The goal of decentralized optimization over a network is to optimize a global objective formed by a sum of local (possibly nonsmooth) convex functions using only local computation and communication. We develop and ana...
详细信息
ISBN:
(纸本)9781617823800
The goal of decentralized optimization over a network is to optimize a global objective formed by a sum of local (possibly nonsmooth) convex functions using only local computation and communication. We develop and analyze distributed algorithms based on dual averaging of subgradients, and provide sharp bounds on their convergence rates as a function of the network size and topology. Our analysis clearly separates the convergence of the optimization algorithm itself from the effects of communication constraints arising from the network structure. We show that the number of iterations required by our algorithm scales inversely in the spectral gap of the network. The sharpness of this prediction is confirmed both by theoretical lower bounds and simulations for various networks.
In this paper, a new method combined fuzzy theory and neuralnetwork was proposed, which was employed to solve multi-maneuvering target tracking. Multi-maneuvering target tracking is a process, which manages measure i...
详细信息
ISBN:
(纸本)9781424451944
In this paper, a new method combined fuzzy theory and neuralnetwork was proposed, which was employed to solve multi-maneuvering target tracking. Multi-maneuvering target tracking is a process, which manages measure information to maintain currently state estimate. The fields of fuzzy sets and neuralnetwork have made rapid progress in recent years. neuralnetworks are nonlinear network of self-organization and self-learning, they possess the capabilities of large-scale parallel processing, distributed information, neuralnetwork have important influence on the revolution of traditional target tracking theory. The training of fuzzy rule-based systems by using the learning ability of neuralnetwork can improve the expression ability of the network. Combining the fuzzy theory and neuralnetwork is a new approach to solve multi-maneuvering target tracking.
We introduce a type of 2-tier convolutional neuralnetwork model for learning distributed paragraph representations for a special task (e.g. paragraph or short document level sentiment analysis and text topic categori...
详细信息
ISBN:
(纸本)9783319265322;9783319265315
We introduce a type of 2-tier convolutional neuralnetwork model for learning distributed paragraph representations for a special task (e.g. paragraph or short document level sentiment analysis and text topic categorization). We decompose the paragraph semantics into 3 cascaded constitutes: word representation, sentence composition and document composition. Specifically, we learn distributed word representations by a continuous bag-of-words model from a large unstructured text corpus. Then, using these word representations as pre-trained vectors, distributed task specific sentence representations are learned from a sentence level corpus with task-specific labels by the first tier of our model. Using these sentence representations as distributed paragraph representation vectors, distributed paragraph representations are learned from a paragraph-level corpus by the second tier of our model. It is evaluated on DBpedia ontology classification dataset and Amazon review dataset. Empirical results show the effectiveness of our proposed learning model for generating distributed paragraph representations.
In this paper, we are able to focus on the fiber-optic distributed acoustic systems required to isolate the oil and gas pipeline, remote areas, facilities and lines in the area. Threatening performances of network str...
详细信息
ISBN:
(纸本)9781728119045
In this paper, we are able to focus on the fiber-optic distributed acoustic systems required to isolate the oil and gas pipeline, remote areas, facilities and lines in the area. Threatening performances of network structures of different complexity and depth. All measurements, the criteria for working independently from the field, the results obtained and the results obtained and on-site troubleshooting methods in different geographical areas. It analyzes the performance results and shows a high performance network in the field in real time.
This paper proposes a neuralnetwork based speech separation method using spatially distributed microphones. Unlike with traditional microphone array settings, neither the number of microphones nor their spatial arran...
详细信息
ISBN:
(纸本)9781713820697
This paper proposes a neuralnetwork based speech separation method using spatially distributed microphones. Unlike with traditional microphone array settings, neither the number of microphones nor their spatial arrangement is known in advance, which hinders the use of conventional multi-channel speech separation neuralnetworks based on fixed size input. To overcome this, a novel network architecture is proposed that interleaves inter-channel processing layers and temporal processing layers. The inter-channel processing layers apply a self-attention mechanism along the channel dimension to exploit the information obtained with a varying number of microphones. The temporal processing layers are based on a bidirectional long short term memory (BLSTM) model and applied to each channel independently. The proposed network leverages information across time and space by stacking these two kinds of layers alternately. Our network estimates time-frequency (TF) masks for each speaker, which are then used to generate enhanced speech signals either with TF masking or beamforming. Speech recognition experimental results show that the proposed method significantly outperforms baseline multi-channel speech separation systems.
