In this paper, a new representation of neural tensor networks is presented. Recently, state-of-the-art neural tensor networks have been introduced to complete RDF knowledge bases. However, mathematical model representation of these networks is still a challenging problem, due to tensor parameters. To solve this problem, it is proposed that these networks can be represented as two-layer perceptron network. To complete the network topology, the traditional gradient based learning rule is then developed. It should be mentioned that for tensor networks there have been developed some learning rules which are complex in nature due to the complexity of the objective function used. Indeed, this paper is aimed to show that the tensor network can be viewed and represented by the two-layer feedforward neural network in its traditional form. The simulation results presented in the paper easily verify this claim.
相似文献The amount of content on online music streaming platforms is immense, and most users only access a tiny fraction of this content. Recommender systems are the application of choice to open up the collection to these users. Collaborative filtering has the disadvantage that it relies on explicit ratings, which are often unavailable, and generally disregards the temporal nature of music consumption. On the other hand, item co-occurrence algorithms, such as the recently introduced word2vec-based recommenders, are typically left without an effective user representation. In this paper, we present a new approach to model users through recurrent neural networks by sequentially processing consumed items, represented by any type of embeddings and other context features. This way we obtain semantically rich user representations, which capture a user’s musical taste over time. Our experimental analysis on large-scale user data shows that our model can be used to predict future songs a user will likely listen to, both in the short and long term.
相似文献The large volume and variety of apps pose a great challenge for people to choose appropriate apps. As a consequence, app recommendation is becoming increasingly important. Recently, app usage data which record the sequence of apps being used by a user have become increasingly available. Such data record the usage context of each instance of app use, i.e., the app instances being used together with this app (within a short time window). Our empirical data analysis shows that a user has a pattern of app usage contexts. More importantly, the similarity in the two users’ preferences over mobile apps is correlated with the similarity in their app usage context patterns. Inspired by these important observations, this paper tries to leverage the predictive power of app usage context patterns for effective app recommendation. To this end, we propose a novel neural approach which learns the embeddings of both users and apps and then predicts a user’s preference for a given app. Our neural network structure models both a user’s preference over apps and the user’s app usage context pattern in a unified way. To address the issue of unbalanced training data, we introduce several sampling methods to sample user-app interactions and app usage contexts effectively. We conduct extensive experiments using a large real app usage data. Comparative results demonstrate that our approach achieves higher precision and recall, compared with the state-of-the-art recommendation methods.
相似文献We propose a new approach for the organic integration of edge cloud offloading decision and Stackelberg game pricing to address the problem that the current Stackelberg games all allocate edge cloud computing resources equally and ignore the difference of different users’ demand for computing resources. Firstly, the Stackelberg game theory is used to establish a model of the optimal amount of data to be offloaded by users and the optimal number of computing resource blocks to be purchased, which converts the multivariate offloading decision problem of users into a univariate optimization problem, simplifies the offloading decision problem of users, and proves the existence of Nash equilibrium. Secondly, the KKT condition is applied to realize the offloading decision of users to purchase the optimal computing resource blocks. The upper and lower bounds of edge cloud pricing are established. Finally, a dynamic programming-based offloading (DPPO) algorithm for edge cloud pricing is proposed to achieve the optimal pricing of edge cloud utility and maximize each user’s own utility. The simulation results show that the proposed method not only achieves the equilibrium of edge cloud utility and user utility, but also has good convergence and scalability. The DPPO algorithm yields better results than with different pricing and offloading strategies.
相似文献This thesis’s object is inertial memristive neural networks (IMNNs) with proportional delays and switching jumps mismatch. Different from the traditional bounded delay, the proportional delay will be infinite as t → ∞. The finite-time synchronization (FN-TS) and fixed-time synchronization (FX-TS) can be realized with the devised controllers for the drive-response systems (D-RSs). Along with the Lyapunov function and some inequalities, the synchronization criteria of D-RSs are given. This paper presents an optimization model with minimum control energy and dynamic error as objective functions, aiming to obtain more accurate and optimized controller parameters. An intelligent algorithm: particle swarm optimization with stochastic inertia weight (SIWPSO) algorithm is introduced to solve the optimization model. Meanwhile, an integrated algorithm for selecting optimal control parameters is presented as well. In this method, the optimal control parameters and the setting time of synchronization can be obtained directly. At last, some simulations are presented to verify the theorems and the optimization model.
