
Autism and Computational Simulations
... AD and various diseases leading to dementia are connected with decrease of the density of weak synaptic connections. What happens with associative memory in simple models if weak connections are removed? Is there a biological mechanism that can help to ...
... AD and various diseases leading to dementia are connected with decrease of the density of weak synaptic connections. What happens with associative memory in simple models if weak connections are removed? Is there a biological mechanism that can help to ...
The Evolution of General Intelligence
... of animal brains, simple two-layer neural networks were evolved using the NEAT algorithm. The connections between the neurons simulated the interaction of processes in the brain, and the length of prolonged evolution (i.e. evolution after a satisfactory performance had been reached) represented the ...
... of animal brains, simple two-layer neural networks were evolved using the NEAT algorithm. The connections between the neurons simulated the interaction of processes in the brain, and the length of prolonged evolution (i.e. evolution after a satisfactory performance had been reached) represented the ...
Machine Learning - Dipartimento di Informatica
... We introduce the principles and the critical analysis of the main paradigms for learning from data and their applications. The concepts are progressively introduced starting from simpler approaches up to the state-of-the-art models in the general conceptual framework of modern machine learning. The ...
... We introduce the principles and the critical analysis of the main paradigms for learning from data and their applications. The concepts are progressively introduced starting from simpler approaches up to the state-of-the-art models in the general conceptual framework of modern machine learning. The ...
Towards a robotic model of the mirror neuron system
... Once the MSOM have been trained, they can generate map outputs (as described in Experiment 1) that can serve as patterns to be associated. For learning the association between sensory and motor representations, we use a threelayer bidirectional perceptron trained using our Bidirectional Activation-b ...
... Once the MSOM have been trained, they can generate map outputs (as described in Experiment 1) that can serve as patterns to be associated. For learning the association between sensory and motor representations, we use a threelayer bidirectional perceptron trained using our Bidirectional Activation-b ...
NEUR3041 Neural computation: Models of brain function 2014
... Brown M A & Sharp P E (1995) `Simulation of spatial-learning in the morris water maze by a neural-network model of the hippocampal-formation and nucleus-accumbens Hippocampus 5 171188. Burgess N, Donnett J G, Jeffery K J & O'Keefe J (1997) `Robotic and neuronal simulation of the hippocampus and ...
... Brown M A & Sharp P E (1995) `Simulation of spatial-learning in the morris water maze by a neural-network model of the hippocampal-formation and nucleus-accumbens Hippocampus 5 171188. Burgess N, Donnett J G, Jeffery K J & O'Keefe J (1997) `Robotic and neuronal simulation of the hippocampus and ...
Artificial Intelligence - Information Technology Services
... Most expert systems are built on the concepts of questions and rules. The expert system asks a question. If it is answered “yes”, another question appears. If it is answered “no”, a different question appears. Based on the answer to this question, another question is asked. This process of question ...
... Most expert systems are built on the concepts of questions and rules. The expert system asks a question. If it is answered “yes”, another question appears. If it is answered “no”, a different question appears. Based on the answer to this question, another question is asked. This process of question ...
Artificial Intelligence - Information Technology Services
... Most expert systems are built on the concepts of questions and rules. The expert system asks a question. If it is answered “yes”, another question appears. If it is answered “no”, a different question appears. Based on the answer to this question, another question is asked. This process of question ...
... Most expert systems are built on the concepts of questions and rules. The expert system asks a question. If it is answered “yes”, another question appears. If it is answered “no”, a different question appears. Based on the answer to this question, another question is asked. This process of question ...
Signature Identification and Recognition using Elman Neural Network
... describe the ability of a computer to translate human writing into text. This may take place in one of two ways either by scanning of written text (off-line method) or by writing directly on to a peripheral input device. The first of these recognition techniques, known as Optical Character Recogniti ...
... describe the ability of a computer to translate human writing into text. This may take place in one of two ways either by scanning of written text (off-line method) or by writing directly on to a peripheral input device. The first of these recognition techniques, known as Optical Character Recogniti ...
Biology
... • Learning algorithms can be very useful even if they have nothing to do with how the brain works ...
... • Learning algorithms can be very useful even if they have nothing to do with how the brain works ...
Prediction - UBC Computer Science
... when restricted to the “core” nodes above. •Evaluation: among the topmost likely edges predicted, how well we do on precision and recall. •Precision = analog of soundness. •Recall = analog of completeness. ...
... when restricted to the “core” nodes above. •Evaluation: among the topmost likely edges predicted, how well we do on precision and recall. •Precision = analog of soundness. •Recall = analog of completeness. ...
cogsci200
... An object (sensory, abstract, etc.) or action (movement process, thought process, etc.) is represented by a collection of feature attractor tokens, each expressing a single token (node) from its lexicon. ...
... An object (sensory, abstract, etc.) or action (movement process, thought process, etc.) is represented by a collection of feature attractor tokens, each expressing a single token (node) from its lexicon. ...
Fraud Detection in Communications Networks Using Neural and
... network consists of five hidden units and one binary output. The neural network was trained using Quasi-Newton optimization. In order to constraint the complexity of the mapping, weight decay type of regularization was used. In weight decay, the cost function (error between the network output and th ...
... network consists of five hidden units and one binary output. The neural network was trained using Quasi-Newton optimization. In order to constraint the complexity of the mapping, weight decay type of regularization was used. In weight decay, the cost function (error between the network output and th ...
Document
... of the literature and the totality of relevant online quantitative data RelEx software for mapping English sentences into semantic structures Doesn’t do reasoning to resolve semantic ambiguity in a context-appropriate way ...
... of the literature and the totality of relevant online quantitative data RelEx software for mapping English sentences into semantic structures Doesn’t do reasoning to resolve semantic ambiguity in a context-appropriate way ...
