture criteria are presented to identify the envelope and capture states of the target. The capture experimental results on a prototype reveal that the generated parameters highly match the targets. The prediction method’s accuracy is higher than that of conventional feedforward neural networks. The capture criteria based on the feedback data from driving motor’s built-in angular velocity sensor can correctly identify the target capture states. In additional, the future research of the adaptive capture control based on self-powered sensors is discussed.

English

One of the major technologies in delivering infrastructure and data service requirements at low cost and with minimal effort is Cloud Computing (CC), which has been implemented in several aspects of the IT industry. Since the rapid growth of CC has been observed, there is still an information security concern that intruders completely attack. With the potential of being practised in various utilizations, blockchain can be implemented in several cloud service providers. Blockchain platform has basically performed a large computation quantity which doesn’t accomplish the practical purpose of building Proof of Work (PoW) with context awareness accord from decentralized participants. Long Short-Term Memory (LSTM)has been designed particularly for overcoming the long-term dependency issues faced by Recurrent Neural Networks (RNN). This paper focuses on a novel consensus mechanism by LSTM which consists of feedback connections in making a difference with several conventional feed-forward Neural Networks. The research directed computation spent to consensus towards RNN optimization for better cyber security in blockchain implemented in the cloud platform. However, the enormous amount of data involved in the blockchain has been trained through the LSTM model that supports serving learning proof through cell states which handle the network of current long-term memory. Therefore, Contextual Identity Management (CAIM) mechanism is adopted through the LSTM model in blockchain for various Cloud Service Provider(CSP) in unifying the contextual details with the process of identity management that generate the probable robust solution. This assists in creating better decisions with respect to policy, authentication, routing and authorization for recent interacted data. Moreover, the proposed LSTM model in blockchain has been compared with the existing cyber-secured model of blockchain to determine the efficiency of the cyber-secured model of blockchain in the cloud platform.

Deep language models for interpretative and predictive materials science

Machine learning (ML) has emerged as an indispensable methodology to describe, discover, and predict complex physical phenomena that efficiently help us learn underlying functional rules, especially in cases when conventional modeling approaches cannot be applied. While conventional feedforward neural networks are typically limited to performing tasks related to static patterns in data, recursive models can both work iteratively based on a changing input and discover complex dynamical relationships in the data. Deep language models can model flexible modalities of data and are capable of learning rich dynamical behaviors as they operate on discrete or continuous symbols that define the states of a physical system, yielding great potential toward end-to-end predictions. Similar to how words form a sentence, materials can be considered as a self-assembly of physically interacted building blocks, where the emerging functions of materials are analogous to the meaning of sentences. While discovering the fundamental relationships between building blocks and function emergence can be challenging, language models, such as recurrent neural networks and long-short term memory networks, and, in particular, attention models, such as the transformer architecture, can solve many such complex problems. Application areas of such models include protein folding, molecular property prediction, prediction of material failure of complex nonlinear architected materials, and also generative strategies for materials discovery. We outline challenges and opportunities, especially focusing on extending the deep-rooted kinship of humans with symbolism toward generalizable artificial intelligence (AI) systems using neuro-symbolic AI, and outline how tools such as ChatGPT and DALL·E can drive materials discovery.

Multiscale recurrent-guided denoising network for distributed acoustic sensing-vertical seismic profile background noise attenuation

In recent years, distributed optical fiber acoustic sensing (DAS) has emerged as a novel seismic acquisition technique. Compared with conventional hydrophones and geophones of microelectromechanical systems, DAS has an advantage in terms of acquisition geometry, such as low-cost and high-density observations. However, the collected DAS records always suffer from various types of noise, which poses challenges for subsequent processing. Thus, deep learning-based solutions have addressed the attenuation of seismic background noise. Denoising networks can provide excellent denoising results. Nonetheless, the architectures of these networks are relatively simple, which may result in degeneration when confronted with the complex DAS background noise. To effectively attenuate complex noise, a novel multiscale network called recurrent-guided self-enhanced attention network (RGSA-Net) is developed for complex seismic data processing. Specifically, the backbone of RGSA-Net uses a conventional feedforward neural network to preliminarily extract the potential features. Meanwhile, multiscale modules, inspired by the recurrent-guided scheme, are used to enhance the contour information. On this basis, a self-enhanced attention module is applied to fuse the multiscale features and further reinforce the effective information, thereby improving the noise attenuation capability. Synthetic and field experiments demonstrate that RGSA-Net indicates promise in complex noise attenuation and weak upgoing signal recovery.