相似文献Person re-identification, having attracted much attention in the multimedia community, is still challenged by the accuracy and the robustness, as the images for the verification contain such variations as light, pose, noise and ambiguity etc. Such practical challenges require relatively robust and accurate feature learning technologies. We introduced a novel deep neural network with PF-BP(Particle Filter-Back Propagation) to achieve relatively global and robust performances of person re-identification. The local optima in the deep networks themselves are still the main difficulty in the learning, in despite of several advanced approaches. A novel neural network learning, or PF-BP, was first proposed to solve the local optima problem in the non-convex objective function of the deep networks. When considering final deep network to learn using BP, the overall neural network with the particle filter will behave as the PF-BP neural network. Also, a max-min value searching was proposed by considering two assumptions about shapes of the non-convex objective function to learn on. Finally, a salience learning based on the deep neural network with PF-BP was proposed to achieve an advanced person re-identification. We test our neural network learning with particle filter aimed to the non-convex optimization problem, and then evaluate the performances of the proposed system in a person re-identification scenario. Experimental results demonstrate that the corresponding performances of the proposed deep network have promising discriminative capability in comparison with other ones.
相似文献Computational intelligence shows its ability for solving many real-world problems efficiently. Synergism of fuzzy logic, evolutionary computation, and neural network can lead to development of a computational efficient and performance-rich system. In this paper, we propose a new approach for solving the human recognition problem that is the fusion of evolutionary fuzzy clustering and functional modular neural networks (FMNN). Evolutionary searching technique is applied for finding the optimal number of clusters that are generated through fuzzy clustering. The functional modular neural network has been used for recognition process that is evaluated with the help of integration based on combining the outcomes of FMNN. Performance of the proposed technique has been empirically evaluated and analyzed with the help of different parameters.
相似文献Neuroevolution is the name given to a field of computer science that applies evolutionary computation for evolving some aspects of neural networks. After the AI Winter came to an end, neural networks reemerged to solve a great variety of problems. However, their usage requires designing their topology, a decision with a potentially high impact on performance. Whereas many works have tried to suggest rules-of-thumb for designing topologies, the truth is that there are not analytic procedures for determining the optimal one for a given problem, and trial-and-error is often used instead. Neuroevolution arose almost 3 decades ago, with some works focusing on the evolutionary design of the topology and most works describing techniques for learning connection weights. Since then, evolutionary computation has been proved to be a convenient approach for determining the topology and weights of neural networks, and neuroevolution has been applied to a great variety of fields. However, for more than 2 decades neuroevolution has mainly focused on simple artificial neural networks models, far from today’s deep learning standards. This is insufficient for determining good architectures for modern networks extensively used nowadays, which involve multiple hidden layers, recurrent cells, etc. More importantly, deep and convolutional neural networks have become a de facto standard in representation learning for solving many different problems, and neuroevolution has only focused in this kind of networks in very recent years, with many works being presented in 2017 onward. In this paper, we review the field of neuroevolution during the last 3 decades. We will put the focus on very recent works on the evolution of deep and convolutional neural networks, which is a new but growing field of study. To the best of our knowledge, this is the best survey reviewing the literature in this field, and we have described the features of each work as well as their performance on well-known databases when available. This work aims to provide a complete reference of all works related to neuroevolution of convolutional neural networks up to the date. Finally, we will provide some future directions for the advancement of this research area.
相似文献Quantum state engineering is a central task in Lyapunov-based quantum control. Given different initial states, better performance may be achieved if the control parameters, such as the Lyapunov function, are individually optimized for each initial state, however, at the expense of computing resources. To tackle this issue, we propose an initial-state-adaptive Lyapunov control strategy with machine learning. Specifically, artificial neural networks are used to learn the relationship between the optimal control parameters and initial states through supervised learning with samples. Two designs are presented where the feedforward neural network and the general regression neural network are used to select control schemes and design Lyapunov functions, respectively. We demonstrate the performance of the designs with a three-level quantum system for an eigenstate control problem. Since the sample generation and the training of neural networks are carried out in advance, the initial-state-adaptive Lyapunov control can be implemented for new initial states without much increase of computational resources.
相似文献