CSatDTA: Prediction of Drug–Target Binding Affinity Using Convolution Model with Self-Attention

Drug discovery, which aids to identify potential novel treatments, entails a broad range of fields of science, including chemistry, pharmacology, and biology. In the early stages of drug development, predicting drug–target affinity is crucial. The proposed model, the prediction of drug–target affinity using a convolution model with self-attention (CSatDTA), applies convolution-based self-attention mechanisms to the molecular drug and target sequences to predict drug–target affinity (DTA) effectively, unlike previous convolution methods, which exhibit significant limitations related to this aspect. The convolutional neural network (CNN) only works on a particular region of information, excluding comprehensive details. Self-attention, on the other hand, is a relatively recent technique for capturing long-range interactions that has been used primarily in sequence modeling tasks. The results of comparative experiments show that CSatDTA surpasses previous sequence-based or other approaches and has outstanding retention abilities.     

神经元网络——它的背景、进展和问题

近年来神经元网络研究的进展,在国际学术界引起了强烈的轰动,成了各界学人的热门话题.本文分析了神经元网络研究的来龙去脉,简要介绍了若干代表性的进展,指出了这一研究的意义、问题和进一步研究的方向,希望引起各界同仁的关注.     

Combination of interference alignment and beamforming in cellular networks

In this paper, we propose two joint transmit-receive iterative algorithms without the cooperation between different base stations based on the idea of interference alignment (IA) to improve the throughput of relay backhaul links in cellular networks for the case of imperfect channel knowledge,which can be implemented with small changes to existing TD-LTE standards. Unlike the previous interference alignment algorithms’ only reducing the sum interference to the other receivers at the transmitter or the sum received Multi-user interference (MUI) at the receiver, our algorithm shapes the transmission of each data stream at transmitters in order not only to minimize interference to the other users, but also to minimize the interference between different streams objected to the same user, suppressing the MUI and Multi-stream interference (MSI) at receivers. The proposed algorithm I is to maximize the SINR at receivers. But the complexity is relatively high. Algorithm II only needs linear operations and sacrifices a little performance for much lower complexity compared to the Maximize SINR iterative algorithm which needs the inversion operation of matrix. It is also proved that the algorithm converges monotonically. The simulation results show that the techniques have considerable performance gain compared with the previous algorithms. Further research about power allocation is also discussed.     

误差反向传播算法的数学推导及实现步骤

提供了人工神经网络的一种算法-误差反向传播算法的数学推导方法及上机实现步骤.     

Decentralized adaptive recurrent neural control structure

This paper presents a novel decentralized variable structure neural control approach for large-scale uncertain systems, which is developed using recurrent high-order neural networks (RHONN). It is assumed that each subsystem belongs to a class of block-controllable nonlinear systems whose vector fields includes interconnection terms, which are bounded by nonlinear functions. A decentralized RHONN structure and the respective learning law are proposed in order to approximate online the dynamical behavior of each nonlinear subsystem. The control law, which is able to regulate and to track the desired reference signals, is designed using the well-known variable structure theory. The stability of the whole system is analyzed via the Lyapunov methodology. The applicability of the proposed decentralized identification and control algorithm is illustrated via simulations as applied to an interconnected double inverted pendulum.     

动态核的形态分解联想算法及抗随机噪声研究

在灰度图像分解算法和动态核形态联想记忆网络的基础上,提出了一种新的联想记忆算法--动态核的形态分解联想算法.该方法显著地提高了联想记忆抗随机噪声的能力,较好地解决了灰度图像在含噪时的联想记忆和识别的问题,从而给出了一种恢复含噪灰度图像的途径,并把该方法推广到了彩色图像的处理.通过实验,验证了该方法的良好性能,取得了理想的结果.     

基于人工神经网络的原油触变特性参数计算

基于Levenberg-Marquardt算法的前馈BP网络的原油触变特性参数计算方法,计算触变特性参数精度高,不依赖于具体的函数形式,能有效克服传统计算方法的不足。     

拱坝近似优化的人工神经网络方法

以国内已建拱坝体形参数为基础,以ＢＰ神经网络方法为手段,建立了拱坝体形参数近似优化的人工神经网络模型．借助该模型不仅可以为拱坝体形优化快速提供高质量的初始可行解,而且可为中、小拱坝体形设计直接提供近似最优解．     

基于软计算思想解决含干扰输入多值异或问题的研究

介绍一种解决含干扰输入多值异或问题的方法。该方法利用遗传算法寻找神经网络结构,使用模糊逻辑控制神经网络的学习率和冲量,并用传播算法训练得到神经网络。结果显示,这种方法能针对问题得到泛化性能、时间复杂度上表现都较为优秀的网络。