The authors present an expandable digital architecture that provides an efficient real time implementation platform for large neural networks. The architecture makes heavy use of the techniques of bit serial stochasti...
详细信息
The authors present an expandable digital architecture that provides an efficient real time implementation platform for large neural networks. The architecture makes heavy use of the techniques of bit serial stochasti...
详细信息
The authors present an expandable digital architecture that provides an efficient real time implementation platform for large neural networks. The architecture makes heavy use of the techniques of bit serial stochastic computing to carry out the large number of required parallel synaptic calculations. In this design all real valued quantities are encoded on to stochastic bit streams in which the '1' density is proportional to the given quantity. The actual digital circuitry is simple and highly regular thus allowing very efficient space usage of fine grained FPGAs. Another feature of the design is that the large number of weights required by a neural network are generated by circuitry tailored to each of their specific values, thus saving valuable cells. Whenever one of these values is required to change, the appropriate circuitry must be dynamically reconfigured. This may always be achieved in a fixed and minimum number of cells for a given bit stream resolution.< >
Case-based reasoning can be applied to software reuse. The approach presented goes beyond furnishing a library of potentially reusable modules and provides a tool that supports the process of reusing software. It uses...
详细信息
Case-based reasoning can be applied to software reuse. The approach presented goes beyond furnishing a library of potentially reusable modules and provides a tool that supports the process of reusing software. It uses case-based reasoning to add flexibility and adaptability to the compositional model of reuse. The authors describe the structure of the case base, emphasizing the case acquisition process during which high level functional information is associated with its components. The system performs advanced data-flow analysis of source code to guide acquisition of the functional specification of a library of software modules. The system then decomposes a user's problem, retrieves matching cases, and adapts and assembles their code. The data-flow of the result is again analyzed to produce test cases which can be used to evaluate the success of case-based reasoning.< >
This paper shows how the compositional software reuse approach can be fruitfully cast in the casebased reasoning (CBR) paradigm. Any CBR system in which the cases are software artifacts must rely on software-specific ...
详细信息
This paper develops an approach which reuses queries from a well known domain (the base domain) in an unfamiliar one (the target domain). The objective is to model the behavior of naive users who often adapt queries f...
详细信息
This paper describes a relational learning system LOPSTER (inductive LOgic Programming with Sub-unification of TERms) that learns very efficiently and with small number of examples a class of typical recursive logic p...
详细信息
The authors develop an approach which reuses queries from a well known domain called the base domain in an unfamiliar one called the target domain. The objective is to model the behavior of naive users who often adapt...
详细信息
The authors develop an approach which reuses queries from a well known domain called the base domain in an unfamiliar one called the target domain. The objective is to model the behavior of naive users who often adapt queries from documentation examples to the problem at hand. They rely on a weak form of derivational analogy-traces of a planner operating in the base domain are used to derive a target domain query's implementation in SQL from its specification. The very simple planner used builds in the base domain plans that result in particularly simple, prototypical queries. Queries are specified in a high level subset of a natural language.< >
The authors show how the compositional software reuse approach can be fruitfully cast in the case-based reasoning (CBR) paradigm. Any CBR system in which the cases are software artifacts must rely on software-specific...
详细信息
The authors show how the compositional software reuse approach can be fruitfully cast in the case-based reasoning (CBR) paradigm. Any CBR system in which the cases are software artifacts must rely on software-specific concepts to provide adequate knowledge representation. However, the fact that these software artifacts can be executed on a computer should yield stronger results than could be expected from generic CBR. The CAESAR system relies on advanced data flow analysis concepts for its representation of knowledge about software modules. Cases and their fragments are retrieved and adapted to solve new problems. The new cases which result are executed on system-generated test sets to evaluate the results of CBR.< >
Kayles is a nonpartizan two-person game. In such games the moves available to both the players are the same and either the player on move wins or the previous player wins. In the "normal form" of the game, t...
详细信息
Kayles is a nonpartizan two-person game. In such games the moves available to both the players are the same and either the player on move wins or the previous player wins. In the "normal form" of the game, the last player who can make a move is declared the winner. In the "misere form" of the game, the player who makes the last move is declared the loser. The complete analysis of the normal form of the game of Kayles has been described by Berlekamp, Conway, and Guy. This paper completes their analysis of the misere form of Kayles. This is done on the basis of certain properties of what have been called "wild" positions of misere games.
Designing interactive interfaces for individual usage is a significantly hard task that is being surmounted by evolving theory and hours of trial aand error. The task of designing interactive interfaces for cooperativ...
详细信息
暂无评论