scispace - formally typeset
Search or ask a question

Answers from top 10 papers

More filters
Papers (10)Insight
Proceedings ArticleDOI
Mario Köppen, M. Teunis, Bertram Nickolay 
13 Apr 1997
14 Citations
Nessy algorithm can be characterized as an individual evolutionary algorithm, but as a neural network too.
Artificial neural network is proved to be an effective algorithm for dealing with recognition, regression and classification tasks.
It was found that artificial neural network (ANN) techniques, in general, provide better classification as compared to the pattern recognition techniques we applied earlier (M. S.
Our experiments indicate that a genetic-algorithm-based artificial neural network that maximizes the total number of correct classifications generally fares well for the binary classification problem.
Artificial neural networks, however, are able to handle classification tasks and show positive results.
The artificial neural network is an effective classification method for solving feature extraction problems.
This study shows that the artificial neural network increases the classification performance using genetic algorithm.
Neural network technique is an effective classification and prediction method.
Artificial neural network is a versatile modelling tool capable of making predictions of values that are difficult to obtain in numerical analysis.
The artificial neural network (ANN) is a computational method based on human brain function and is efficient in recognizing previously trained patterns.

Related Questions

Document classification on neural networks using only positive examples.4 answersDocument classification using neural networks with only positive examples has been explored in several papers. Larry M. Manevitz and Malik Yousef have shown in their papers that a simple feedforward neural network can be trained to filter documents when only positive information is available. They have found that this method is superior to more standard methods such as tf-idf retrieval based on an "average vector". J. Farkas discusses the relevance of neural networks in classifying electronic natural language documents and shows that neural networks can be taught to classify text according to predefined specifications. Rastislav Lencses presents an enriched approach to document clustering using neural networks and distributional semantics.
AM classification in foudary application?3 answersApplication classification in the context of foudary applications is addressed in several papers. One paper proposes an automatic application classification method based on acquiring protocol-related information of network communication protocols used by multiple applications. The applications are then clustered based on this information, allowing for the analysis of malicious applications with similar protocol-related information. Another paper presents a method that utilizes application descriptions and performs word segmentation to obtain keywords for classification. The applications are then classified based on these keywords, achieving unified re-classification. Additionally, a paper proposes a second order-based anomaly detection method to predict and describe application incidents based on monitored server traffic metrics. Another paper introduces a method for convenient and automatic terminal equipment application classification based on application characteristic information and predefined classification information. Finally, a system is described that uses tags associated with known sets of traffic types to mark traffic flows based on matching sets of traffic types.
What is classification in machine vision?2 answersClassification in machine vision refers to the process of categorizing or labeling objects or regions of interest in images or videos based on their visual characteristics. It involves training machine learning algorithms to recognize and differentiate between different classes or categories of objects or features within an image. For example, in the context of agriculture, machine vision algorithms have been developed to classify and segment raw sugarcane billets based on their quality. Similarly, in the field of autonomous transportation, machine vision algorithms have been used to classify road surface types such as asphalt, gravel, and pavement. In the context of intelligent vehicles, machine vision algorithms have been employed to accurately identify and classify different road categories, such as asphalt road, brick road, dirt road, and gravel road. In the domain of fruit classification, machine vision algorithms have been utilized to extract and classify different kinds of apple defects, such as decay and bruise. Furthermore, in the field of scanning probe microscopy, machine vision algorithms have been applied to analyze and identify complex chiral patterns in SPM images.
How can artificial intelligence be used to classify animals?5 answersArtificial intelligence can be used to classify animals in various ways. One approach is using AI algorithms to analyze camera trap images and discriminate individual animals carrying tags. Another method involves developing deep neural network algorithms that utilize accelerometry data to classify animal behavior. Additionally, deep learning computer vision models can be trained to automatically detect, count, and classify different species in camera trap images. These models can provide accurate predictions and facilitate the application of AI in wildlife monitoring. By implementing these AI techniques, researchers and practitioners can efficiently classify animals, monitor their behavior, and analyze large datasets from camera traps.
What are the different types of machine learning algorithms?5 answersMachine learning algorithms can be classified into various types. These include supervised, unsupervised, semi-supervised, and reinforcement learning. Additionally, deep learning is a subset of machine learning that can analyze data on a large scale. Some commonly used machine learning algorithms are the Naïve Bayes classifier, support vector machine, neural network, and decision tree. These algorithms are used for tasks such as data classification, prediction, pattern recognition, data mining, and image processing. The main advantage of using machine learning is that once an algorithm learns from data, it can perform tasks autonomously.
Is artificial neural network supervised learning?9 answers

