scispace - formally typeset
Search or ask a question

Answers from top 10 papers

More filters
Papers (10)Insight
This paper shows that a new type of artificial neural network (ANN) -- the Simultaneous Recurrent Network (SRN) -- can, if properly trained, solve a difficult function approximation problem which conventional ANNs -- either feedforward or Hebbian -- cannot.
These building blocks can be applied to artificial neural network (ANN) design in particular and to analog signal processing in general.<>
An artificial neural network, a biologically inspired computing method which has an ability to learn, self-adjust, and be trained, provides a powerful tool in solving complex problems.
In such event, artificial neural network (ANN) model can be a potential alternative to the conventional models.
Artificial neural network (ANN) resembles brain biological neural network and can be used to simulate chaotic system.
Artificial neural network, a biologically inspired computing method which has an ability to learn, self-adjust, and be trained, provides a powerful tool in solving pattern recognition problems.
Artificial neural network (ANN) is another promising alternative with the unique capability of nonlinear self-adaptive modeling.
Journal ArticleDOI
S. P. Trasatti, F. Mazza 
20 Citations
Among these, the artificial neural network (NN) system appears to be a powerful tool to tackle situations in w...
This kind of network combines or better fuses the advantages of backpropagation artificial neural algorithm and Hu moment.
Proceedings ArticleDOI
T. Baker, Dan Hammerstrom 
08 May 1989
26 Citations
One popular artificial neural network model, the back-propagation algorithm, promises to be a powerful and flexible learning model.

Related Questions

What is human-in-the-loop ai?5 answersHuman-in-the-loop AI refers to an approach in which humans are actively involved in the AI development process, particularly in the design, training, and evaluation stages. This involvement of humans helps in identifying unproductive layers of the AI architecture, leading to the creation of lightweight AI architectures suitable for embedded applications. By enabling human-machine interaction (HMI) during AI inference, the AI-in-the-loop concept combines the strengths of AI and humans. In this approach, the AI primarily solves the task but can seek human assistance through appropriate HMI when unsure about the correctness of its inference. The use of HMI during AI development reduces the resources needed and makes AI more reliable and explainable. Additionally, the concept of human-in-the-loop is also applied in novelty generation, where humans provide guidance in selecting and filtering novelties generated by abstract models of environments.
What are ctcf mediated loops?3 answersCTCF-mediated loops are chromatin loops that are formed and regulated by the CCCTC-binding factor (CTCF) protein. CTCF is a transcription regulator involved in various cellular processes and plays a crucial role in three-dimensional (3D) genome organization. These loops are formed when CTCF binds to specific DNA sequences called CTCF binding sites (CBSs) and acts as an anchor for the cohesin protein complex. The cohesin complex extrudes DNA loops that are anchored by CTCF in a polar orientation. The orientation of CTCF binding polarity controls cohesin-mediated DNA looping, and the presence of CTCF motifs and sequence conservation are important indicators of chromatin loops. CTCF-mediated loops have been found to be involved in gene regulation, cell development, disease progression, and the spatial organization of the genome.
What is the phenomenon of human-in-the-loop training of neural network?5 answersHuman-in-the-loop training of neural networks refers to a training approach that involves the active participation of humans in the training process. In this approach, humans provide feedback or guidance to the neural network during the training phase, which helps improve the performance and interpretability of the model. The feedback can be in the form of labeled data, annotations, or evaluations of the model's output. By incorporating human feedback, the neural network can learn from the expertise and knowledge of humans, leading to better results. This approach has been applied in various domains such as music generation, polyp detection in colonoscopy, synthetic aperture radar target recognition, and feature aggregation in machine learning.
How do I make a loop run multiple regression models in Python?6 answers
How to create a loop to run multiple regression models SAS?5 answers
How to use artificial neural network?10 answers

