SUCCESSIVE LEARNING IN HETERO-ASSOCIATIVE MEMORY USING CHAOTIC NEURAL NETWORKS

1999 ◽  
Vol 09 (04) ◽  
pp. 285-299 ◽  
Author(s):  
YUKO OSANA ◽  
MASAFUMI HAGIWARA
Keyword(s):  
Neural Networks ◽  
Input Data ◽  
Temporal Summation ◽  
Continuous Data ◽  
Learning Method ◽  
Associative Memories ◽  
Chaotic Neural Networks ◽  
Proposed Model ◽  
The Difference ◽  
Correct Data

In this paper, we propose a successive learning method in hetero-associative memories, such as Bidirectional Associative Memories and Multidirectional Associative Memories, using chaotic neural networks. It can distinguish unknown data from the stored known data and can learn the unknown data successively. The proposed model makes use of the difference in the response to the input data in order to distinguish unknown data from the stored known data. When input data is regarded as unknown data, it is memorized. Furthermore, the proposed model can estimate and learn correct data from noisy unknown data or incomplete unknown data by considering the temporal summation of the continuous data input. In addition, similarity to the physiological facts in the olfactory bulb of a rabbit found by Freeman are observed in the behavior of the proposed model. A series of computer simulations shows the effectiveness of the proposed model.

scholarly journals Capacity Visual Attention Networks

10.29007/lcmk ◽  
2018 ◽  
Author(s):  
Marcus Edel ◽  
Joscha Lausch
Keyword(s):  
Neural Networks ◽  
High Resolution ◽  
Machine Translation ◽  
Input Data ◽  
Counting Process ◽  
Model Output ◽  
Attention Networks ◽  
Attention Model ◽  
Proposed Model ◽  
Extract Information

Inspired by recent work in machine translation and object detection, we introduce an attention-based model that automatically learns to extract information from an image by adaptively assigning its capacity across different portions of the input data and only processing the selected regions of different sizes at high resolution. This is achieved by combining two modules: an attention sub-network which uses a mechanism to model a human-like counting process and a capacity sub-network. This sub-network efficiently identifies input regions for which the attention model output is most sensitive and to which we should devote more capacity and dynamically adapt the size of the region. We focus our evaluation on the Cluttered MNIST, SVHN, and Cluttered GTSRB image datasets. Our findings indicate that the proposed model is able to drastically reduce the number of computations, compared with traditional convolutional neural networks, while maintaining similar or better performance.

A Neural N-Gram Network for Text Classification

2018 ◽  
Vol 22 (3) ◽  
pp. 380-386 ◽  
Author(s):  
Zhenguo Yan ◽  
◽  
Yue Wu
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Text Classification ◽  
Word Order ◽  
Input Data ◽  
State Of The Art ◽  
Poor Performance ◽  
Proposed Model ◽  
Classification Tasks ◽  
N Gram

Convolutional Neural Networks (CNNs) effectively extract local features from input data. However, CNN based on word embedding and convolution layers displays poor performance in text classification tasks when compared with traditional baseline methods. We address this problem and propose a model named NNGN that simplifies the convolution layer in the CNN by replacing it with a pooling layer that extracts n-gram embedding in a simpler way and obtains document representations via linear computation. We implement two settings in our model to extract n-gram features. In the first setting, which we refer to as seq-NNGN, we consider word order within each n-gram. In the second setting, BoW-NNGN, we do not consider word order. We compare the performance of these settings in different classification tasks with those of other models. The experimental results show that our proposed model achieves better performance than state-of-the-art models.

Acquisition of Adaptive Behavior for the SMA-Net Robot Using Chaotic Neural Networks

2004 ◽  
Vol 16 (4) ◽  
pp. 411-419
Author(s):  
Ikuo Suzuki ◽  
◽  
Masaru Fujii ◽  
Keitaro Naruse ◽  
Hiroshi Yokoi ◽  
...  
Keyword(s):  
Neural Networks ◽  
Flexible Structure ◽  
Thermal Transition ◽  
Learning Method ◽  
Dynamic Learning ◽  
Chaotic Neural Networks ◽  
Heating And Cooling ◽  
Robot Behavior ◽  
Sma Spring ◽  
Rhythm Pattern

In this paper, we propose control for the SMA-Net Robot, a flexible structure consisting of many units and shape memory alloy (SMA) springs. To generate greater force for movement, more than one SMA spring is required. Since SMA springs are driven by thermal transition, controlling individual spring heating patterns is important in SMA-Net Robot behavior. It is a problem in controlling SMA spring that its detailed control is difficult because of the nonlinearity. We propose methodology that arranges heating and cooling as a rhythm pattern memorized by many chaotic neural networks (CNNs). To renew connecting weights in the network, we use the modified dynamic learning method (DLM) in online learning. The results of computational experiments showed that the SMA-Net Robot with the proposed control generates movement automatically.

scholarly journals KOHONEN NEURAL NETWORKS FOR RAINFALL-RUNOFF MODELING: CASE STUDY OF PIANCÓ RIVER BASIN

2013 ◽  
pp. 176-182 ◽  
Author(s):  
Camilo Allyson Simoes de Farias ◽  
Celso A. G. Santos ◽  
Artur M. G. Lourenço ◽  
Tatiane C. Carneiro
Keyword(s):  
Neural Networks ◽  
River Basin ◽  
Input Data ◽  
Missing Values ◽  
Rainfall Runoff ◽  
Data Set ◽  
Runoff Modeling ◽  
Proposed Model ◽  
Kohonen Neural Networks ◽  
Streamflow Data

The existence of long and reliable streamflow data records is essential to establishing strategies for the operation of water resources systems. In areas where streamflow data records are limited or present missing values, rainfall-runoff models are typically used for reconstruction and/or extension of river flow series. The main objective of this paper is to verify the application of Kohonen Neural Networks (KNN) for estimating streamflows in Piancó River. The Piancó River basin is located in the Brazilian semiarid region, an area devoid of hydrometeorological data and characterized by recurrent periods of water scarcity. The KNN are unsupervised neural networks that cluster data into groups according to their similarities. Such models are able to classify data vectors even when there are missing values in some of its components, a very common situation in rainfall-runoff modeling. Twenty two years of rainfall and streamflow monthly data were used in order to calibrate and test the proposed model. Statistical indexes were chose as criteria for evaluating the performance of the KNN model under four different scenarios of input data. The results show that the proposed model was able to provide reliable estimations even when there were missing values in the input data set.

A Structure Learning Method for Block-Based Neural Networks

2013 ◽  
Vol 133 (10) ◽  
pp. 1976-1982 ◽  
Author(s):  
Hidetaka Watanabe ◽  
Seiichi Koakutsu ◽  
Takashi Okamoto ◽  
Hironori Hirata
Keyword(s):  
Neural Networks ◽  
Structure Learning ◽  
Learning Method ◽  
Block Based
Sign in / Sign up

Export Citation Format

Share Document