Application of the PSO–neural network in rainfall–runoff modeling

Abstract In this study, rainfall–runoff (R–R) models were developed by assembling Particle Swarm Optimization (PSO) with the Feed Forward Neural Network (FFNN) and the Wavelet Neural Network (WNN). Performances of the model were compared with the wavelet ensembled neural network (WNN) and the conventional FFNN. The data from 1981 to 2005 were used for calibration and from 2006 to 2014 for validation of the models. Different combinations of rainfall and runoff were considered as inputs to the PSO–FFNN model. The fitness value and computational time of all the combinations were computed. Input combination was selected based on the lowest fitness value and lowest computational time. Four R–R models (FFNN, WNN, PSO–FFNN and PSO–WNN) were developed with the best input combination. The performance of the models was evaluated using statistical parameters (Nash–Sutcliffe Efficiency (NSE), D and root mean square error (RMSE)) and parameters vary in the range of (0.86–0.90), (0.95–0.97) and (68.87–84.37), respectively. After comparing the performance parameters and computational time of all four models, it was found that the PSO–FFNN model gave better values of NSE (0.89), D (0.97), RMSE (68.87) and less computational time (125.42 s) than other models. Thus, the PSO–FFNN model was better than the other three models (FFNN, WNN and PSO–WNN).

A Multi-Task Network Approach for Calculating Discrimination-Free Insurance Prices

In applications of predictive modeling, such as insurance pricing, indirect or proxy discrimination is an issue of major concern. Namely, there exists the possibility that protected policyholder characteristics are implicitly inferred from non-protected ones by predictive models, and are thus having an undesirable (or illegal) impact on prices. A technical solution to this problem relies on building a best-estimate model using all policyholder characteristics (including protected ones) and then averaging out the protected characteristics for calculating individual prices. However, such approaches require full knowledge of policyholders' protected characteristics, which may in itself be problematic. Here, we address this issue by using a multi-task neural network architecture for claim predictions, which can be trained using only partial information on protected characteristics, and it produces prices that are free from proxy discrimination. We demonstrate the use of the proposed model and we find that its predictive accuracy is comparable to a conventional feedforward neural network (on full information). However, this multi-task network has clearly superior performance in the case of partially missing policyholder information.

An Interpretation of Long Short-Term Memory Recurrent Neural Network for Approximating Roots of Polynomials

This paper aims to present a flexible method for interpreting the Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) for the relational structure between the roots and the coefficients of a polynomial. A database is first developed for randomly selected inputs based on the degrees of the univariate polynomial which is then used to approximate the polynomial roots through the proposed LSTM-RNN model. Furthermore, an adaptive learning optimization algorithm is used specifically to update the network weights iteratively based on training deep neural networks data. Thus, the method can exploit the ability to find the individual learning rates for each variable through adaptive learning rate strategies to effectively prevent the weights from fluctuating in a wide spectrum. Finally, several experimental results are performed which shows that the proposed LSTM-RNN model can be used as an alternative approach to compute an approximation of each root for a given polynomial. Furthermore, the results are compared with the conventional feedforward neural network based artificial neural network model. The results clearly demonstrate the superiority of the proposed LSTM-RNN model for roots approximation in terms of accuracy, mean square error and faster convergence.

