Explore the vast range of titles available.

In the Knowledge Grounded Dialogue (KGD) generation, the explicit modeling of instance-variety of knowledge specificity and its seamless fusion with the dialogue context remains challenging. This paper presents an innovative approach, the Knowledge Interpolated conditional Variational auto-encoder (KIV), to address these issues. In particular, KIV introduces a novel interpolation mechanism to fuse two latent variables: independently encoding dialogue context and grounded knowledge. This distinct fusion of context and knowledge in the semantic space enables the interpolated latent variable to guide the decoder toward generating more contextually rich and engaging responses. We further explore deterministic and probabilistic methodologies to ascertain the interpolation weight, capturing the level of knowledge specificity. Comprehensive empirical analysis conducted on the Wizard-of-Wikipedia and Holl-E datasets verifies that the responses generated by our model performs better than strong baselines, with notable performance improvements observed in both automatic metrics and manual evaluation.

Medical image segmentation has the priori guiding significance for clinical diagnosis and treatment. In the past ten years, a large number of experimental facts have proved the great success of deep convolutional neural networks in various medical image segmentation tasks. However, the convolutional networks seem to focus too much on the local image details, while ignoring the long-range dependence. The Transformer structure can encode long-range dependencies in image and learn high-dimensional image information through the self-attention mechanism. But this structure currently depends on the database scale to give full play to its excellent performance, which limits its application in medical images with limited database size. In this paper, the characteristics of CNNs and Transformer are integrated to propose a dual encoding–decoding structure of the X-shaped network (X-Net). It can serve as a good alternative to the traditional pure convolutional medical image segmentation network. In the encoding phase, the local and global features are simultaneously extracted by two types of encoders, convolutional downsampling, and Transformer and then merged through jump connection. In the decoding phase, a variational auto-encoder branch is added to reconstruct the input image itself in order to weaken the impact of insufficient data. Comparative experiments on three medical image datasets show that X-Net can realize the organic combination of Transformer and CNNs.

Quantum devices with a large number of gate electrodes allow for precise control of device parameters. This capability is hard to fully exploit due to the complex dependence of these parameters on applied gate voltages. We experimentally demonstrate an algorithm capable of fine-tuning several device parameters at once. The algorithm acquires a measurement and assigns it a score using a variational auto-encoder. Gate voltage settings are set to optimize this score in real-time in an unsupervised fashion. We report fine-tuning times of a double quantum dot device within approximately 40 min.

The disentanglement of different objective properties from the external world is the foundation of language development for agents. The basic target of this process is to summarise the common natural properties and then to name it to describe those properties in the future. To realise this purpose, a new learning model is introduced for the disentanglement of several sensorimotor concepts (e.g. sizes, colours and shapes of objects) while the causal relationship is being learnt during interaction without much a priori experience and external instructions. This learning model links predictive deep neural models and the variational auto-encoder (VAE) and provides the possibility that the independent concepts can be extracted and disentangled from both perception and action. Moreover, such extraction is further learnt by VAE to memorise their common statistical features. The authors examine this model in the affordance learning setting, where the robot is trying to learn to disentangle about shapes of the tools and objects. The results show that such a process can be found in the neural activities of the $\\beta $β-VAE unit, which indicate that using similar VAE models is a promising way to learn the concepts, and thereby to learn the causal relationship of the sensorimotor interaction.

Prediction based on time series has a wide range of applications. Due to the complex nonlinear and random distribution of time series data, the performance of learning prediction models can be reduced by the modeling bias or overfitting. This paper proposes a novel planar flow-based variational auto-encoder prediction model (PFVAE), which uses the long- and short-term memory network (LSTM) as the auto-encoder and designs the variational auto-encoder (VAE) as a time series data predictor to overcome the noise effects. In addition, the internal structure of VAE is transformed using planar flow, which enables it to learn and fit the nonlinearity of time series data and improve the dynamic adaptability of the network. The prediction experiments verify that the proposed model is superior to other models regarding prediction accuracy and proves it is effective for predicting time series data.

