Network Bending: Expressive Manipulation of Generative Models in Multiple Domains

This paper presents the network bending framework, a new approach for manipulating and interacting with deep generative models. We present a comprehensive set of deterministic transformations that can be inserted as distinct layers into the computational graph of a trained generative neural network and applied during inference. In addition, we present a novel algorithm for analysing the deep generative model and clustering features based on their spatial activation maps. This allows features to be grouped together based on spatial similarity in an unsupervised fashion. This results in the meaningful manipulation of sets of features that correspond to the generation of a broad array of semantically significant features of the generated results. We outline this framework, demonstrating our results on deep generative models for both image and audio domains. We show how it allows for the direct manipulation of semantically meaningful aspects of the generative process as well as allowing for a broad range of expressive outcomes.     

A Classical Formulation of Quantum Theory?

We explore a particular way of reformulating quantum theory in classical terms, starting with phase space rather than Hilbert space, and with actual probability distributions rather than quasiprobabilities. The classical picture we start with is epistemically restricted, in the spirit of a model introduced by Spekkens. We obtain quantum theory only by combining a collection of restricted classical pictures. Our main challenge in this paper is to find a simple way of characterizing the allowed sets of classical pictures. We present one promising approach to this problem and show how it works out for the case of a single qubit.     

Application of Deep Eutectic Solvents in the Synthesis of Substituted 2-Mercaptoquinazolin-4(3H)-Ones: A Comparison of Selected Green Chemistry Methods

In this study, deep eutectic solvents (DESs) were used as green and eco-friendly media for the synthesis of substituted 2-mercaptoquinazolin-4(3H)-ones from different anthranilic acids and aliphatic or aromatic isothiocyanates. A model reaction on anthranilic acid and phenyl isothiocyanate was performed in 20 choline chloride-based DESs at 80 °C to find the best solvent. Based on the product yield, choline chloride:urea (1:2) DES was found to be the most effective, while DESs acted both as solvents and catalysts. Desired compounds were prepared with moderate to good yields using stirring, microwave-assisted, and ultrasound-assisted synthesis. Significantly, higher yields were obtained with mixing and ultrasonication (16–76%), while microwave-induced synthesis showed lower effectiveness (13–49%). The specific contribution of this research is the use of DESs in combination with the above-mentioned green techniques for the synthesis of a wide range of derivatives. The structures of the synthesized compounds were confirmed by ¹H and ¹³C NMR spectroscopy.     

Fusion Domain-Adaptation CNN Driven by Images and Vibration Signals for Fault Diagnosis of Gearbox Cross-Working Conditions

The vibration signal of gearboxes contains abundant fault information, which can be used for condition monitoring. However, vibration signal is ineffective for some non-structural failures. In order to resolve this dilemma, infrared thermal images are introduced to combine with vibration signals via fusion domain-adaptation convolutional neural network (FDACNN), which can diagnose both structural and non-structural failures under various working conditions. First, the measured raw signals are converted into frequency and squared envelope spectrum to characterize the health states of the gearbox. Second, the sequences of the frequency and squared envelope spectrum are arranged into two-dimensional format, which are combined with infrared thermal images to form fusion data. Finally, the adversarial network is introduced to realize the state recognition of structural and non-structural faults in the unlabeled target domain. An experiment of gearbox test rigs was used for effectiveness validation by measuring both vibration and infrared thermal images. The results suggest that the proposed FDACNN method performs best in cross-domain fault diagnosis of gearboxes via multi-source heterogeneous data compared with the other four methods.     

A Probabilistic Re-Intepretation of Confidence Scores in Multi-Exit Models

In this paper, we propose a new approach to train a deep neural network with multiple intermediate auxiliary classifiers, branching from it. These ‘multi-exits’ models can be used to reduce the inference time by performing early exit on the intermediate branches, if the confidence of the prediction is higher than a threshold. They rely on the assumption that not all the samples require the same amount of processing to yield a good prediction. In this paper, we propose a way to train jointly all the branches of a multi-exit model without hyper-parameters, by weighting the predictions from each branch with a trained confidence score. Each confidence score is an approximation of the real one produced by the branch, and it is calculated and regularized while training the rest of the model. We evaluate our proposal on a set of image classification benchmarks, using different neural models and early-exit stopping criteria.     

