scispace - formally typeset
Search or ask a question

Is artificial neural networks easy to learn? 

Computer science
Artificial neural network
Mass transfer
Time delay neural network
Ultrafiltration

Answers from top 10 papers

More filters
Papers (10)Insight
Journal Article•DOI
Simulation of membrane separation by neural networks
Harri Niemi, Abhay B. Bulsari, Seppo Palosaari 
15 Jun 1995-Journal of Membrane Science
84 Citations
Neural networks offer the advantage of being easy to use.
Open access•Journal Article•DOI
Tuning the Parameters of a Convolutional Artificial Neural Network by Using Covering Arrays
Humberto Pérez-Espinosa, Himer Avila-George, Josefina Rodríguez-Jacobo, Hector A. Cruz-Mendoza, Juan Martínez-Miranda, Ismael Edrein Espinosa-Curiel 
31 Dec 2016-Research on computing science
12 Citations
Artificial Neural Networks have proven to be a very powerful machine learning algorithm which can be adequate to learn successfully a variety of tasks.
Proceedings Article•DOI
Identification of three phase induction motor incipient faults using neural network
A. Siddique, G.S. Yadava, Bhim Singh 
19 Sep 2004
13 Citations
The artificial neural network techniques are rather easy to develop and to perform.
Book Chapter•DOI
Counting With Artificial Neural Networks: An Experiment
Jaap Hoekstra
01 Jan 1992
7 Citations
For small numbers, artificial neural networks can be efficiently learned to count.
Journal Article•DOI
Neural Networks In Mining Sciences – General Overview And Some Representative Examples
Ryszard Tadeusiewicz
01 Dec 2015-Archives of Mining Sciences
48 Citations
This will be easy, because there are currently quite a few ready-made computer programs, easily available, which allow their user to quickly and effortlessly create artificial neural networks, run them, train and use in practice.
Journal Article•DOI
Neurofuzzy is useful aid in diagnosing acute appendicitis.
Mesut Tez, Selda Tez, Erdal Göçmen 
23 Apr 2008-World Journal of Surgery
7 Citations
Neural networks can learn (i. e., adapt) from data and feedback, but understanding the pattern learned by neural networks is difficult.
Open access•Journal Article•DOI
Use of neural network models in the market risk management
Mariya Radosteva, Vladimir Soloviev, Vera Ivanyuk, Anatoliy Tsvirkun 
23 Aug 2018-Advances in systems science and applications
27 Citations
Artificial neural networks can be most adequately characterised as «computational models» with particular properties such as the ability to adapt or learn, to generalise, or to cluster or organise data, and which operation is based on parallel processing.
Open access•Journal Article•DOI
Artificial Neural Networks Based Modeling and Control of Continuous Stirred Tank Reactor
R. Suja Mani Malar, T. Thyagarajan 
31 Mar 2009-American Journal of Engineering and Applied Sciences
13 Citations
Results indicated that neural networks can learn accurate models and give good nonlinear control when model equations are not known.
Journal Article•DOI
The use of artificial neural networks in construction management: a review
A. Halim Boussabaine
01 Sep 1996-Construction Management and Economics
149 Citations
Artificial neural networks (ANNs) are systems that can learn.
Journal Article•DOI
Effectiveness of artificial neural networks for first swing stability determination of practical systems
E. Hobson, G.N. Allen 
01 May 1994-IEEE Transactions on Power Systems
46 Citations
It is concluded that artificial neural networks have difficulty in returning consistently accurate answers under varying network conditions.

Related Questions

Why do people seemingly find it easy to believe in psychic phenomena?5 answersPeople seemingly find it easy to believe in psychic phenomena due to various factors. One factor is the influence of religious orientation, as individuals with different religious beliefs, including orthodox Christians, unorthodox religious believers, and the nonreligious, all showed a small positive correlation with overall psychic belief. Additionally, the presentation of fake psychic demonstrations can lead to an increase in psychic beliefs, even when participants have been warned about the deception. However, providing alternative explanations or disclosing the deceptive methods can mitigate this effect and reduce psychic beliefs. Furthermore, the mass media plays a significant role in shaping beliefs, as the plethora of presentations with psychic themes compensates for any orthodox religious teachings against the occult and emerges as the most salient influence on belief in psychic phenomena. Overall, a combination of religious orientation, exposure to fake demonstrations, and media influence contribute to the ease with which people believe in psychic phenomena.
Where was Easy zero knowledge learning mentioned?5 answersEasy zero knowledge learning was mentioned in the paper by Peikert and Shiehian.
Are information systems easy?7 answers
How do you create an artificial neural network?10 answers
How to start learning artificial neural network?10 answers
Is artificial neural network easy to learn?9 answers

