Book Chapter10.1007/978-3-642-13523-1_26
A network-based computational model with learning
Hideaki Suzuki,Hiroyuki Ohsaki,Hidefumi Sawai +2 more
- 21 Jun 2010
- pp 193-193
8
TL;DR: A more realistic model for the brain could be implemented with functional molecular agents which move around the neural network and cause a change in the neural functionality.
read more
Abstract: As is well-known, a natural neuron is made up of a huge number of biomolecules from a nanoscopic point of view. A conventional ‘artificial neural network’ (ANN) [1] consists of nodes with static functions, but a more realistic model for the brain could be implemented with functional molecular agents which move around the neural network and cause a change in the neural functionality.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Medical Diagnostic Systems Using Artificial Intelligence (AI) Algorithms: Principles and Perspectives
Simarjeet Kaur,Jimmy Singla,Lewis Nkenyereye,Sudan Jha,Deepak Prashar,Gyanendra Prasad Joshi,Shaker El-Sappagh,Md. Saiful Islam,S. M. Riazul Islam +8 more
TL;DR: Some important insights are revealed into current and previous different AI techniques in the medical field used in today’s medical research, particularly in heart disease prediction, brain disease, prostate, liver disease, and kidney disease.
Algorithmically transitive network: A self-organizing data-flow network with learning
Hideaki Suzuki,Hiroyuki Ohsaki,Hidefumi Sawai +2 more
- 01 Dec 2010
TL;DR: A novel non-von Neumann computational model named “Algorithmically Transitive Network” (ATN) is presented, a data-flow network composed of operation nodes and data edges that causes backward propagation of differential coefficients with respect to token variables or node parameters.
A Network Representation of First-Order Logic That Uses Token Evolution for Inference
TL;DR: The paper argues the soundness and completeness of the network in a conventional way, then explains how a kind of ambiguous solution is obtained by the newly developed method.
3
A Data-Flow Network That Represents First-Order Logic for Inference
Hideaki Suzuki,Mikio Yoshida,Hidefumi Sawai +2 more
- 16 Nov 2012
TL;DR: The paper argues the soundness and completeness of the network in a conventional way, then explains how a kind of ambiguous solution is obtained by a new developed method to solve simultaneous equations buried in the network.
2
Algorithmically Transitive Network: Learning Padé Networks for Regression
Hideaki Suzuki
- 10 Dec 2012
TL;DR: Numerical experiments with benchmark problems show that the ATN in the form of a Pade approximant has better learning capability than linear regression analysis in a power series, the standard multi-layered neural network with the back-propagation learning, the support vector machine using the radial basis function as kernel, or the simple genetic programming.
1
References
Learning representations by back-propagating errors
TL;DR: Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.
30.1K
•Book
Neural Networks And Learning Machines
Simon Haykin
- 01 Jan 2010
TL;DR: Refocused, revised and renamed to reflect the duality of neural networks and learning machines, this edition recognizes that the subject matter is richer when these topics are studied together.
7.2K
Towards an active network architecture
D.L. Tennenhouse,David Wetherall +1 more
- 15 Apr 1996
TL;DR: This paper describes the vision of an active network architecture, the approach to its design, and survey the technologies that can be brought to bear on its implementation, and proposes that the research community mount a joint effort to develop and deploy a wide area ActiveNet.
739
•Book
The Roots of Backpropagation: From Ordered Derivatives to Neural Networks and Political Forecasting
Paul J. Werbos
- 01 Jan 1994
TL;DR: This book discusses forms of Backpropagation for Sensitivity Analysis, Optimization, and Neural Networks, and the importance of the Multivariate ARMA(1,1) Model in this regard.
734
•Book
Data flow computing: theory and practice
John A. Sharp
- 03 Jan 1992
TL;DR: This book contains a selection of chapters by researchers on various aspects of the data flow approach in computing: comparisons of various data flow machine designs, data flow architectures, intentional programming and operator nets, and the relationship between data flow models and modern structured design techniques.
59