Papers by Neven Dragojlovic
Proposal for Parallel Computer Architecture of a Cellular Type Aimed at Development of an Autonomous Learning Machine
2012 UKSim 14th International Conference on Computer Modelling and Simulation, 2012
This parallel computer proposal is based on a three dimensional architecture that is inseparable ... more This parallel computer proposal is based on a three dimensional architecture that is inseparable from the software stored in each of its basic components. The software in each basic component (cell) is an equivalent of cellular DNA, and as it deals with all possible situations in the cell's local environment, it would not need to be replaced frequently. All the "cells" at a given level have the same software, and different software at different levels. The system is asynchronous with fixed connections between levels. Only one module is described, but it is structured so that its output can be used as input to an equivalent module, whose software can be adapted to the needs of the user. The 3D modular architecture permits for creation of sufficiently complex modular system that permits simulation of the modular structure of the brain. It permits autonomous learning and feature extraction necessary for formation of the internal "model of the world", used for comparison with incoming sensory data. As autonomous learning machine needs to function on an internal model of the world, something that this system allows for, the research and development based on this system can help in the creation of a "commonsense-machine".
Parallel computer architecture of a cellular type, modifiable and expandable
Complex pattern deciphering using architecture parallel to swarm intelligence
Parallel computer architecture of a cellular type, modifiable and expandable
The assumption behind this system is that it is essential to understand information transfer in a... more The assumption behind this system is that it is essential to understand information transfer in a networked system if the system is to develop an internal worldview essential for creation of meaning. The pivoting idea in Ray Kurzweil’s “How to Create a Mind” is “a basic ingenious mechanism for recognizing, remembering, and predicting a pattern, repeated in the neo-cortex hundreds of millions of times, and organized in a hierarchy of increasing levels of abstraction”, and Hofstadter’s investigations in “Surfaces and Essences” make it clear that “perception is inseparable from high-level cognition”.
The goal of the system described in this article, is to create an autonomous deep learning system that can deal with the complete set of possible states of 2D changing patterns. In this system fast-data-inputs are classified and memorized in modules composed of cellular networks housed in a multilevel architecture. Queries, recall, recognition, and prediction are all part of the system, whose essence lies in distributed memory, asynchronous independent cellular calculations, and internal up and down feedback.
The problem of state space is resolved by dividing patterns into local primitives capable of dealing with total local state space, and sharing that information with surrounding local units and higher and lower levels.
Intelligent distributed computing needs to use nodes (agents) capable of independent computation,... more Intelligent distributed computing needs to use nodes (agents) capable of independent computation, and capable of receiving and sending information to other nodes. Such nodes need to use a common language (here binary code 2D patterns) and be housed in an architecture that permits each node to remember all of its potential states, all possible states of its environment, and use heuristics imbedded in its local program to reach decisions independently.
The “architecture” can be distributed between physically separated nodes interacting with Wi-Fi or similar means, and variety of inputs can be translated into common language. This article suggests how memory associations at each level, and at each node, can function together to create an evolving meaning and classification system. (Based on US 7426500 and US 864598 and articles by author found in the bibliography.)
Proposal for Parallel Computer Architecture of a Cellular Type Aimed at Development of an Autonomous Learning Machine
This parallel computer proposal is based on a three dimensional architecture that is inseparable ... more This parallel computer proposal is based on a three dimensional architecture that is inseparable from the software stored in each of its basic components. The software in each basic component (cell) is an equivalent of cellular DNA, and as it deals with all possible situations in the cell's local environment, it would not need to be replaced frequently. All the "cells" at a given level have the same software, and different software at different levels. The system is asynchronous with fixed connections between levels. Only one module is described, but it is structured so that its output can be used as input to an equivalent module, whose software can be adapted to the needs of the user. The 3D modular architecture permits for creation of sufficiently complex modular system that permits simulation of the modular structure of the brain. It permits autonomous learning and feature extraction necessary for formation of the internal "model of the world", used for comparison with incoming sensory data. As autonomous learning machine needs to function on an internal model of the world, something that this system allows for, the research and development based on this system can help in the creation of a "commonsense-machine".
Intelligent distributed computing needs to use nodes (agents) capable of independent computation,... more Intelligent distributed computing needs to use nodes (agents) capable of independent computation, and capable of receiving and sending information to other nodes. Such nodes need to use a common language (here binary code 2D patterns) and be housed in an architecture that permits each node to remember all of its potential states, all possible states of its environment, and use heuristics imbedded in its local program to reach decisions independently.
Uploads
Papers by Neven Dragojlovic
The goal of the system described in this article, is to create an autonomous deep learning system that can deal with the complete set of possible states of 2D changing patterns. In this system fast-data-inputs are classified and memorized in modules composed of cellular networks housed in a multilevel architecture. Queries, recall, recognition, and prediction are all part of the system, whose essence lies in distributed memory, asynchronous independent cellular calculations, and internal up and down feedback.
The problem of state space is resolved by dividing patterns into local primitives capable of dealing with total local state space, and sharing that information with surrounding local units and higher and lower levels.
The “architecture” can be distributed between physically separated nodes interacting with Wi-Fi or similar means, and variety of inputs can be translated into common language. This article suggests how memory associations at each level, and at each node, can function together to create an evolving meaning and classification system. (Based on US 7426500 and US 864598 and articles by author found in the bibliography.)