Evaluating neural networks and artificial intelligence systems

1994 ◽  
Author(s):  
David S. Alberts
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Artificial Intelligence Systems

scholarly journals Emotion Detection using Facial Expressions with Convolution Neural Networks

2019 ◽  
Vol 8 (2S11) ◽  
pp. 3612-3615
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Facial Expressions ◽  
Health Monitoring ◽  
Human Condition ◽  
Emotion Detection ◽  
Human Environment ◽  
Interaction Field ◽  
Research Theme ◽  
Artificial Intelligence Systems

Artificial intelligence systems to perceive human feeling have pulled in much research premium, and potential uses of such frameworks flourish, spreading over areas, for example, client mindful showcasing, health monitoring wellbeing observing, and genuinely shrewd robotic interfaces. Human are enthusiastic creatures and it assumes a significant job behind their thoughts and activity. In this way, it is important that emotion handling capacities are assimilated for planning of human condition. The investigation, recognition and synthesis of feelings can plan the human environment. In this procedure the data uses, for example, sound, visual, composed and mental data. An epic research theme to be developed in the Human Computer Interaction field is Emotion Recognition utilizing Facial Expressions.

Artificial Intellect with Artificial Neural Networks

2021 ◽  
pp. 44-52
Author(s):  
В.М. Еськов ◽  
М.А. Филатов ◽  
Г.В. Газя ◽  
Н.Ф. Стратан
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Statistical Methods ◽  
Order Parameters ◽  
System Synthesis ◽  
New Information ◽  
Artificial Neural ◽  
Definition Of ◽  
Artificial Intelligence Systems

В настоящее время не существует единого определения искусственного интеллекта. Требуется такая классификация задач, которые должны решать системы искусственного интеллекта. В сообщении дана классификация задач при использовании искусственных нейросетей (в виде получения субъективно и объективно новой информации). Показаны преимущества таких нейросетей (неалгоритмизируемые задачи) и показан класс систем (третьего типа — биосистем), которые принципиально не могут изучаться в рамках статистики (и всей науки). Для изучения таких биосистем (с уникальными выборками) предлагается использовать искусственные нейросети, которые решают задачи системного синтеза (отыскание параметров порядка). Сейчас такие задачи решает человек в режиме эвристики, что не моделируется современными системами искусственного интеллекта. Currently, there is no single definition of artificial intelligence. We need a Such categorization of tasks to be solved by artificial intelligence. The paper proposes a task categorization for artificial neural networks (in terms of obtaining subjectively and objectively new information). The advantages of such neural networks (non-algorithmizable problems) are shown, and a class of systems (third type biosystems) which cannot be studied by statistical methods (and all science) is presented. To study such biosystems (with unique samples) it is suggested to use artificial neural networks able to perform system synthesis (search for order parameters). Nowadays such problems are solved by humans through heuristics, and this process cannot be modeled by the existing artificial intelligence systems.

The architecture challenge: Future artificial-intelligence systems will require sophisticated architectures, and knowledge of the brain might guide their construction

2017 ◽  
Vol 40 ◽  
Author(s):  
Gianluca Baldassarre ◽  
Vieri Giuliano Santucci ◽  
Emilio Cartoni ◽  
Daniele Caligiore
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Human Cognition ◽  
Important Means ◽  
The Brain ◽  
Artificial Intelligence Systems

AbstractIn this commentary, we highlight a crucial challenge posed by the proposal of Lake et al. to introduce key elements of human cognition into deep neural networks and future artificial-intelligence systems: the need to design effective sophisticated architectures. We propose that looking at the brain is an important means of facing this great challenge.

scholarly journals Exploiting Artificial Neural Networks Machine Learning Errors for Attacks on AI Systems

2021 ◽  
pp. 23-32
Author(s):  
Т. В. Гавриленко ◽  
А. В. Гавриленко
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Artificial Neural ◽  
Current Paradigm ◽  
Artificial Intelligence Systems

В статье приведен обзор различных методов атак и подходов к атакам на системы искусственного интеллекта, построенных на основе искусственных нейронных сетей. Показано, что начиная с 2015 года исследователи в различных странах активно развивают методы атак и подходы к атакам на искусственные нейронные сети, при этом разработанные методы и подходы могут иметь критические последствия при эксплуатации систем искусственного интеллекта. Делается вывод о необходимости развития методологической и теоретической базы искусственных нейронных сетей и невозможности создания доверительных систем искусственного интеллекта в текущей парадигме. The paper provides an overview of methods and approaches to attacks on neural network-based artificial intelligence systems. It is shown that since 2015, global researchers have been intensively developing methods and approaches for attacks on artificial neural networks, while the existing ones may have critical consequences for artificial intelligence systems operations. We come to the conclusion that theory and methodology for artificial neural networks is to be elaborated, since trusted artificial intelligence systems cannot be created in the framework of the current paradigm.