Inferring material properties of the lower mantle minerals using Mixture Density Networks

Interpretation of information available from seismic data in terms of temperature and composition requires an understanding of the physical properties of minerals, in particular, the elastic properties of candidate Earth minerals at the relevant (here, lower mantle) pressure and temperature. A common practice for the bulk elastic properties is to measure volume at a range of pressures and temperatures using experiments or computational methods. These datasets are then typically fit to a pre-determined functional form, or equation of state to allow computation of elastic properties at any other pressure or temperature. However, errors, both random and systematic, limitations in the number of data and choice of pressure marker and scale, as well as different functional forms of equations of state, all contribute to the uncertainties in mineral seismic properties. In an attempt to present a more comprehensive view of these uncertainties, we use neural-network based techniques to infer the relationship among: pressure, temperature, volume, bulk modulus, and thermal expansivity of MgO. We illustrate our approach on experimental data, but an extension to ab initio data is straightforward. The type of neural network used is called a Mixture Density Network (MDN) which is a combination of a conventional feed-forward neural network and a mixture model that consists of Gaussian functions. MDNs are capable of approximating arbitrary probability density functions, which allows us to compute the uncertainties in the predicted equations of state. Since the networks interpolate locally between input samples, pressure-volume-temperature relations are implicitly learned from data without imposing any explicit thermodynamic assumptions or ad-hoc relationships. We use the partial derivatives of the mapping between inputs (pressure and temperature) and output (volume) to compute the isothermal bulk modulus and thermal expansivity. Flexibility of the MDNs allows us to investigate the uncertainty due to certain data in one region of pressure-temperature space without influencing the posterior probability density everywhere. In general, we find that the elastic properties of MgO are well-constrained by experimental data. However, our study highlights regions in which sparse or inconsistent data lead to poorly constrained elastic properties, namely: at low pressure and high temperature (<25GPa and >1500K), and temperatures above 2700K. While the former conditions are likely not important for the Earth's lower mantle, they are relevant in other planetary bodies such as the Moon and Mars. Comparison with conventional equation of state forms shows that assuming a certain functional form of the pressure-volume-temperature relationship leads to potential bias in uncertainty quantification, because the uncertainties are then specific to the underlying form. In combination with data sets of other lower mantle minerals, this technique should improve uncertainty quantification in interpretations of seismic data.

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

Deep artificial neural networks apply principles of the brain’s information processing that led to breakthroughs in machine learning spanning many problem domains. Neuromorphic computing aims to take this a step further to chips more directly inspired by the form and function of biological neural circuits, so they can process new knowledge, adapt, behave, and learn in real time at low power levels. Despite several decades of research, until recently, very few published results have shown that today’s neuromorphic chips can demonstrate quantitative computational value. This is now changing with the advent of Intel’s Loihi, a neuromorphic research processor designed to support a broad range of spiking neural networks with sufficient scale, performance, and features to deliver competitive results compared to state-of-the-art contemporary computing architectures. This survey reviews results that are obtained to date with Loihi across the major algorithmic domains under study, including deep learning approaches and novel approaches that aim to more directly harness the key features of spike-based neuromorphic hardware. While conventional feedforward deep neural networks show modest if any benefit on Loihi, more brain-inspired networks using recurrence, precise spike-timing relationships, synaptic plasticity, stochasticity, and sparsity perform certain computation with orders of magnitude lower latency and energy compared to state-of-the-art conventional approaches. These compelling neuromorphic networks solve a diverse range of problems representative of brain-like computation, such as event-based data processing, adaptive control, constrained optimization, sparse feature regression, and graph search.

Monthly surface runoff prediction using artificial intelligence: A study from a tropical climate river basin