See what other people are reading

What are the recent studies on nanofiber from 2020 to 2023?
5 answers
Recent studies on nanofibers from 2020 to 2023 have focused on various applications and advancements in the field. One study demonstrated the growth of carbon nanofibers on a nickel foam as a binder-free electrode for electrochemical advanced oxidation processes, which showed excellent reduction rates of O2 to H2O2. Another study explored the use of an aromatic polyimide-based nanofiber membrane separator for lithium-ion batteries, which exhibited enhanced charge and discharge performance and high ion conductivity. Additionally, a study presented a multifunctional micro/nanofiber-based dressing patch for advanced wound care, which enabled rapid wound healing, protection against external microbial, and wound status monitoring. Furthermore, research focused on drug-grafted polymers, where polylactic acid-dicumarol conjugates were electrospun into nanofiber membranes for peritendinous adhesion prevention. Lastly, studies explored the fabrication and application of biomedical nanofiber hydrogels for sustained drug delivery, with a focus on self-gelling nanofiber systems made from peptides or other natural proteins.
What is Machine learning?
5 answers
Machine learning is a branch of artificial intelligence that involves teaching computers to learn from examples, data, and experience without being explicitly programmed. It uses algorithms to enable computers to evolve behaviors based on empirical data. Machine learning is closely related to other fields such as statistics, computer science, and artificial intelligence. It has been successfully applied in various fields including pattern recognition, computer vision, finance, and biomedical and medical applications. Machine learning algorithms have the potential to optimize and automate complex processes, improve decision-making, and enhance outcomes in fields such as radiotherapy. Machine learning addresses problems where there are no human experts, problems where human experts are unable to explain their expertise, problems with rapidly changing phenomena, and applications that need to be customized for individual users.
Why rock surface has less water content?
3 answers
Rock surfaces have less water content due to various factors. One reason is that water content and porosity have a weak influence or relationship with the compressive strength of rocks. Additionally, the physical and chemical properties of minerals can be dramatically changed by the incorporation of water, which can reduce the strength of minerals. Furthermore, the near-surface water balance in mine-affected landscapes plays a key role in re-vegetation performance, and increased vegetation cover can result in a greater volume of water removed from the near-surface through evapotranspiration. Moreover, water desaturation processes in water-saturated rock can occur when the evaporative water loss at the rock surface is larger than the water flow from the surrounding saturated region, leading to a decrease in water content. Finally, rock moisture levels on different aspects of rock outcrops can vary, with the southern aspect usually having lower rock moisture levels due to dominant rain-bearing winds and snow accumulation on the northern aspect.
How to prevent cold spray processes from clogging?
4 answers
To prevent clogging in cold spray processes, several methods can be employed. One approach is to use a larger standoff distance during the spraying process, which allows for easier maneuverability of the spray gun. Another method involves cooling the raw powder supply flow path to prevent clogging of the raw powder supply port. Additionally, using a two-particle material supply system can help mitigate blockage of the nozzle by the second particle material. Computational fluid dynamics techniques can be used to identify the factors causing nozzle clogging, such as particle dispersion and high-temperature nozzle walls, and to develop cooling devices to prevent clogging. Furthermore, the design of the nozzle itself can incorporate a cooling jacket to prevent clogging and ensure smooth flow of the refrigerant.
What is the overview of hydrate formation?
5 answers
Hydrate formation is a process of concern in various industries, including oil and gas production systems. It occurs when gas phases interact with water molecules under specific conditions of low temperatures or high pressures. The formation of hydrates poses risks to process safety as it can lead to the plugging of pipes and instruments. Understanding the thermodynamic and kinetic aspects of hydrate formation is crucial for developing effective prevention and mitigation strategies. Porous media systems play a significant role in hydrate formation and can enhance the kinetics of hydrate formation. Promoters are often used to facilitate rapid hydrate formation. Fundamental properties and theories related to hydrate nucleation and growth have been extensively studied. Mathematical models have been developed to determine the thermobaric parameters and characteristics of hydrate formation processes. Overall, a comprehensive understanding of hydrate formation is essential for various applications and future research endeavors.
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.