Artificial intelligence in a rugged design based on multi-bit rules

In this paper, the technologies for training large artificial neural networks are considered: the first technology is based on the use of multilayer “deep” neural networks; the second technology involves the use of a “wide” single-layer network of neurons giving 256 private binary solutions. A list of attacks aimed at the simplest one-bit neural network decision rule is given: knowledge extraction attacks and software data modification attacks; their content is considered. All single-bit decision rules are unsafe for applying. It is necessary to use other decision rules. The security of applying neural network decision rules in relation to deliberate hacker attacks is significantly reduced if you use a decision rule of a large number of output bits. The most important property of neural network transducers is that when it is trained using 20 examples of the “Friend” image, the “Friend” output code of 256 bits long is correctly reproduced with a confidence level of 0.95. This means that the entropy of the “Friend” output codes is close to zero. A well-trained neural network virtually eliminates the ambiguity of the “Friend” image data. On the contrary, for the “Foe” images, their initial natural entropy is enhanced by the neural network. The considered works made it possible to create a draft of the second national standard for automatic training of networks of quadratic neurons with multilevel quantizers.

Learning without loss

We explore a new approach for training neural networks where all loss functions are replaced by hard constraints. The same approach is very successful in phase retrieval, where signals are reconstructed from magnitude constraints and general characteristics (sparsity, support, etc.). Instead of taking gradient steps, the optimizer in the constraint based approach, called relaxed–reflect–reflect (RRR), derives its steps from projections to local constraints. In neural networks one such projection makes the minimal modification to the inputs x, the associated weights w, and the pre-activation value y at each neuron, to satisfy the equation $x\cdot w=y$ x ⋅ w = y . These projections, along with a host of other local projections (constraining pre- and post-activations, etc.) can be partitioned into two sets such that all the projections in each set can be applied concurrently—across the network and across all data in the training batch. This partitioning into two sets is analogous to the situation in phase retrieval and the setting for which the general purpose RRR optimizer was designed. Owing to the novelty of the method, this paper also serves as a self-contained tutorial. Starting with a single-layer network that performs nonnegative matrix factorization, and concluding with a generative model comprising an autoencoder and classifier, all applications and their implementations by projections are described in complete detail. Although the new approach has the potential to extend the scope of neural networks (e.g. by defining activation not through functions but constraint sets), most of the featured models are standard to allow comparison with stochastic gradient descent.

Node Importance Evaluation of Cyber-Physical System under Cyber-Attacks Spreading

The study of cyber-attacks, and in particular the spread of attack on the power cyber-physical system, has recently attracted considerable attention. Identifying and evaluating the important nodes under the cyber-attack propagation scenario are of great significance for improving the reliability and survivability of the power system. In this paper, we improve the closeness centrality algorithm and propose a compound centrality algorithm based on adaptive coefficient to evaluate the importance of single-layer network nodes. Moreover, we quantitatively calculated the decouple degree of cascading failures caused by exposed nodes formed by attack propagation. At last, experiments based on the IEEE 57 test system show that the proposed compound centrality algorithm can match the cyber-attack propagation scenario well, and we give the importance values of the nodes in a specific attack scenario.

Toward reliable automatic liver and tumor segmentation using convolutional neural network based on 2.5D models

Purpose We investigated the parameter configuration in the automatic liver and tumor segmentation using a convolutional neural network based on 2.5D model. The implementation of 2.5D model shows promising results since it allows the network to have a deeper and wider network architecture while still accommodates the 3D information. However, there has been no detailed investigation of the parameter configurations on this type of network model. Methods Some parameters, such as the number of stacked layers, image contrast, and the number of network layers, were studied and implemented on neural networks based on 2.5D model. Networks are trained and tested by utilizing the dataset from liver and tumor segmentation challenge (LiTS). The network performance was further evaluated by comparing the network segmentation with manual segmentation from nine technical physicians and an experienced radiologist. Results Slice arrangement testing shows that multiple stacked layers have better performance than a single-layer network. However, the dice scores start decreasing when the number of stacked layers is more than three layers. Adding higher number of layers would cause overfitting on the training set. In contrast enhancement test, implementing contrast enhancement method did not show a statistically significant different to the network performance. While in the network layer test, adding more layers to the network architecture does not always correspond to the increasing dice score result of the network. Conclusions This paper compares the performance of the network based on 2.5D model using different parameter configurations. The result obtained shows the effect of each parameter and allow the selection of the best configuration in order to improve the network performance in the application of automatic liver and tumor segmentation.

A survey of community detection methods in multilayer networks

Community detection is one of the most popular researches in a variety of complex systems, ranging from biology to sociology. In recent years, there’s an increasing focus on the rapid development of more complicated networks, namely multilayer networks. Communities in a single-layer network are groups of nodes that are more strongly connected among themselves than the others, while in multilayer networks, a group of well-connected nodes are shared in multiple layers. Most traditional algorithms can rarely perform well on a multilayer network without modifications. Thus, in this paper, we offer overall comparisons of existing works and analyze several representative algorithms, providing a comprehensive understanding of community detection methods in multilayer networks. The comparison results indicate that the promoting of algorithm efficiency and the extending for general multilayer networks are also expected in the forthcoming studies.