UNIVERSIDAD SAN FRANCISCO DE QUITO USFQ Detección y
... wink followed by a right wink. Here, it can also be noticed that not all channels showed important activity as discussed in the last section. In order to extract the four entries necessaries per channel in real time, a Hamming window was applied to the signals. This window was selected so the proces ...
... wink followed by a right wink. Here, it can also be noticed that not all channels showed important activity as discussed in the last section. In order to extract the four entries necessaries per channel in real time, a Hamming window was applied to the signals. This window was selected so the proces ...
ARTIFICIAL NEURAL NETWORKS AND COMPLEXITY: AN
... 1. Introduction: complex systems and connectionism Understanding the world around us is usually a difficult task. All dynamically evolving phenomena in the natural world are produced by a strong interaction among a great number of causes of which only few are visible or measurable. Moreover, the phe ...
... 1. Introduction: complex systems and connectionism Understanding the world around us is usually a difficult task. All dynamically evolving phenomena in the natural world are produced by a strong interaction among a great number of causes of which only few are visible or measurable. Moreover, the phe ...
MS PowerPoint 97/2000 format
... – Input: A digraph H = {Xj -> Xi : Xj Ci}, and a set of weights w(Xi ,Y) for each Xi, Y Ci – Output: An acyclic subgraph G H that maximizes WH [G] = i w(Xi , Pa(Xi)) – Decompose H by using standard graph decomposition methods – Find a local maximum weight – Combine them into a global solution ...
... – Input: A digraph H = {Xj -> Xi : Xj Ci}, and a set of weights w(Xi ,Y) for each Xi, Y Ci – Output: An acyclic subgraph G H that maximizes WH [G] = i w(Xi , Pa(Xi)) – Decompose H by using standard graph decomposition methods – Find a local maximum weight – Combine them into a global solution ...
Simulation of PSO using ONE Simulator in DTN
... fastest possible routing scheme. In epidemic routing, the data delivery results in inefficient use of the network resources such as power, bandwidth, and buffer at each node[4,5]. ii) Location Based Routing In some cases, the location of the nodes may be known, that can be used in case of opportunis ...
... fastest possible routing scheme. In epidemic routing, the data delivery results in inefficient use of the network resources such as power, bandwidth, and buffer at each node[4,5]. ii) Location Based Routing In some cases, the location of the nodes may be known, that can be used in case of opportunis ...
Learning as a phenomenon occurring in a critical state
... perceptual learning has evidenced that training to a specific task induces dynamic changes in the functional connectivity able to “sculpt” the spontaneous activity of the resting human brain and to act as a form of “system memory” [21]. It is therefore tempting to investigate the role that critical ...
... perceptual learning has evidenced that training to a specific task induces dynamic changes in the functional connectivity able to “sculpt” the spontaneous activity of the resting human brain and to act as a form of “system memory” [21]. It is therefore tempting to investigate the role that critical ...
PSY105 Neural Networks 2/5
... • We can describe patterns at one level of description that emerge due to rules followed at a lower level of description. • Neural network modellers hope that we can understand behaviour by creating models of networks of artificial neurons. ...
... • We can describe patterns at one level of description that emerge due to rules followed at a lower level of description. • Neural network modellers hope that we can understand behaviour by creating models of networks of artificial neurons. ...
Acquisition of Box Pushing by Direct-Vision
... trial also can be seen in Fig. 5(b). The reason of the behavioral difference is suggested as follows. In the case of (b), if the robot makes a frontal approach toward the center of the long side, it has to go a long way round and takes a long time to reach. On the other hand, if it goes forward, the ...
... trial also can be seen in Fig. 5(b). The reason of the behavioral difference is suggested as follows. In the case of (b), if the robot makes a frontal approach toward the center of the long side, it has to go a long way round and takes a long time to reach. On the other hand, if it goes forward, the ...
High Performance Data mining by Genetic Neural Network
... weights for the network. Balance between genetic programming and neural networks, the network topology are an interesting topic. In advance of his generation program using appropriate structure for the network gets updated. Performance results on some math functions show that the algorithm has sever ...
... weights for the network. Balance between genetic programming and neural networks, the network topology are an interesting topic. In advance of his generation program using appropriate structure for the network gets updated. Performance results on some math functions show that the algorithm has sever ...
Catastrophic interference
Catastrophic Interference, also known as catastrophic forgetting, is the tendency of a artificial neural network to completely and abruptly forget previously learned information upon learning new information. Neural networks are an important part of the network approach and connectionist approach to cognitive science. These networks use computer simulations to try and model human behaviours, such as memory and learning. Catastrophic interference is an important issue to consider when creating connectionist models of memory. It was originally brought to the attention of the scientific community by research from McCloskey and Cohen (1989), and Ractcliff (1990). It is a radical manifestation of the ‘sensitivity-stability’ dilemma or the ‘stability-plasticity’ dilemma. Specifically, these problems refer to the issue of being able to make an artificial neural network that is sensitive to, but not disrupted by, new information. Lookup tables and connectionist networks lie on the opposite sides of the stability plasticity spectrum. The former remains completely stable in the presence of new information but lacks the ability to generalize, i.e. infer general principles, from new inputs. On the other hand, connectionst networks like the standard backpropagation network are very sensitive to new information and can generalize on new inputs. Backpropagation models can be considered good models of human memory insofar as they mirror the human ability to generalize but these networks often exhibit less stability than human memory. Notably, these backpropagation networks are susceptible to catastrophic interference. This is considered an issue when attempting to model human memory because, unlike these networks, humans typically do not show catastrophic forgetting. Thus, the issue of catastrophic interference must be eradicated from these backpropagation models in order to enhance the plausibility as models of human memory.