China
Africa
Explore chapters and articles related to this topic
Shallow Neural Networks
Published in Adrian A. Hopgood, Intelligent Systems for Engineers and Scientists, 2021
Artificial neural networks are a family of techniques for numerical learning, like the optimization algorithms reviewed in Chapters 6 and 7, but in contrast to the symbolic learning techniques reviewed in Chapter 5. They consist of many nonlinear computational elements that form the network nodes or neurons, linked by weighted interconnections. They are analogous in structure to the neurological system in humans and animals, which is made up of real rather than artificial neural networks. Practical artificial neural networks are much simpler than biological ones, so it is unrealistic to expect them to produce the sophisticated behavior of humans or animals. Nevertheless, they are effective at a range of tasks based on pattern matching. Throughout the rest of this book, we will use the expression neural network to mean an artificial neural network. The technique of using neural networks is described as connectionism. Neural networks typically comprise artificial neurons arranged in layers. The networks described in this chapter have few layers—seldom more than three—and are therefore considered shallow.
Cognitive Architectures
Published in Ron Fulbright, Democratization of Expertise, 2020
CLARION is also unique from other architectures in this group because it employs connectionism. Connectionism is a branch of artificial intelligence using artificial neural networks (ANNs) to describe and replicate intelligence (McCulloch and Pitts, 1943; Hebb, 1949; Medler, 1998). Connectionism is inspired by the structure of the human brain and is based on interconnected networks of simple units (like neurons in the human brain). When such a network is presented with a stimulus (some form of input information) it causes signals to flow from unit to unit regulated by weighting factors on each connection. The network’s response can be fine-tuned by changing the weights on the connections. Over several trials, the response of the network can be tuned to be different for different stimuli. After training, when presented with a similar stimulus, an ANN can determine the kind of stimulus by comparing its response to the responses formed by the training set. This gives connectionist networks a great deal of robustness in dealing with unstructured and partial data which historically have caused production rule systems problems.
Parallel Processing and Parallel Machines
Published in Hojjat Adeli, Parallel Processing in Computational Mechanics, 2020
Hojjat Adeli, Prasad R. Vishnubhotla
A number of cognition scientists and artificial intelligence researchers have argued that human intelligence is due to the interaction of a large number of simple processing units. This idea has not been very persuasive in the past, but there is a new resurgence of interest in modeling human thought and intelligence with parallel distributed processing (PDP) (Hinton and Anderson, 1981; Jorgensen and Matheus, 1986; McClelland et al., 1986; Rumelhart et al., 1986a,1986b). This research is also known as connectionism, a notion used to describe the importance of interactions among neurons in modeling intelligent systems. The PDP models of human thought processes are also appealing from a physiologic point of view.
Socioenactive Interaction: Addressing Intersubjectivity in Ubiquitous Design Scenarios
Published in International Journal of Human–Computer Interaction, 2023
Maria Cecilia Calani Baranauskas, Emanuel Felipe Duarte, José A. Valente
Cognitive Science was defined by Varela et al. (1991) more as the affiliation of some disciplines (Linguistics, Philosophy, Cognitive Psychology, Neuroscience) than a discipline per se, aiming at studying the mind. The computer model of the mind, which dominated the early works in the field, gave room to a diversity of visions within cognitive sciences at various periods of time. Cognitivism, inspired by digital computers, holds that (human) cognition is based on symbolic mental representation, i.e., the mind operates by processing representations of the world, which exists independently of the organism. Thus, its central proposition is the understanding that the world preexists to the subject, there is an objective reality capable of being captured, and knowledge occurs through representations of this objective world (Baum & Kroeff, 2018). In this model, information would reach the organism from exposure to stimuli (input) and return to the environment through behavioral responses (output), based on basic processing rules. Connectionism is thought of as an alternative to cognitivism, in which the symbolic processing is distributed over a network of simpler components, resulting in the emergence of a global behavior of the system. In contrast to cognitivism and connectionism, enactivism is a non-representationalist approach, in which cognition is understood as an embodied action, that is, it is intrinsically connected to the biological realization of an organism in its environment.
Classification of Customer Reviews Using Machine Learning Algorithms
Published in Applied Artificial Intelligence, 2021
An artificial neural network (ANN), usually called neural network (NN), is a mathematical model or computational model that is inspired by the structure and functional aspects of biological neural networks. A neural network consists of an interconnected group of artificial neurons, and it processes information using a connectionist approach to computation (the central connectionist principle is that mental phenomena can be described by interconnected networks of simple and often uniform units). In most cases, an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network during the learning phase. Modern neural networks are usually used to model complex relationships between inputs and outputs or to find patterns in data. A feed-forward neural network is an artificial neural network where connections between the units do not form a directed cycle. In this network, the information moves in only one direction, forward, from the input nodes, through the hidden nodes (if any) to the output nodes. There are no cycles or loops in the network.
Knowledge Management Models within Information Technology Projects
Published in Journal of Computer Information Systems, 2018
The first epistemology, cognitivism, focuses on logic and deduction and views the world as an objective set of facts. The second epistemology, connectionism, is based upon logic, but connectionism includes the individuals and the social process of knowledge [10]. According to von Krogh and Roos [41], connectionism also models knowledge development based upon the human brain. The third epistemology, autopoietic, uses a more open process for input into knowledge creation. According to von Krogh and Roos [41], autopoietic systems are characterized by being (a) autonomous, (b) simultaneously open and closed, (c) self-referential, and (d) observable. In the autopoietic system, input knowledge that may be either tacit or explicit will be viewed as data and knowledge is not imported but is produced by the individual.