Training and Testing of a Single-Layer LSTM Network for Near-Future Solar Forecasting

Increasing integration of renewable energy sources, like solar photovoltaic (PV), necessitates the development of power forecasting tools to predict power fluctuations caused by weather. With trustworthy and accurate solar power forecasting models, grid operators could easily determine when other dispatchable sources of backup power may be needed to account for fluctuations in PV power plants. Additionally, PV customers and designers would feel secure knowing how much energy to expect from their PV systems on an hourly, daily, monthly, or yearly basis. The PROGNOSIS project, based at the Cyprus University of Technology, is developing a tool for intra-hour solar irradiance forecasting. This article presents the design, training, and testing of a single-layer long-short-term-memory (LSTM) artificial neural network for intra-hour power forecasting of a single PV system in Cyprus. Four years of PV data were used for training and testing the model (80% for training and 20% for testing). With a normalized root mean squared error (nRMSE) of 10.7%, the single-layer network performed similarly to a more complex 5-layer LSTM network trained and tested using the same data. Overall, these results suggest that simple LSTM networks can be just as effective as more complicated ones.

Nonlinear Structural Fusion for Multiplex Network

Many real-world complex systems have multiple types of relations between their components, and they are popularly modeled as multiplex networks with each type of relation as one layer. Since the fusion analysis of multiplex networks can provide a comprehensive insight, the structural information fusion of multiplex networks has become a crucial issue. However, most of these existing data fusion methods are inappropriate for researchers to apply to complex network analysis directly. The feature-based fusion methods ignore the sharing and complementarity of interlayer structural information. To tackle this problem, we propose a multiplex network structural fusion (MNSF) model, which can construct a network with comprehensive information. It is composed of two modules: the network feature extraction (NFE) module and the network structural fusion (NSF) module. (1) In NFE, MNSF first extracts a low-dimensional vector representation of a node from each layer. Then, we construct a node similarity network based on embedding matrices and K-D tree algorithm. (2) In NSF, we present a nonlinear enhanced iterative fusion (EIF) strategy. EIF can strengthen high-weight edges presented in one (i.e., complementary information) or more (i.e., shared information) networks and weaken low-weight edges (i.e., redundant information). The retention of low-weight edges shared by all layers depends on the tightness of connections of their K-order proximity. The usage of higher-order proximity in EIF alleviates the dependence on the quality of node embedding. Besides, the fused network can be easily exploited by traditional single-layer network analysis methods. Experiments on real-world networks demonstrate that MNSF outperforms the state-of-the-art methods in tasks link prediction and shared community detection.

Recommendation Algorithm in Double-Layer Network Based on Vector Dynamic Evolution Clustering and Attention Mechanism

The purpose of recommendation systems is to help users find effective information quickly and conveniently and also to present the items that users are interested in. While the literature of recommendation algorithms is vast, most collaborative filtering recommendation approaches attain low recommendation accuracies and are also unable to track temporal changes of preferences. Additionally, previous differential clustering evolution processes relied on a single-layer network and used a single scalar quantity to characterise the status values of users and items. To address these limitations, this paper proposes an effective collaborative filtering recommendation algorithm based on a double-layer network. This algorithm is capable of fully exploring dynamical changes of user preference over time and integrates the user and item layers via an attention mechanism to build a double-layer network model. Experiments on Movielens, CiaoDVD, and Filmtrust datasets verify the effectiveness of our proposed algorithm. Experimental results show that our proposed algorithm can attain a better performance than other state-of-the-art algorithms.

Price Linkage Rumors in the Stock Market and Investor Risk Contagion on Bilayer-Coupled Networks

Investor heterogeneities include investor risk preference, investor risk cognitive level, information value, and investor influence. From the perspective of the stock price linkage, this article constructs an SCIR contagion model of investor risk on a single-layer network. It digs out the investor risk caused by rumors in the stock market under the stock price linkage and its contagion mechanism. The function and influence of different mechanism probabilities and investor heterogeneities on the effects of risk contagion in the stock market are explored through computer simulation. Based on the SCIR contagion model of investor risk on single-layer network, we construct an SCI1I2R contagion model of investor risk on bilayer-coupled networks. Initially, the evolution mechanisms of investor risk contagion in the stock market are compared in single-layer and bilayer-coupled networks. Thereafter, the evolution characteristics and rules of investor risk contagion under different connection modes and heterogeneous mechanism probabilities are compared on bilayer-coupled networks. The results corroborate the following. (1) In the SCIR contagion model of investor risk on a single-layer network, immune failure probability and immune probability have the “global effect”. (2) Investor heterogeneities both have “global effect” and “local effect” on investor risk contagion. (3) Compared with the investor risk contagion on a single-layer network, bilayer-coupled networks can expand the investor risk contagion and have a “global enhancement” effect. (4) Among the three interlayer connection modes of the SCI1I2R model of investor risk contagion on bilayer-coupled networks, the assortative link has the effect of “local enhancement”, while the disassortative link has the effect of “local inhibition”. (5) In the SCI1I2R model of investor risk contagion on bilayer-coupled networks, heterogeneous mechanism probabilities have “global effect” and “local effect”. The research conclusion provides a theoretical basis for regulators to prevent financial risks from spreading among different investors, which is of high theoretical value and practical significance.