Molecular modeling is an important topic in drug discovery. Decades of research have led to the development of high quality scalable molecular force fields. In this paper, we show that neural networks can be used to train a universal approximator for
energy potential functions. By incorporating a fully automated training process we have been able to train smooth, differentiable, and predictive potential functions on large-scale crystal structures. A variety of tests have also been performed to show the superiority and versatility of the machine-learned model.
Deep neural networks (DNNs) are playing key roles in various artificial intelligence applications such as image classification and object recognition. However, a growing number of studies have shown that there exist adversarial examples in DNNs, whic
h are almost imperceptibly different from original samples, but can greatly change the network output. Existing white-box attack algorithms can generate powerful adversarial examples. Nevertheless, most of the algorithms concentrate on how to iteratively make the best use of gradients to improve adversarial performance. In contrast, in this paper, we focus on the properties of the widely-used ReLU activation function, and discover that there exist two phenomena (i.e., wrong blocking and over transmission) misleading the calculation of gradients in ReLU during the backpropagation. Both issues enlarge the difference between the predicted changes of the loss function from gradient and corresponding actual changes, and mislead the gradients which results in larger perturbations. Therefore, we propose a universal adversarial example generation method, called ADV-ReLU, to enhance the performance of gradient based white-box attack algorithms. During the backpropagation of the network, our approach calculates the gradient of the loss function versus network input, maps the values to scores, and selects a part of them to update the misleading gradients. Comprehensive experimental results on emph{ImageNet} demonstrate that our ADV-ReLU can be easily integrated into many state-of-the-art gradient-based white-box attack algorithms, as well as transferred to black-box attack attackers, to further decrease perturbations in the ${ell _2}$-norm.
Motivated by the rapid development of energy harvesting technology and content-aware communication in access networks, this paper considers the push mechanism design in small-cell base stations (SBSs) powered by renewable energy. A user request can b
e satisfied by either push or unicast from the SBS. If the SBS cannot handle the request, the user is blocked by the SBS and is served by the macro-cell BS (MBS) instead, which typically consumes more energy. We aim to minimize the ratio of user requests blocked by the SBS. With finite battery capacity, Markov decision process based problem is formulated, and the optimal policy is found by dynamic programming (DP). Two threshold-based policies are proposed: the push-only threshold-based (POTB) policy and the energy-efficient threshold-based (EETB) policy, and the closed-form blocking probabilities with infinite battery capacity are derived. Numerical results show that the proposed policies outperform the conventional non-push policy if the content popularity changes slowly or the content request generating rate is high, and can achieve the performance of the greedy optimal threshold-based (GOTB) policy. In addition, the performance gap between the threshold-based policies and the DP optimal policy is small when the energy arrival rate is low or the request generating rate is high.
This paper considers two base stations (BSs) powered by renewable energy serving two users cooperatively. With different BS energy arrival rates, a fractional joint transmission (JT) strategy is proposed, which divides each transmission frame into tw
o subframes. In the first subframe, one BS keeps silent to store energy while the other transmits data, and then they perform zero-forcing JT (ZF-JT) in the second subframe. We consider the average sum-rate maximization problem by optimizing the energy allocation and the time fraction of ZF-JT in two steps. Firstly, the sum-rate maximization for given energy budget in each frame is analyzed. We prove that the optimal transmit power can be derived in closed-form, and the optimal time fraction can be found via bi-section search. Secondly, approximate dynamic programming (DP) algorithm is introduced to determine the energy allocation among frames. We adopt a linear approximation with the features associated with system states, and determine the weights of features by simulation. We also operate the approximation several times with random initial policy, named as policy exploration, to broaden the policy search range. Numerical results show that the proposed fractional JT greatly improves the performance. Also, appropriate policy exploration is shown to perform close to the optimal.