See what other people are reading

How the networks work?
5 answers
Networks work by utilizing infrastructure and intangible assets to achieve their goals. In the case of epilepsy care during the COVID-19 pandemic, a multi-stakeholder epilepsy Learning Network used a transparent and mundane shared infrastructure to shape their response to the changes in care. Fully-connected feedforward neural networks (FCNNs) or multi-layer perceptrons (MLPs) exhibit properties that can be explained by a pair of operations: random projection into a higher-dimensional space and sparsification. The value of networks is primarily based on intangible assets such as employee skills and IT infrastructure, and a framework consisting of success factors, results, reference measures, and failure factors can be used to assess and utilize these assets. Understanding networking concepts can be achieved through resources that provide a solid introduction and assume no prior knowledge.
Islanding using wavelet transform
5 answers
Islanding detection using wavelet transform is a commonly used method in distributed generation (DG) systems. Several papers propose different approaches to detect islanding using wavelet transform combined with machine learning techniques. Spötl and Yilmaz & Bayrak present methods that use wavelet transform and artificial neural networks (ANN) for islanding detection. Another paper by Ajith & Shereef proposes a method that uses wavelet transform decomposition and K-Nearest Neighbor (KNN) classification for islanding detection. These methods aim to reduce the non-detection zone (NDZ) and improve the detection time for islanding events. The use of wavelet transform allows for the extraction of detailed coefficients that can capture transient variations during islanding. By combining wavelet transform with machine learning techniques, these methods provide effective islanding detection in DG systems.
What is hidden layer in artificial neural network?
5 answers
The hidden layer in an artificial neural network refers to a layer of neurons that are not directly connected to the input or output layers. It is an intermediate layer that processes the input data and extracts relevant features before passing them on to the output layer. The purpose of the hidden layer is to enable the network to learn complex patterns and improve the performance of the network. The number of hidden layers and the number of neurons in each hidden layer are important factors in determining the architecture of the neural network. Different research papers propose various methods to determine the optimal number of hidden layers and neurons, such as interconnecting the hidden neurons within the same layer, using deep learning architecture with multiple feedforward layers, or removing unnecessary hidden neurons to enhance performance.
What are the best practices for improving the performance of a chatbot?
5 answers
The best practices for improving the performance of a chatbot include the following: (1) Predicting whether the best response should be a question and retrieving responses accordingly. (2) Incorporating a Neural Machine Translation (NMT) engine and a search-based engine to enhance the chatbot's performance in language learning. (3) Using deep learning techniques, such as convolutional neural networks, to improve the accuracy of chatbots. (4) Expanding the knowledge database of the chatbot through social media platforms like Twitter to provide accurate and flexible answers. These practices have been shown to significantly improve the retrieval performance, enhance language learning, increase accuracy, and provide appropriate answers in terms of context.
How does digital self-extension influence the way people comment on online content?
5 answers
Digital self-extension, the concept of extending one's self to digital possessions, has been explored in the context of consumer behavior. However, there is limited research on how digital self-extension influences the way people comment on online content. The use of digital technologies has brought changes to the extended self, challenging traditional notions of self and the relationship between objects and consumers in digital environments. Understanding the implications of self-extension to digital possessions can provide insights into maintaining digital possessions for the long term. Additionally, the affordances of digital technologies may influence behavior and potentially impact the actions associated with saving or personal information for the long term. Further research is needed to explore the specific influence of digital self-extension on online commenting behavior.
How to improve the accuracy of chord suggestion with deep learning?
4 answers