Accurate surface runoff prediction is vital for water resources engineers for various applications. Advances in the artificial intelligence techniques can act as robust tools for modelling hydrological processes. The present study focuses on testing the reliability of different data sources and choosing the correct source to model the rainfall-runoff process under data scarce situations using AI techniques. In this study, an absolute homogeneity test was performed for TRMM, gridded and observed precipitation data and found that the observed precipitation dataset is homogeneous and best suitable for modelling rainfall-runoff process in Kallada river basin, Kerala. Emotional artificial neural network (EANN) is a novel hybrid neural network and it is suggested in the present study for accurate monthly surface runoff prediction. This study was also conceived to address and investigate the efficiency of EANN for forecasting monthly surface runoff and compare the performances with conventional feed forward neural network (FFNN) and multivariate adaptive regression spline (MARS) models. Suitable goodness-of-fit criteria such as Nash–Sutcliffe efficiency (NSE), root mean square error (RMSE) and coefficient of determination (R2) and graphical indicators are used for assessing the efficacy of the developed models. The results showed that the EANN model performs better with R2 = 0.80 for the training phase and R2 = 0.77 for validation phase compared to other models. The improvement in the performance of EANN model over FFNN model is 12% and 5.8% for coefficient of determination in the training and validation phase, respectively. Further, the Taylor diagram indicates that there is a close match between the observed and EANN model predicted values in terms of statistical parameters. Overall, this study demonstrated the effectiveness of EANN in modelling the rainfall-runoff process and also could be a useful technique in other fields of water resources engineering.

General Purpose Structure-Based Drug Discovery Neural Network Score Functions with Human-Interpretable Pharmacophore Maps.

The BioChemical Library (BCL) is an academic open-source cheminformatics toolkit comprising ligand-based virtual high-throughput screening (vHTS) tools such as quantitative structure–activity/property relationship (QSAR/QSPR) modeling, small molecule flexible alignment, small molecule conformer generation, and more. Here, we expand the capabilities of the BCL to include structure-based virtual screening. We introduce two new score functions, BCL-AffinityNet and BCL-DockANNScore, based on novel distance-dependent signed protein–ligand atomic property correlations. Both metrics are conventional feed-forward dropout neural networks trained on the new descriptors. We demonstrate that BCL-AffinityNet is one of the top performing score functions on the comparative assessment of score functions 2016 affinity prediction and affinity ranking tasks. We also demonstrate that BCL-AffinityNet performs well on the CSAR-NRC HiQ I and II test sets. Furthermore, we demonstrate that BCL-DockANNScore is competitive with multiple state-of-the-art methods on the docking power and screening power tasks. Finally, we show how our models can be decomposed into human-interpretable pharmacophore maps to aid in hit/lead optimization. Altogether, our results expand the utility of the BCL for structure-based scoring to aid small molecule discovery and design. BCL-AffinityNet, BCL-DockANNScore, and the pharmacophore mapping application, as well as the remainder of the BCL cheminformatics toolkit, are freely available with an academic license at the BCL Commons site hosted on http://meilerlab.org/.

Sandstone Reservoirs Porosity and Water Saturation Estimation Using Functional Network Techniques

An accurate determination of porosity and water saturation is vital for evaluating an oil reserve and proposing a development plan for developed sandstone reservoir. The objective of this study is to provide an improved intelligent approach the use of functional networks to estimate porosity and water saturation from well log using real field data in sandstone reservoir where it becomes difficult to acquire reliable well logging data. The proposed methodology makes use of appropriate well logs and core measurements. A portion of the data available was retained for verification of the prediction of water saturation and porosity. This paper presents a novel method for estimating these two important parameters directly from conventional well measurements. The recently proposed Functional Networks technique is applied for rapid and accurate prediction of these parameters, using six and five basic well log measurements as data for estimating porosity and water saturation respectively. Functional network is a generalization of the conventional Feed Forward Neural Networks, which overcome many of the drawbacks of the conventional neural network techniques. The proposed functional network was trained using data gathered from two wells in the Middle East region. Results obtained from this case study of sandstone reservoir using the proposed intelligent technique have shown to be fast and accurate referring to core samples porosity and water saturation values.