It is widely acknowledged that the forthcoming 5G architecture will be highly heterogeneous and deployed with a high degree of density. These changes over the current 4G bring many challenges on how to achieve an efficient operation from the network
management perspective. In this article, we introduce a revolutionary vision of the future 5G wireless networks, in which the network is no longer limited by hardware or even software. Specifically, by the idea of virtualizing the wireless networks, which has recently gained increasing attention, we introduce the Everything-as-a-Service (XaaS) taxonomy to light the way towards designing the service-oriented wireless networks. The concepts, challenges along with the research opportunities for realizing XaaS in wireless networks are overviewed and discussed.
Non-Orthogonal Multiple Access (NOMA) has been proposed to enhance the Spectrum Efficiency (SE) and cell-edge capacity. This paper considers the massive Multi-Input Multi-Output (MIMO) with Non-Orthogonal Multiple Access (NOMA) encoding. The close-fo
rm expression of capacity of the massive MIMO with NOMA is given here. Apart from the previous Successive Interference Cancellation (SIC) method, the Power Hard Limiter (PHD) is introduced here for better reality implement.
Energy Efficiency (EE) is a big issue in 5th Generation Wireless Communications (5G) on condition that the number of access User Equipments (UEs) are exploding and more antennas should be equipped in one Base Station (BS). In EE studies, prior litera
tures focus on the energy consumption of single separated BS coverage area or through scheduling mechanism or network coding method. But some other elements are ignored in those literatures, such as the energy consumption of machine room, circuit, etc. In this paper, to be more closer to the reality, based on the Cloud Radio Access Network (C-RAN), we modify its traditional structure for easier layout of sleeping mechanism in the real world, study the EE issue within a comprehensive view while taking more elements into consideration. We modified the traditional C-RAN structure with the purpose of much easily adopting the sleeping mechanism with on-off selection method. Afterwards, the EE issue is modeled into a mathematical optimizing problem and its solution is given by a tractable method. The analysis of sum capacity in one cluster of this modified structure is addressed first. Then based on the analysis, the EE issue is studied with a comprehensive view while taking more elements into consideration. In the next step, we convert it into an optimization problem and give its solution with the sleeping techniques. Comparing with prior works, this proposal is of better performance for the merit of comprehensive vision and easier layout characteristic.
The explosive growth of mobile multimedia traffic calls for scalable wireless access with high quality of service and low energy cost. Motivated by the emerging energy harvesting communications, and the trend of caching multimedia contents at the acc
ess edge and user terminals, we propose a paradigm-shift framework, namely GreenDelivery, enabling efficient content delivery with energy harvesting based small cells. To resolve the two-dimensional randomness of energy harvesting and content request arrivals, proactive caching and push are jointly optimized, with respect to the content popularity distribution and battery states. We thus develop a novel way of understanding the interplay between content and energy over time and space. Case studies are provided to show the substantial reduction of macro BS activities, and thus the related energy consumption from the power grid is reduced. Research issues of the proposed GreenDelivery framework are also discussed.
Motivated by the recent development of energy harvesting communications, and the trend of multimedia contents caching and push at the access edge and user terminals, this paper considers how to design an effective push mechanism of energy harvesting
powered small-cell base stations (SBSs) in heterogeneous networks. The problem is formulated as a Markov decision process by optimizing the push policy based on the battery energy, user request and content popularity state to maximize the service capability of SBSs. We extensively analyze the problem and propose an effective policy iteration algorithm to find the optimal policy. According to the numerical results, we find that the optimal policy reveals a state dependent threshold based structure. Besides, more than 50% performance gain is achieved by the optimal push policy compared with the non-push policy.
Mott insulators with both spin and orbital degeneracy are pertinent to a large number of transition metal oxides. The intertwined spin and orbital fluctuations can lead to rather exotic phases such as quantum spin-orbital liquids. Here we consider tw
o-component (spin 1/2) fermionic atoms with strong repulsive interactions on the $p$-band of the optical square lattice. We derive the spin-orbital exchange for quarter filling of the $p$-band when the density fluctuations are suppressed, and show it frustrates the development of long range spin order. Exact diagonalization indicates a spin-disordered ground state with ferro-orbital order. The system dynamically decouples into individual Heisenberg spin chains, each realizing a Luttinger liquid accessible at higher temperatures compared to atoms confined to the $s$-band.