Due to the strong concealment of electricity theft and the limitation of inspection resources, the number of power theft samples mastered by the power department is insufficient, which limits the accuracy of power theft detection. Therefore, a data augmentation method for electricity theft detection based on the conditional variational auto-encoder (CVAE) is proposed. Firstly, the stealing power curves are mapped into low dimensional latent variables by using the encoder composed of convolutional layers, and the new stealing power curves are reconstructed by the decoder composed of deconvolutional layers. Then, five typical attack models are proposed, and the convolutional neural network is constructed as a classifier according to the data characteristics of stealing power curves. Finally, the effectiveness and adaptability of the proposed method is verified by a smart meters’ data set from London. The simulation results show that the CVAE can take into account the shapes and distribution characteristics of samples at the same time, and the generated stealing power curves have the best effect on the performance improvement of the classifier than the traditional augmentation methods such as the random oversampling method, synthetic minority over-sampling technique, and conditional generative adversarial network. Moreover, it is suitable for different classifiers.

Optimal integration of transcriptomics data and associated spatial information is essential towards fully exploiting spatial transcriptomics to dissect tissue heterogeneity and map out inter-cellular communications. We present SEDR, which uses a deep autoencoder coupled with a masked self-supervised learning mechanism to construct a low-dimensional latent representation of gene expression, which is then simultaneously embedded with the corresponding spatial information through a variational graph autoencoder. SEDR achieved higher clustering performance on manually annotated 10 × Visium datasets and better scalability on high-resolution spatial transcriptomics datasets than existing methods. Additionally, we show SEDR’s ability to impute and denoise gene expression (URL: https://github.com/JinmiaoChenLab/SEDR/ ).

Variational auto-encoders (VAE) have been widely used in process modeling due to the ability of deep feature extraction and noise robustness. However, the construction of a supervised VAE model still faces huge challenges. The data generated by the existing supervised VAE models are unstable and uncontrollable due to random resampling in the latent subspace, meaning the performance of prediction is greatly weakened. In this paper, a new multi-layer conditional variational auto-encoder (M-CVAE) is constructed by injecting label information into the latent subspace to control the output data generated towards the direction of the actual value. Furthermore, the label information is also used as the input with process variables in order to strengthen the correlation between input and output. Finally, a neural network layer is embedded in the encoder of the model to achieve online quality prediction. The superiority and effectiveness of the proposed method are demonstrated by two real industrial process cases that are compared with other methods.

The Internet of Things (IoT) refers to a system of interconnected, internet-connected devices and sensors that allows the collection and dissemination of data. The data provided by these sensors may include outliers or exhibit anomalous behavior as a result of attack activities or device failure, for example. However, the majority of existing outlier detection algorithms rely on labeled data, which is frequently hard to obtain in the IoT domain. More crucially, the IoT’s data volume is continually increasing, necessitating the requirement for predicting and identifying the classes of future data. In this study, we propose an unsupervised technique based on a deep Variational Auto-Encoder (VAE) to detect outliers in IoT data by leveraging the characteristic of the reconstruction ability and the low-dimensional representation of the input data’s latent variables of the VAE. First, the input data are standardized. Then, we employ the VAE to find a reconstructed output representation from the low-dimensional representation of the latent variables of the input data. Finally, the reconstruction error between the original observation and the reconstructed one is used as an outlier score. Our model was trained only using normal data with no labels in an unsupervised manner and evaluated using Statlog (Landsat Satellite) dataset. The unsupervised model achieved promising and comparable results with the state-of-the-art outlier detection schemes with a precision of ≈90% and an F1 score of 79%.

Anomalies frequently occur during the operation of spacecraft in orbit, and studying anomaly detection methods is crucial to ensure the normal operation of spacecraft. Due to the complexity of spacecraft structures, telemetry data possess characteristics such as high dimensionality, complexity, and large scale. Existing methods frequently ignore or fail to explicitly extract the correlation between variables, and due to the lack of prior knowledge, it is difficult to obtain the initial relationship of variables. To address these issues, this paper proposes a new method, namely spatio-temporal graph learning reconstruction (STGLR), for spacecraft anomaly detection. STGLR employs a dynamic graph learning module to infer the initial relationships among telemetry variables. It then constructs a spatio-temporal feature extraction module to capture complex spatio-temporal dependencies among variables, leveraging a graph sample and aggregation network to learn embedded features and incorporating an attention mechanism to adaptively select salient features. Finally, a reconstruction module is used to learn the latent representations of features, capturing the normal patterns in telemetry data and achieving anomaly detection. To validate the effectiveness of the proposed method, experiments were conducted on two public spacecraft datasets, and the results demonstrate that the performance of the STGLR method surpasses existing anomaly detection methods, with an average F1 score exceeding 0.97.