A neural compiler

Gruau, Frédéric; Ratajszczak, Jean-Yves; Wiber, Gilles

doi:10.1016/0304-3975(94)00200-3

Cited by 28 publications

(15 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are some related works in the literature about symbolic neural computation. Article [3] introduces JaNNeT, a dialect of Pascal with some parallel constructs. This algorithmic description is translated, using several automated steps to produce a non-homogenous neural network (with four different neuron types) able to perform the required computations.…”

Section: Netdefmentioning

confidence: 99%

Competitive Learning and Symbolic Computation Integration

Neto¹,

Coelho²,

Ferreira³

2016

Anais Do 5. Congresso Brasileiro De Redes Neurais

View full text Add to dashboard Cite

In some recent works, it was shown that any algorithmic description might be mapped on a recurrent neural network. A neural oriented language called NETDEF, such that each program corresponds to a modular neural net that computes it, is the tool to achieve this. This article focuses on merging symbolic and subsymbolic computation. Adding high-order neurons to the network model allows learning integration into the NETDEF symbolic computing paradigm, since it is possible to execute learning algorithms in the same neural model that performs symbolic computation. It is shown how the model may process competitive learning methods inside this framework.

show abstract

Section: Netdefmentioning

confidence: 99%

Competitive Learning and Symbolic Computation Integration

Neto¹,

Coelho²,

Ferreira³

2016

Anais Do 5. Congresso Brasileiro De Redes Neurais

View full text Add to dashboard Cite

show abstract

“…Simon 5 and Chakraborty 6, 7 experimented with the feasibility of compilers that can use various types of heuristics. Gruau et al 8 developed a neural compiler. The compiler takes as input a Pascal program and produces as output a neural network that performs the computations specified by the program.…”

Section: Related Workmentioning

confidence: 99%

A compiler‐based toolkit to teach and learn finite automata

Chakraborty

Saxena

Katti

2010

Comp Applic In Engineering

View full text Add to dashboard Cite

This paper introduces a compiler technology based approach to model and simulate finite automata for pedagogical purposes. The compiler technology helps to define a language to formally model finite automata and to develop a toolkit to simulate them efficiently. The language is called Finite Automaton Description Language (FADL) and the toolkit is based on it. A fast single-pass compiler is used to compile a finite automaton defined in FADL. Then an interpreter is used to simulate the working of the compiled finite automaton for any input string. The nondeterminism of a Nondeterministic Finite Automaton (NFA) is simulated using backtracking. A tool to view the transition diagram of the finite automaton is provided. A Deterministic Finite Automaton (DFA) can be additionally compiled using an optimizing compiler that also minimizes the number of states. Tools for converting an NFA to a DFA and for converting a DFA to a Turing machine are also provided. A preliminary testing of the toolkit has been performed in which the participating students observed that the toolkit is an interesting teaching tool and it helped them to acquire a better perception about finite automata.

show abstract

“…The initial research studies on Blob computing were theoretical research works on defining a language based on cellular development (Cellular Encoding) [26], on designing a compiler to translate imperative programs into a cellular code [30], on proving the optimal space/time model performance within a simplified framework [31], and finally on introducing the Blob concept and proving implementation correctness on an arbitrary architecture [28]. The present and upcoming studies aim at presenting the principles of Blob computing, Blob programming and investigating implementation issues of Blob computers.…”

Section: Blob Computingmentioning

confidence: 99%

“…The program specifies when and how Blobs are created, and as a result, it implicitly tells the architecture how to exploit space and parallelism. We have already developed a compiler for translating programs based on an imperative language (Pascal) into Cellular Code [30], on which the Blob language is based, without significantly increasing the program size, thereby demonstrating the expressiveness of the programming language; the compiler and the associated translation techniques have been patented [25]. Section 2 presents the related work.…”

Section: Introductionmentioning

confidence: 99%

BLOB computing

Gruau

Lhuillier

Reitz

et al. 2004

Proceedings of the 1st Conference on Computing Frontiers

Self Cite

View full text Add to dashboard Cite

Current processor and multiprocessor architectures are almost all based on the Von Neumann paradigm. Based on this paradigm, one can build a general-purpose computer using very few transistors, e.g., 2250 transistors in the first Intel 4004 microprocessor. In other terms, the notion that on-chip space is a scarce resource is at the root of this paradigm which trades on-chip space for program execution time. Today, technology considerably relaxed this space constraint. Still, few research works question this paradigm as the most adequate basis for high-performance computers, even though the paradigm was not initially designed to scale with technology and space.In this article, we propose a different computing model, defining both an architecture and a language, that is intrinsically designed to exploit space; we then investigate the implementation issues of a computer based on this model, and we provide simulation results for small programs and a simplified architecture as a first proof of concept. Through this model, we also want to outline that revisiting some of the principles of today's computing paradigm has the potential of overcoming major limitations of current architectures.

show abstract

A neural compiler

Cited by 28 publications

References 4 publications

Competitive Learning and Symbolic Computation Integration

Competitive Learning and Symbolic Computation Integration

A compiler‐based toolkit to teach and learn finite automata

BLOB computing

Contact Info

Product

Resources

About