See what other people are reading

What are the ontological underpinnings of qualitative research?
5 answers
Qualitative research is underpinned by various ontological perspectives. Researchers recognize that realities are multiple and subjective, and they aim to understand phenomena from the perspectives of participants. The ontological stance of qualitative research is in contrast to the positivist, quantitative approach that assumes an objective reality. The researcher's ontological stance influences every aspect of the research process, including the chosen methodology, methods, research questions, and prospective outcomes. Researchers engaging in qualitative studies online must closely examine and interrogate the digital tools, systems, and services they use to establish trustworthy epistemological claims. The philosophical assumptions underlying qualitative research are integral to the procedures and frameworks employed, such as phenomenology, which sets the stage for discussion and process illustration.How can AI help in the fight against cybercrime?
5 answers
AI can help in the fight against cybercrime by enabling more advanced and efficient threat detection and response. AI-powered systems can analyze vast amounts of data and identify patterns that would be difficult or impossible for a human to detect, allowing for real-time threat response. Additionally, AI can help organizations better manage and secure their networks and devices, as well as identify and mitigate vulnerabilities. AI-based solutions can provide effective and robust cyber defense capabilities, including identifying malware attacks, network intrusions, phishing and spam emails, and data breaches, and alerting security incidents when they occur. However, it is important to note that AI also presents new challenges in cybersecurity, as it can be used to enable more sophisticated forms of cyber-attacks.Concept of psychological test for counseling?
4 answers
Psychological tests are used in counseling to assess and understand the psychological state of individuals. These tests involve the use of various features such as data variance weighted information entropy, gradient direction features, and local contrast features. The complexity of the image is defined by combining these features, which allows for effective feature extraction and segmentation in psychological counseling. The choice of appropriate tests and the proper interpretation of test scores are crucial in counseling. Counselors need to have statistical and technical knowledge about tests, as well as substantive psychological knowledge about the behavior domain being assessed. Psychological assessment is considered a core competency in counseling, providing specific answers to various clinical, psychoeducational, occupational, forensic, and neuropsychological questions. Best practices in assessment include attention to diversity contexts, ethics, and standards.What are the most popular features of TikTok?
4 answers
TikTok's most popular features include the ability for content creators to use stylistic devices such as semantic and lexical parallelism to emphasize specific ideas and create humorous effects. Additionally, TikTok provides a platform for women to articulate their interpretation of their bodies, freeing themselves from gendered prescriptions and becoming the subject of their bodies. The app is particularly popular among young people, with teenagers being the main user demographic. TikTok is also known for its memetic videos, which often feature lip-syncing, dance routines, and comedic skits. Furthermore, TikTok has become a theatrical space where users can engage in performance-making, blurring the lines between live performance, theatricality, and digital culture.What's the meaning of adversarial examples in machine learning?
5 answers
Adversarial examples in machine learning refer to inputs that are intentionally modified by an attacker to cause a model to make incorrect predictions. These attacks can have serious consequences in applications such as autonomous vehicles, medical diagnosis, and security systems. Adversarial attacks exploit vulnerabilities in deep learning models, making it easy to create samples that manipulate the model's predictions. Transfer-based adversarial attacks involve generating adversarial examples using a substitute model and using them to attack an unseen target model. The output inconsistency problem can hinder the transferability of adversarial attacks between different types of deep neural network architectures. To address this, a common knowledge learning framework is proposed to improve the transferability of adversarial examples by distilling knowledge from different teacher architectures into one student network. Adversarial example threats are inputs that are maliciously modified to induce misclassification in machine learning classifiers. Identifying these threats at the architecture design stage is crucial for developing secure machine learning systems.What are the best ways to save money on food as a college student?
5 answers