scholarly journals Back Propagation and Transformation Methods in Artificial Intelligence Systems

2006 ◽  
Vol 1 ◽  
pp. 367
Author(s):  
G. Moskvin
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Back Propagation ◽  
Automatic Measuring ◽  
A Priority ◽  
Transformation Methods ◽  
First Time ◽  
And Training ◽  
Artificial Intelligence Systems

Detailed description of methods of back propagation and back transformation also distributions for training of neural networks is given. A comparative estimation of a priority of methods of back transformation and back propagation for the decision of tasks of synthesis and training of neural networks, also for intelligent automatic measuring and AI systems for the first time is carried out.

An Overview of Applications of Artificial Intelligence Using Different Techniques, Algorithms, and Tools

2021 ◽  
pp. 325-347
Author(s):  
Yadira Quiñonez
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Learning Automata ◽  
Critical Discussion ◽  
Response Threshold ◽  
Threshold Models ◽  
Application Area ◽  
Stochastic Learning ◽  
General Society ◽  
Artificial Intelligence Systems

Technology is currently a crucial benchmark in any application area. In general, society is immersed in the era of digitalization; therefore, incorporating digital technology in different application areas has been more accessible. Nowadays, claiming that adopting artificial intelligence systems in any area is already an emerging need. In this chapter, several artificial intelligence techniques are presented, as well as algorithms and tools that have been used to provide a variety of solutions such as artificial neural networks, convolutional neural networks architecture, AI models, machine learning, deep learning, and bio-inspired algorithms focused mainly on ant colony optimization, response threshold models, and stochastic learning automata. Likewise, the main applications that use AI techniques are described, and the main trends in this discipline are mentioned. This chapter ends with a critical discussion of artificial intelligence advances.

scholarly journals Prospects for the use of artificial neural networks for problem solving in clinical transplantation

2021 ◽  
Vol 23 (2) ◽  
pp. 177-182
Author(s):  
R. M. Kurabekova ◽  
A. A. Belchenkov ◽  
O. P. Shevchenko
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Neural Networks ◽  
Big Data ◽  
Information Technologies ◽  
Learning Technologies ◽  
Human Intelligence ◽  
Solid Organ ◽  
Clinical Transplantation ◽  
Artificial Intelligence Systems

Management of solid organ recipients requires a significant amount of research and observation throughout the recipient’s life. This is associated with accumulation of large amounts of information that requires structuring and subsequent analysis. Information technologies such as machine learning, neural networks and other artificial intelligence tools make it possible to analyze the so-called ‘big data’. Machine learning technologies are based on the concept of a machine that mimics human intelligence and and makes it possible to identify patterns that are inaccessible to traditional methods. There are still few examples of the use of artificial intelligence programs in transplantology. However, their number has increased markedly in recent years. A review of modern literature on the use of artificial intelligence systems in transplantology is presented.

scholarly journals What is Interpretability?

2020 ◽  
Author(s):  
Adrian Erasmus ◽  
Tyler D. P. Brunet ◽  
Eyal Fisher
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Novel Theory ◽  
Scientific Phenomenon ◽  
Artificial Neural ◽  
Artificial Intelligence Systems

AbstractWe argue that artificial networks are explainable and offer a novel theory of interpretability. Two sets of conceptual questions are prominent in theoretical engagements with artificial neural networks, especially in the context of medical artificial intelligence: (1) Are networks explainable, and if so, what does it mean to explain the output of a network? And (2) what does it mean for a network to be interpretable? We argue that accounts of “explanation” tailored specifically to neural networks have ineffectively reinvented the wheel. In response to (1), we show how four familiar accounts of explanation apply to neural networks as they would to any scientific phenomenon. We diagnose the confusion about explaining neural networks within the machine learning literature as an equivocation on “explainability,” “understandability” and “interpretability.” To remedy this, we distinguish between these notions, and answer (2) by offering a theory and typology of interpretation in machine learning. Interpretation is something one does to an explanation with the aim of producing another, more understandable, explanation. As with explanation, there are various concepts and methods involved in interpretation: Total or Partial, Global or Local, and Approximative or Isomorphic. Our account of “interpretability” is consistent with uses in the machine learning literature, in keeping with the philosophy of explanation and understanding, and pays special attention to medical artificial intelligence systems.

Sign in / Sign up

Export Citation Format

Share Document