Resilient back-propagation approach in small-world feed-forward neural network topology based on Newman–Watts algorithm

The scientific researches are focused on network topologies and training algorithms fields because they reduce overfitting problem in artificial neural networks. In this context, we showed in our previous work that Newman–Watts small-world feed-forward artificial neural networks present better classification and prediction performance than conventional feed-forward artificial neural networks. In this study, we investigate the effects of the Resilient back-propagation algorithm on SW network topology and propose a Resilient Newman–Watts small-world feed-forward artificial neural network model by assuming fixed initial topological conditions. We find that Resilient small-world network further reduces overfitting and further increases the network performance when compared to the conventional feed-forward artificial neural networks. Furthermore, it is shown that the proposed network model does not increase the algorithmic complexity as per other models. The obtained results imply that the proposed model can contribute to the solving of overfitting problem encountered in both deep neural networks and conventional artificial neural networks.

A hybrid wavelet-optimally-pruned extreme learning machine model for the estimation of international roughness index of rigid pavements

ABSTRACT International Roughness Index (IRI) is a key parameter in pavement performance evaluation. This study investigates developing a reliable prediction model that can be used to estimate IRI of rigid pavements using innovative machine learning techniques. Optimally Pruned Extreme Learning Machine (OP-ELM) and Wavelet analysis are integrated to improve the OP-ELM results and design a novel hybrid Wavelet-OPELM (WOPELM) model for the IRI prediction. The proposed model is compared statistically to the OP-ELM and conventional feed-forward Artificial Neural Network (ANN) as well as regression model with respect to their efficiency to predict IRI of jointed plain concrete pavement (JPCP) sections in USA. The relevant data was collected from the Long-Term Pavement Performance (LTPP) database. Eight input variables, initial IRI, pavement age, transverse cracks, percent joints spalled, flexible and rigid patching areas, total joint faulting, freeze index, and percent subgrade passing No. 200 U.S. sieve, are assessed and used to predict the IRI. The results show that the initial IRI, total joint faulting, and freezing index are the most significant parameters for IRI prediction. The WOPELM is found to be a robust and more accurate modelling technique compared to OP-ELM, ANN, and regression for IRI prediction with only a 7% prediction error.

Hydrological drought assessment through streamflow forecasting using wavelet enabled artificial neural networks

In semi-arid watersheds, hydrological drought is manifested by reasonably low streamflow conditions. This makes streamflow forecasting as an inevitable component for implementing drought management practices. Data-driven modelling techniques are often applied for simulating the streamflow forecasts. In this study, a comparison between conventional feedforward neural network (FFNN) model and wavelet enabled artificial neural network (WANN) model is carried out to analyse their effectiveness in streamflow forecasting. The input data used to develop and simulate the models are monthly precipitation, and monthly river stage of twenty-five years (January 1991 to December 2015). Data pre-processing is carried out using correlation analysis prior to neural network modelling for selecting appropriate input combinations. The preprocessed data is directly given as input for FFNN; whereas for WANN, the preprocessed time series datasets are decomposed into several sub-series and are used as the inputs. Analysis on three different transfer functions that are commonly used in ANN models is carried out to identify the best transfer function. Hyperbolic tangent sigmoid transfer function is found to be best suitable for modelling streamflow forecasts. The result also shows that there is a significant improvement in streamflow forecasting ability for WANN models compared to FFNN. Drought forecasting is carried out by developing a standardized streamflow index from the forecasted streamflow. The drought forecasting technique discussed here will help planners to make informed decisions on watershed management and drought mitigation measures.

Prediction of Solutions of Arithmetic and Logical Operations on the Basis of the Mathematical Model of Cognitive Digital Automata

An approach to the problem of solution prediction of arithmetic and logical operations on the basis of the mathematical model of cognitive digital automata (CDA) is proposed. A particular advantage of the proposed approach is that the training procedure can be performed on limited (minimum) training sets. Prediction or generation of solutions is performed on the basis of the mathematical model of CDA which is formed in the course of training. As a testbed for the approach, the modeling of an n-bit parallel adder was implemented. The mathematical model of the adder was formed, which made it possible to reproduce the entire truth table for the n-bit parallel adder. The results obtained could be useful as an alternative solution to a number of problems known for conventional feed-forward neural networks, e.g. on-the-fly learning and catastrophic forgetting.