To improve the accuracy of chord suggestion with deep learning, several approaches have been proposed in the literature. One method is to use contrastive learning, where the model is trained with a combination of labeled and unlabeled data, and contrast loss is applied to generate a more uniform representation of features. Another approach is to incorporate Long Short-Term Memory (LSTM) networks, which consider chord information from previous time steps, into the chord recognition system. Additionally, personalizing chord labels based on annotator subjectivity has been shown to improve the performance of automatic chord estimation systems. Finally, a compact neural network called FifthNet has been proposed, which exploits the known structure of music spectra to achieve accurate chord recognition with fewer parameters and computational expense.
Artificial intelligence on food baking proceess?
3 answers
Artificial intelligence (AI) has been applied to various aspects of the food baking process. One study developed an intelligent baking device and method based on in-depth learning, which generated baking curves and controlled mechanical motion for baking different food materials. Another study proposed an intelligent food baking oven that addressed issues such as uneven baking, poor baking effect, and manual washing difficulties. The oven incorporated features like heating and rotating devices, as well as a cleaning device. Additionally, AI has been used to analyze newspaper articles and predict the taste of words, leading to the development of a chocolate that represents the mood of each year. Furthermore, an AI-based approach has been proposed to support decision-making in food chains, including the wheat to bread chain, by formalizing knowledge and addressing conflicting priorities. These studies demonstrate the potential of AI in improving the food baking process.
What is the purpose of a chaotic system in cryptography?
4 answers
A chaotic system is used in cryptography to ensure confidentiality and create secure encryption algorithms. Chaotic systems exhibit nonlinearity and a high degree of randomness, making them effective in cryptography. These systems are based on the principles of chaos theory, which states that complex systems often produce unpredictable results. By utilizing chaotic behavior, encryption keys can be generated that are difficult to reverse engineer, making it extremely challenging to crack the code. Chaotic systems can also be used for time series forecasting, which can be applied in cryptographic applications to produce encryption keys. Additionally, chaotic systems can be used to create image encryption algorithms, resulting in cipher-images with high entropy values and low correlation between adjacent pixels. Overall, chaotic systems provide a foundation for creating secure and effective cryptographic techniques.
Why AI to predict CVD why not relying on doctor diagnosis?
5 answers
AI is being used to predict cardiovascular disease (CVD) because it can improve the diagnosis process and overcome limitations of relying solely on doctor diagnosis. AI methods, such as machine learning, can analyze large amounts of data and identify patterns that may not be easily detectable by human doctors. Ultrasound imaging, for example, can be enhanced and automated using machine learning algorithms to segment arterial walls and improve the accuracy of CVD diagnosis. Additionally, AI can provide a more objective and consistent approach to diagnosis, reducing the potential for human error. It is important to note that AI is not meant to replace doctors, but rather to assist them in making more accurate and efficient diagnoses. By combining the expertise of doctors with the analytical capabilities of AI, the diagnosis of CVD can be improved, leading to better patient outcomes.
What is the fastest way to learn a language?
5 answers
The fastest way to learn a language is through a fast language learning method and system that collects character string information input by a user and outputs multiple information layers corresponding to the input method tool. This method allows for faster language learning by utilizing knowledge learning techniques and improving learning efficiency. Additionally, a fast memory method for language learning based on an automatic cycle screening system of a computer can also be used. This method follows an optimal language learning mode theory and involves issuing detection questions, verifying language information input by the user, and deleting language units that are answered correctly. By deleting memorized language units, excessive learning is avoided, learning efficiency is improved, and learning time is saved.
Document classification on neural networks using only positive examples.
4 answers
Document classification using neural networks with only positive examples has been explored in several papers. Larry M. Manevitz and Malik Yousef have shown in their papers that a simple feedforward neural network can be trained to filter documents when only positive information is available. They have found that this method is superior to more standard methods such as tf-idf retrieval based on an "average vector". J. Farkas discusses the relevance of neural networks in classifying electronic natural language documents and shows that neural networks can be taught to classify text according to predefined specifications. Rastislav Lencses presents an enriched approach to document clustering using neural networks and distributional semantics.