Auto-encoder is a special kind of neural network based on reconstruction. De-noising auto-encoder (DAE) is an improved auto-encoder which is robust to the input by corrupting the original data first and then reconstructing the original input by minimizing the reconstruction error function. And contractive auto-encoder (CAE) is another kind of improved auto-encoder to learn robust feature by int...

Chinese characters have a huge set of character categories, more than 20,000 and the number is still increasing as more and more novel characters continue being created. However, the enormous characters can be decomposed into a compact set of about 500 fundamental and structural radicals. This paper introduces a novel radical analysis network (RAN) to recognize printed Chinese characters by ide...

In the field of robotics real-time image processing can provide the information necessary for mobile robots to execute a task in indoor environment. In this paper the application of a simple neural network-based system to translation and scale-invariant object recognition in the artificial vision structure of a mobile robot is proposed. The suggested bio-inspired vision system is mainly constit...

A superconducting radio-frequency (SRF) photo injector is in operation at the electron linac for beams with high brilliance and low emittance (ELBE) radiation center generates continuous wave (CW) average current brightness user since 2018. The speed of measurement SRF gun beamline can be increased by improving slit-scan system, thus time one phase space mapping shortened from about 15 minutes ...

Binarization plays a key role in the automatic information retrieval from document images. This process is usually performed in the first stages of documents analysis systems, and serves as a basis for subsequent steps. Hence it has to be robust in order to allow the full analysis workflow to be successful. Several methods for document image binarization have been proposed so far, most of which...

The proposed IAFC neural networks have both stability and plasticity because theyuse a control structure similar to that of the ART-1(Adaptive Resonance Theory) neural network.The unsupervised IAFC neural network is the unsupervised neural network which uses the fuzzyleaky learning rule. This fuzzy leaky learning rule controls the updating amounts by fuzzymembership values. The supervised IAFC ...

security term in mobile ad hoc networks has several aspects because of the special specification of these networks. in this paper a distributed architecture was proposed in which each node performed intrusion detection based on its own and its neighbors’ data. fuzzy-neural interface was used that is the composition of learning ability of neural network and fuzzy ratiocination of fuzzy system as...

This paper focuses on feed-forward neural network with attention-based encoder to solve the challenge of abstractive summarization. We also briefly explored the potential of attentive recurrent neural network and recurrent neural network encoder-decoder. Those models were originally proposed to solve similar tasks, such as news articles summarization and machine translation; we modify and exten...