In this paper, we investigate the possibility of applying machine learning methods to data derived from the area of natural language and show how rules, induced by machine learning, are changed after the original data are compressed by grouping together entries, attributes, and attribute values. Also shown is how excessive compression of input data may affect the accuracy of induced rules.

/pdf/data-compression-in-machine-learning-applied-to-natural-5gllofy5z9.pdf

Algebraic Structure Theory of Sequential Machines

Data compression in machine learning applied to natural language

Hierarchical COCOLOG for finite machines

The discussion in the computer-science literature of the relative merits of linear- versus branching-time frameworks goes back to the early 1980s. One of the beliefs dominating this discussion has been that the linear-time framework is not expressive enough semantically, making linear-time logics lacking in expressiveness. In this work we examine the branching-linear issue from the perspective of process equivalence, which is one of the most fundamental concepts in concurrency theory, as defining a notion of equivalence essentially amounts to defining semantics for processes. We accept three principles that have been recently proposed for concurrent-process equivalence. The first principle takes contextual equivalence as the primary notion of equivalence. The second principle requires the description of a process to specify all relevant behavioral aspects of the process. The third principle requires observable process behavior to be reflected in its input/output behavior. It has been recently shown that under these principles trace semantics for nondeterministic transducers is fully abstract. Here we consider two extensions of the earlier model: probabilistic transducers and asynchronous transducers. We show that in both cases trace semantics is fully abstract.

background

/pdf/trace-semantics-is-fully-abstract-20rx148rap.pdf

Trace Semantics is Fully Abstract

The Interpreted Sequential Machine (ISM) model handles a new approach for modeling and formal verification of discrete complex systems.

Formal Representation and Proof of the Interpreted Sequential Machine Model

Techniques for the advanced logic design of nanodevices and nanolCs in spatial dimensions are being formulated to incorporate specific topologies that satisfy certain requirements of nanotechnology. One of these topologies, the hypercube, is currently being considered for the design of a network-based combinational logic implementation in the form of a hypercube extension called the N-hypercube. We propose the M-hypercube, using a similar topology to design any sequential logic in spatial dimensions. To reduce the complexity of the M-hypercube design, two methods, a top-down and a bottom-up, are presented. The former uses sequential machine decomposition methods and the latter uses a new hypercube topology, called the MN-cell. The MN-cell, consisting of two closely coupled 2D hypercubes, an M-hypercube and an N-hypercube, is a 3D hypercube. It is shown that MN-cells can implement flip-flops and thus can be used as building blocks for sequential logic design in nanodimensions. The logic design of a basic computer in nanospace using MN-cells and N-hypercubes is also presented using several examples.

Algebraic Structure Theory of Sequential Machines

Citations

Data compression in machine learning applied to natural language

Hierarchical COCOLOG for finite machines

Trace Semantics is Fully Abstract

Formal Representation and Proof of the Interpreted Sequential Machine Model

Logic and Computer Design in Nanospace

Related Papers (5)

Switching and Finite Automata Theory

Optimal State Assignment for Finite State Machines

MIS: A Multiple-Level Logic Optimization System

Introduction to Automata Theory, Languages, and Computation

Logic Minimization Algorithms for VLSI Synthesis