Our purpose is, in medium term, to detect in air images, characteristic shapes and objects such as airports, industrial plants, planes, tanks, trucks, ... with great accuracy and low rate of mistakes. However, we also...
详细信息
ISBN:
(纸本)0819438545
Our purpose is, in medium term, to detect in air images, characteristic shapes and objects such as airports, industrial plants, planes, tanks, trucks, ... with great accuracy and low rate of mistakes. However, we also want to value whether the link between neuralnetworks and multi-agents systems is relevant and effective. If it appears to be really effective, we hope to use this kind of technology in other fields. That would be an easy and convenient way to depict and to use the agents' knowledge which is distributed and fragmented. After a first phase of preliminary tests to know if agents are able to give relevant information to a neuralnetwork, we verify that only a few agents running on an image are enough to inform the network and let it generalize the agents' distributed and fragmented knowledge. In a second phase, we developed a distributed architecture allowing several, multi-agents systems running at the same time on different computers with different images. All those agents send information to a "multi neuralnetworks system" whose job is to identify the shapes detected by the agents. The name we gave to our project is Jarod.
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 study the nonlinear regression problem in a network of nodes and introduce long short term memory (LSTM) based algorithms. In order to learn the parameters of the LSTM architecture in an online manne...
详细信息
ISBN:
(纸本)9781509064946
In this paper, we study the nonlinear regression problem in a network of nodes and introduce long short term memory (LSTM) based algorithms. In order to learn the parameters of the LSTM architecture in an online manner, we put. the LSTM equations into a nonlinear state space form and then introduce our distributed particle filtering (DPF) based training algorithm. Our training algorithm asymptotically achieves the optimal training performance. In our simulations, we illustrate the performance improvement achieved by the introduced algorithm with respect to the conventional methods.
Efficient and robust algorithms for decentralized estimation in networks are essential to many distributed systems. Whereas distributed estimation of sample mean statistics has been the subject of a good deal of atten...
详细信息
Efficient and robust algorithms for decentralized estimation in networks are essential to many distributed systems. Whereas distributed estimation of sample mean statistics has been the subject of a good deal of attention, computation of U-statistics, relying on more expensive averaging over pairs of observations, is a less investigated area. Yet, such data functionals are essential to describe global properties of a statistical population, with important examples including Area Under the Curve, empirical variance, Gini mean difference and within-cluster point scatter. This paper proposes new synchronous and asynchronous randomized gossip algorithms which simultaneously propagate data across the network and maintain local estimates of the U-statistic of interest. We establish convergence rate bounds of O(1/t) and O(log t/t) for the synchronous and asynchronous cases respectively, where t is the number of iterations, with explicit data and network dependent terms. Beyond favorable comparisons in terms of rate analysis, numerical experiments provide empirical evidence the proposed algorithms surpasses the previously introduced approach.
In our mobile vehicle project, sensors for environment modeling are a CCD color camera and two line-scan laser range finders. The CCD color camera is used to detect road edges. The two line-scan laser range finders ar...
详细信息
ISBN:
(纸本)0819442836
In our mobile vehicle project, sensors for environment modeling are a CCD color camera and two line-scan laser range finders. The CCD color camera is used to detect road edges. The two line-scan laser range finders are used to detect obstacles. Only two line-scan laser range finders increase processing speed, but there are blind zones for low obstacles, especially near the vehicle. In this paper, neuralnetwork and fuzzy logic are used to cluster and fuse obstacle points provided by two line-scan laser range finders. There is an assumption that obstacles missed by laser radar in some instant must be detected previously. A circle Adaptive Resonance neuralnetwork algorithm is used to incrementally cluster obstacle points provided by laser range finders into candidate obstacles. Every candidate obstacle is expressed by a circle, and is assigned a belief by a fuzzy logic system. Inputs of the fuzzy logic system are radius and number of points. Fuzzy rules are provided by human and can be fine-tuned with training data. The final true obstacle is the nearest one chosen from candidate obstacles whose beliefs exceed a threshold. Experiment results indicate that our mobile vehicle can safely follow road and avoid obstacles.
Nearest neighbor is a popular nonparametric method for classification and regression with many appealing properties. In the big data era, the sheer volume and spatial/temporal disparity of big data may prohibit centra...
ISBN:
(纸本)9781713829546
Nearest neighbor is a popular nonparametric method for classification and regression with many appealing properties. In the big data era, the sheer volume and spatial/temporal disparity of big data may prohibit centrally processing and storing the data. This has imposed considerable hurdle for nearest neighbor predictions since the entire training data must be memorized. One effective way to overcome this issue is the distributed learning framework. Through majority voting, the distributed nearest neighbor classifier achieves the same rate of convergence as its oracle version in terms of the regret, up to a multiplicative constant that depends solely on the data dimension. The multiplicative difference can be eliminated by replacing majority voting with the weighted voting scheme. In addition, we provide sharp theoretical upper bounds of the number of subsamples in order for the distributed nearest neighbor classifier to reach the optimal convergence rate. It is interesting to note that the weighted voting scheme allows a larger number of subsamples than the majority voting one. Our findings are supported by numerical studies.
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.
Power load forecasting is an important part of the power system planning, and accurate load forecasting can provide necessary basis data for the dispatcher, which is extremely important in the planning and operation o...
详细信息
ISBN:
(纸本)9781457703218
Power load forecasting is an important part of the power system planning, and accurate load forecasting can provide necessary basis data for the dispatcher, which is extremely important in the planning and operation of power system. neuralnetwork can approximate any nonlinear mapping with arbitrary precision, and its distributed information storage and processing structure have a certain fault tolerant. So neuralnetwork is suitable for complex system modeling, and it can be used as the main method to predict photovoltaic power operation state variables. This paper uses the neuralnetwork algorithm to establish photovoltaic power system's load forecast model, and except the generate historical data, meteorological forecast information is added to the algorithm, then the model is trained and tested, the high-precision prediction results can show the effectiveness of the algorithm.
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.
Currently, artificial intelligence technology is attracting much attention, and image processing field is also making remarkable progress in recognition rate through CNN models. Furthermore, Capsule network which is f...
详细信息
ISBN:
(纸本)9781728129464
Currently, artificial intelligence technology is attracting much attention, and image processing field is also making remarkable progress in recognition rate through CNN models. Furthermore, Capsule network which is flexible in changing pose of image is being studied in various fields by improving disadvantage of Pooling Layer of CNN model. We propose a method to accelerate the learning of CapsNet model, which is much slower than the existing neuralnetwork model. TensorFlow, Google's deep-running library, and the Apache Foundation's Hadoop framework are run through Python. We can confirm that the learning time is decreased in inverse proportion to the increase of the number of nodes in learning CapsNet according to the proposed method of distributedprocessing.
暂无评论