胶质液体泡沫(CLA)的形成及其稳定性研究

以研究胶质液体泡沫(CLA)内部结构及其特性为最终目的, 对组成为十二烷基醇聚氧乙烯(3)醚(AEO-3)/正癸烷/十二烷基硫酸钠(SDS)/水的CLA体系形成过程和稳定动力学行为进行了电导率测定和光学显微观察. 通过上述两过程的电导率变化探明了CLA的形成和稳定性动力学行为, 并被光学显微照片所证实. 实验结果表明CLA的形成是一个低能量乳化过程, 经历了水相泡沫化→油相替代气泡乳化→CLA形成. 在整个乳化过程中, 没有发生相的转变现象, CLA呈O/W型乳状液. 其稳定性并不遵守一级动力学模型. 在常温下, 其电导率曲线呈直线关系; 当温度超过318.15 K时, 其电导率曲线近似于Langmuir等温线形. 并可用Sigmoidal模型σ_t=(σ₁－σ₂)/[1＋e^(t－t₀)/S] ＋σ₂较好的拟合, 式中, σ_t表示t 时的电导率值(μS/cm); t表示时间(min); σ₁, σ₂分别代表存储过程中电导率最小值和最大值(μS/cm); t₀对应于σ_t等于 1/2(σ₁＋σ₂)的时间t值(min); S描述了电导率曲线陡峭程度(min). 并提出了CLA的破乳过程包括液膜排液和液膜破裂两个阶段, 同时伴随有絮凝过程发生的稳定性机理.     

有机杂化锑硒化合物的溶剂热合成与晶体结构

自1996年Kanatzid is以有机胺为结构导向剂,第一次用溶剂热法合成了含过渡金属钴的锑硫化物[Co(en)3]CoSb4S8[3]以来,水热和溶剂热技术逐渐成为合成多元金属硫属化物的重要方法[1-7]。本文以FeC l2·4H2O、Sb和Se为原料,在乙二胺中于140℃进行溶剂热反应,合成了锑硒化合物[Fe(e     

纳米六方相氮化铝的合成和光学性能研究

报道了以AlCl₃和Mg₃N₂为反应物, 在500 ℃条件下, 用简易的设备, 合成六方相AlN纳米材料. 样品的XRD和XPS图谱表明, 实验得到的AlN样品是纯的六方相AlN, 其中的杂质相含量均小于仪器的探测灵敏度. TEM图表明, AlN样品呈多孔网络状结构, 网络的骨架大小在10～20 nm之间. 对AlN样品的光学性能的研究表明, AlN样品的禁带宽度值约为6.12 eV; 红外吸收谱以680 cm^－1为中心形成一个很宽的红外吸收带; 其拉曼散射峰较AlN薄膜和AlN单晶向低波数方向移动.     

分子旋光度的密度泛函计算及Soman绝对构型确定

手性化合物绝对构型的确定一直是有机化学特别是手性药物合成研究过程中经常遇到的问题之一. 利用密度泛函DFT/B3LYP量子化学计算方法, 通过计算两种已知旋光度分子的旋光度, 确认计算条件和验证计算结果的可靠性, 并将此方法应用于Soman旋光度的计算. 结合文献报道的Soman分子实验旋光度测定结果, 首次采用理论计算方法确定了梭曼(Soman)分子四个异构体的绝对构型, 分别为P(R),C(S)-Soman→P(＋)C(＋), P(R),C(R)-Soman→P(＋)C(－), P(S),C(S)-Soman→P(－)C(＋), P(S),C(R)-Soman→P(－)C(－).