The ability to store and retrieve information is critical in any type of neural network. In neural network, the memory particularly associative memory, can be defined as the one in which the input pattern leads to the...
详细信息
ISBN:
(纸本)9789728865863
The ability to store and retrieve information is critical in any type of neural network. In neural network, the memory particularly associative memory, can be defined as the one in which the input pattern leads to the response of a stored pattern (output vector) that corresponds to the input vector. During the learning phase the memory is fed with a number of input vectors that it learns and remembers and in the recall phase when some known input is presented to it, the network exactly recalls and reproduces the required output vector. In this paper, we improve and increase the storing ability of the memory model proposed in[1]. Besides, we show that there are certain instances where the algorithm in[1] does not produce the desired performance by retrieving exactly the correct vector from the memory. That is, in their algorithm, a number of output vectors can become activated from the stimulus of an input vector while the desired output is just a single correct vector. We propose a simple solution that overcomes this and can uniquely and correctly determine the output vector stored in the associative memory when an input vector is applied. Thus we provide a more general scenario of this neural network memory model consisting of memory element called Competitive Cooperative Neuron (CCN).
in semiconductor manufacturing, the spatial pattern of failed devices in a wafer can give precious hints on which step of the process is responsible for the failures. In the literature, Kohonen39;s Self Organizing F...
详细信息
in semiconductor manufacturing, the spatial pattern of failed devices in a wafer can give precious hints on which step of the process is responsible for the failures. In the literature, Kohonen's Self Organizing Feature Maps (SOM) and Adaptive Resonance Theory 1 (ART1) architectures have been compared, concluding that the latter are to be preferred. However, both the simulated and the real data sets used for validation and comparison were very limited. In this paper, the use of ART1 and SOM as wafer classifiers is re-assessed on much more extensive simulated and real data sets. We conclude that ART1 is not adequate, whereas SOM provide completely satisfactory results including visually effective representation of spatial failure probability of the pattern classes. (c) 2005 Elsevier B.V. All rights reserved.
The proceedings contain 16 papers. The special focus in this conference is on Computer Vision for Analysis of Underwater Imagery. The topics include: Categorization of Document Image Tampering Techniques and How to Id...
ISBN:
(纸本)9783030057916
The proceedings contain 16 papers. The special focus in this conference is on Computer Vision for Analysis of Underwater Imagery. The topics include: Categorization of Document Image Tampering Techniques and How to Identify Them;overview of the Multimedia Information Processing for Personality & Social networks Analysis Contest;handwritten Texts for Personality Identification Using Convolutional neuralnetworks;recognition of Apparent Personality Traits from Text and Handwritten Images;multimodal Database of Emotional Speech, Video and Gestures;from Text to Speech: A Multimodal Cross-Domain Approach for Deception Detection;marine Snow Removal Using a Fully Convolutional 3D neural Network Combined with an Adaptive Median Filter;strategies for Tackling the Class Imbalance Problem in Marine Image Classification;an Online Platform for Underwater Image Quality Evaluation;tracking Sponge Size and Behaviour with Fixed Underwater Observatories;enhancement of Low-Lighting Underwater Images Using Dark Channel Prior and Fast Guided Filters;Underwater-GAN: Underwater Image Restoration via Conditional Generative Adversarial Network;single Image Plankton 3D Reconstruction from Extended Depth of Field Shadowgraph;a Novel Method for Race Determination of Human Skulls.
Noisy or adverse input is a threat to the safe deployment of neuralnetworks in production. To ensure the safe operations of such networks they need to be hardened to work under such conditions. Abstract interpretatio...
详细信息
This paper presents a combined method of content-based retrieval and classification of ultrasound medical images representing three types of ovarian cysts: Simple Cyst, Endometrioma, and Teratoma. Combination of histo...
详细信息
ISBN:
(纸本)9783642121586
This paper presents a combined method of content-based retrieval and classification of ultrasound medical images representing three types of ovarian cysts: Simple Cyst, Endometrioma, and Teratoma. Combination of histogram moments and Gray Level Co-Occurrence Matrix (GLCM) based statistical texture descriptors has been proposed as the features for retrieving and classifying ultrasound images. To retrieve images, relevance between the query image and the target images has been measured using a similarity model based on Gower's similarity coefficient. Image classification has been performed applying Fuzzy k-Nearest Neighbour (k-NN) classification technique. A database of 478 ultrasound ovarian images has been used to verify the retrieval and classification accuracy of the proposed system. In retrieving ultrasound images, the proposed method has demonstrated above 79% and 75% of average precision considering the first 20 and 40 retrieved images respectively. Further, 88.12% of average classification accuracy has been achieved in classifying ultrasound images using the proposed method.
In recent years, deep neuralnetworks have reached state of the art performance across many different domains. Computer vision in particular has benefited immensely from deep learning. Despite their high performance, ...
详细信息
Video prediction is a complicated task as countless possible future frames exist that are equally plausible. While recent work have made progress in the prediction and generation of future video frames, these work hav...
详细信息
ISBN:
(数字)9781665490627
ISBN:
(纸本)9781665490627
Video prediction is a complicated task as countless possible future frames exist that are equally plausible. While recent work have made progress in the prediction and generation of future video frames, these work have not attempted to disentangle different features of videos such as an object's structure and its dynamics. Such a disentanglement would allow one to control these aspects to some extent in the prediction phase, while at the same time maintain the object's intrinsic properties that are learned as the model's internal representation. In this work, we propose Ladder Variational Recurrent neuralnetworks (LVRNN). We employ a type of ladder autoencoder shown to be effective for feature disentanglement on images and apply it to the Variational Recurrent neural Network (VRNN) architecture, which has been used for video prediction. We rely on extracted keypoints in each frame to separate the structure from the visual features. We then show how different levels of the ladder network learn to disentangle features and demonstrate that each of these levels can be used for controlling different aspects of future frames such as structure and dynamics. We evaluate our method on the Human3.6M and BAIR robot datasets. We show that our method is able to perform hierarchical disentanglement, yet provide reasonable results compared to similar methods.
The proceedings contain 13 papers. The special focus in this conference is on Multimodal patternrecognition of Social Signals in Human-Computer-Interaction. The topics include: Bimodal recognition of Cognitive Load B...
ISBN:
(纸本)9783319592589
The proceedings contain 13 papers. The special focus in this conference is on Multimodal patternrecognition of Social Signals in Human-Computer-Interaction. The topics include: Bimodal recognition of Cognitive Load Based on Speech and Physiological Changes;Human Mobility-pattern Discovery and Next-Place Prediction from GPS Data;Fusion Architectures for Multimodal Cognitive Load recognition;Performance Analysis of Gesture recognition Classifiers for Building a Human Robot Interface;On Automatic Question Answering Using Efficient Primal-Dual Models;Hierarchical Bayesian Multiple Kernel Learning Based Feature Fusion for Action recognition;Audio Visual Speech recognition Using Deep Recurrent neuralnetworks;Audio-Visual recognition of Pain Intensity;The SenseEmotion Database: A Multimodal Database for the Development and Systematic Validation of an Automatic Painand Emotion-recognition System;Photometric Stereo for 3D Face Reconstruction Using Non Linear Illumination Models and Recursively Measured Action Units.
In living beings, any patternrecognition task involves complex processes of concepts formation. We propose a model based on the principle of neural assemblies to develop internal representations of characters. neural...
详细信息
Computational models of visual processing often use framebased image acquisition techniques to process a temporally changing stimulus. This approach is unlike biological mechanisms that are spikebased and independent ...
详细信息
暂无评论