The best ways to save money on food as a college student include optimizing the cost of meals through techniques like Linear Programming (LP) and Integer Linear Programming (ILP). Additionally, addressing food waste on college campuses can help reduce costs. Studies have shown that large quantities of food are wasted on college campuses, while simultaneously, many college students experience food insecurity. Targeted approaches, such as the use of smartphones, can be effective in addressing both food waste and food insecurity on college campuses. For example, the Campus Plate platform allows students to quickly discover and retrieve recoverable food, reducing waste and increasing food accessibility. By implementing these strategies, college students can save money on food while also contributing to a more sustainable food system.What are the key components of the WAMI index?
4 answers
The key components of the WAMI index are not mentioned in the provided abstracts.What are the shortcomings of the available intrusion detection systems in cloud computing?
5 answers
Intrusion detection systems (IDSs) in cloud computing have several shortcomings. The first challenge is the identification of complicated and anonymous attacks, which can be hindered by unwanted delays. Another issue is the ease of the cloud and the continual restructuring and movement of cloud resources, which pose challenges for intrusion detection. Additionally, the effectiveness and speed of detection are critical aspects that need improvement. To overcome these obstacles, machine learning techniques are suggested to be utilized in conjunction with parallelization. Statistical models, safe system approaches, neural networks, and other methods are used for intrusion detection, but accuracy needs improvement. Furthermore, cloud security features such as confidentiality, availability, and integrity are susceptible to attacks, making security solutions necessary. In summary, the shortcomings of available IDSs in cloud computing include delays in detection, challenges due to cloud dynamics, and the need for improved accuracy and speed of detection.How does the salinity of the Bay of Bengal change during the dry season?
5 answers
The salinity of the Bay of Bengal during the dry season is influenced by various factors. Positive salinity anomalies exceeding 2 psu are observed in the northern Bay of Bengal, while negative salinity anomalies are observed around Sri Lanka. The future changes in surface circulation and coastal nitrate pathways in the Bay of Bengal indicate that coastal nitrate transports decrease in the northern Bay and increase in the southwestern Bay during the dry season. The advent of satellite remotely-sensed Sea Surface Salinity (SSS) data has provided synoptic maps of the Bay of Bengal SSS, showing seasonal freshening along the east coast of India due to equatorward advection of low-salinity water by the East Indian Coastal Current (EICC). The presence of river runoff into the Bay of Bengal during the dry season strengthens the West India Coastal Current (WICC) and promotes the northward advection of warmer water, resulting in higher sea surface temperatures in the northeastern Arabian Sea. The high salinity core in the Bay of Bengal during the dry season originates primarily from the western equatorial Indian Ocean, reaching the Bay via the Somali Current, Equatorial Undercurrent, and Southwest Monsoon Current (SMC).How can deep learning be used for change detection in satellite data?
5 answers
Deep learning is a powerful approach for change detection in satellite data. It involves analyzing multi-temporal satellite images and using deep neural networks to automatically detect and classify changes. The process typically includes extracting features from the images using techniques like principle component analysis or convolutional neural networks. These features are then used to train models that can accurately identify changes in the data. Deep learning methods have been shown to be effective in this domain, with studies demonstrating their superiority over other technologies in terms of efficiency and accuracy. They can handle large volumes of data, perform feature extraction and classification tasks, and produce change maps with high accuracy. Overall, deep learning offers a promising solution for change detection in satellite data, enabling better analysis and understanding of urban areas and other applications.When oversample imbalanced data?
5 answers
Oversampling is a popular method used to construct balanced samples in imbalanced data classification. It is particularly useful when the proportion of classes is heavily skewed, leading to deteriorated classifier performance. Oversampling techniques aim to increase the number of instances in the minority class by generating synthetic examples. This helps to improve classification performance by providing more representative data for the minority class. Several studies have shown the effectiveness of oversampling strategies in addressing imbalanced datasets, achieving high-quality performance in terms of accuracy and minimizing false negatives.