We present a robust distributed algorithm for approximate probabilistic inference in dynamical systems, such as sensor networks and teams of mobile robots. Using assumed density filtering, the network nodes maintain a...
详细信息
ISBN:
(纸本)9780262195683
We present a robust distributed algorithm for approximate probabilistic inference in dynamical systems, such as sensor networks and teams of mobile robots. Using assumed density filtering, the network nodes maintain a tractable representation of the belief state in a distributed fashion. At each time step, the nodes coordinate to condition this distribution on the observations made throughout the network, and to advance this estimate to the next time step. In addition, we identify a significant challenge for probabilistic inference in dynamical systems: message losses or network partitions can cause nodes to have inconsistent beliefs about the current state of the system. We address this problem by developing distributed algorithms that guarantee that nodes will reach an informative consistent distribution when communication is re-established. We present a suite of experimental results on real-world sensor data for two real sensor network deployments: one with 25 cameras and another with 54 temperature sensors.
Large-scale and distributed software development initiatives demand a systematic testing process in order to prevent failures. Significant amount of resources are usually allocated on testing. Like any development and...
详细信息
ISBN:
(数字)9783319466811
ISBN:
(纸本)9783319466811;9783319466804
Large-scale and distributed software development initiatives demand a systematic testing process in order to prevent failures. Significant amount of resources are usually allocated on testing. Like any development and designing task, testing activities have to be prioritised in order to efficiently validate the produced code. By using source code complexity measurement, Computational Intelligence and Image processing techniques, this research presents a new approach to prioritise testing efforts on large-scale and distributed software projects. The proposed technique was validated by automatically highlighting sensitive code within the Linux device drivers source code base. Our algorithm was able to classify 3, 077 from 35, 091 procedures as critical code to be tested. We argue that the approach is general enough to prioritise test tasks of most critical large-scale and distributed developed software such as: Operating Systems, Enterprise Resource Planning and Content Management systems.
A grey neuralnetwork model was proposed on the basis of the models. The fluctuation of data sequence is weakened by the grey theory and the neuralnetwork is capable of processing non-linear adaptable information, an...
详细信息
ISBN:
(纸本)0769529097
A grey neuralnetwork model was proposed on the basis of the models. The fluctuation of data sequence is weakened by the grey theory and the neuralnetwork is capable of processing non-linear adaptable information, and the GNN is a combination of those advantages. The results reveal, the alkalinity of sinter can be accurately predicted through this model by reference to small sample and information. It was concluded that the GNN model is effective with the advantages of high precision, less requirement of samples and comparatively simple calculation.
The remarkable processing capabilities of the nervous system must derive at least in part from the large numbers of neurons participating (roughly 1010), since the timescales involved are of the order of milliseconds,...
详细信息
The remarkable processing capabilities of the nervous system must derive at least in part from the large numbers of neurons participating (roughly 1010), since the timescales involved are of the order of milliseconds, rather than the nanoseconds of modern computers. We summarise common features of the neuralnetwork models which attempt to capture this behaviour and describe the many levels of parallelism which they exhibit. A range of models has been implemented on the SIMD (ICL distributed Array Processor) and MIMD (Meiko Computing Surface) hardware at Edinburgh. Examples include: (i) training algorithms in the context of the Hopfield net, with specific application to the storage of words and text with content-addressable memory; (ii) the back-propagation training algorithm for the multi-layer perception; (iii) image restoration with Hopfield and Tank analogue neurons, and (iv) the Durbin and Willshaw elastic net, as applied to the travelling salesman problem.
Deployment of pattern recognition applications for large-scale data sets is an open issue that needs to be addressed. In this paper, an attempt is made to explore new methods of partitioning and distributing data, tha...
详细信息
ISBN:
(纸本)9783642249570;9783642249587
Deployment of pattern recognition applications for large-scale data sets is an open issue that needs to be addressed. In this paper, an attempt is made to explore new methods of partitioning and distributing data, that is, resource virtualization in the cloud by fundamentally re-thinking the way in which future data management models will need to be developed on the Internet. The work presented here will incorporate content-addressable memory into Cloud data processing to entail a large number of loosely-coupled parallel operations resulting in vastly improved performance. Using a lightweight associative memory algorithm known as distributed Hierarchical Graph Neuron (DHGN), data retrieval/processing can be modeled as pattern recognition/matching problem, conducted across multiple records and data segments within a single-cycle, utilizing a parallel approach. The proposed model envisions a distributed data management scheme for large-scale data processing and database updating that is capable of providing scalable real-time recognition and processing with high accuracy while being able to maintain low computational cost in its function.
暂无评论