150 likes | 298 Views
A new type of Structured Artificial Neural Networks based on the Matrix Model of Computation. Sergio Pissanetzky. The Matrix Model of Computation (MMC) consists of two sparse matrices: M = (C, Q) C = Matrix of Services Q = Matrix of Sequences.
E N D
A new type of Structured Artificial Neural Networksbased on the Matrix Model of Computation Sergio Pissanetzky
The Matrix Model of Computation (MMC) consists of two sparse matrices: M = (C, Q) C = Matrix of Services Q = Matrix of Sequences
Converting a neural network to MMC b1 b2 w1 x1 w3 Σ φ1 v1 x3 w2 x2 φ2 Σ x5 v2 w4 x4
MMC as new type of neural network ● MMC is equivalent to the equations● MMC supports all ANN features. ● In addition, MMC supports global features such as network structure and organization, objects and ontologies.
The Scope Constriction Algorithm (SCA) SCA organizes information into objects and reveals the natural ontology of the system.
PROGRAM DATA
Data channel “Turbulent” flow
PROGRAM DATA G “Laminar” flow H G H G H
Where do objects come from? ● SCA only minimizes the scopes. ● In nature, scopes are resources. ● Processes compete for resources. ● Scopes are naturally minimized. ● Objects and inheritance arise naturally.
DYNAMICS ● New information keeps arriving. ● SCA keeps forming new objects. ● Larger objects grow out of smaller objects. ● Objects evolve with time. Some stabilize. ● The process continues indefinitely.