A domain-specific software architecture for adaptive intelligent systems

Hayes-Roth, Barbara; Pfleger, Karl; Lalanda, Philippe; Morignot, Philippe; Balabanović, Marko

doi:10.1109/32.385968

Cited by 95 publications

(32 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The requirements of recurrent learning processes can be satisfied by the reconfiguration and flexibility of FPGAs, [11], [20], [21]. Weight modification and architecture reconfiguration can be carried out at run time.…”

Section: Characteristics Of the System Architecture For The Fpga Basementioning

confidence: 99%

See 1 more Smart Citation

Approach to an FPGA embedded, autonomous object recognition system: run-time learning and adaptation

et al. 2009

View full text Add to dashboard Cite

Neural networks, widely used in pattern recognition, security applications and robot control have been chosen for the task of object recognition within this system. One of the main drawbacks of the implementation of traditional neural networks in reconfigurable hardware is the huge resource consuming demand. This is due not only to their intrinsic parallelism, but also to the traditional big networks designed. However, modern FPGA architectures are perfectly suited for this kind of massive parallel computational needs. Therefore, our proposal is the implementation of Tiny Neural Networks, TNN -self-coined term-, in reconfigurable architectures. One of most important features of TNNs is their learning ability. Therefore, what we show here is the attempt to rise the autonomy features of the system, triggering a new learning phase, at run-time, when necessary. In this way, autonomous adaptation of the system is achieved. The system performs shape identification by the interpretation of object singularities. This is achieved by interconnecting several specialized TNN that work cooperatively. In order to validate the research, the system has been implemented and configured as a perceptron-like TNN with backpropagation learning and applied to the recognition of shapes. Simulation results show that this architecture has significant performance benefits.

show abstract

Section: Characteristics Of the System Architecture For The Fpga Basementioning

confidence: 99%

“…It is part of a broader line of research investigating methods of scaling high level, intelligent, cognitive architectures, into limited resources embedded systems. An adapted Blackboard architecture, BB1/AIS [10], [11], is the architectural underlying framework on top of which the system is built.…”

Section: Introductionmentioning

confidence: 99%

Approach to an FPGA embedded, autonomous object recognition system: run-time learning and adaptation

et al. 2009

View full text Add to dashboard Cite

show abstract

“…The work on "design patterns" is typical of this strand. While the "Gang of Four" patterns [33] are directed at the programming language level, the concept can be applied at any level of abstraction, including requirements (where the experience may be captured as "frames" [42]), whole-concept system structure (where the experience is captured as domainspecific software architectures [10,38,79]), and generally at the level of system components and connectors (where the experience is captured as styles and architectural templates [9,34]). …”

Section: The Wisdom Of Experiencementioning

confidence: 99%

Software Design and Architecture The once and future focus of software engineering

Taylor

Hoek

2007

Future of Software Engineering (FOSE '07)

View full text Add to dashboard Cite

show abstract

“…A more promising approach would be to also supply more abstract actions and replanning functions along with the detailed orders, a problem which is still the subject of research. Though the selection of suitable abstractions and associated architectures is still a topic of ongoing research [24,40,55,67], a promising prototype implementation of high-level concepts for robots in space is underway [53,54].…”

Section: Uncontrolled Environmentsmentioning

confidence: 99%

Integrated architecture for industrial robot programming and control

Nilsson

Johansson

1999

Robotics and Autonomous Systems

View full text Add to dashboard Cite

As robot control systems are traditionally closed, it is difficult to add supplementary intelligence. Accordingly, as based on a new notion of user views, a layered system architecture is proposed. Bearing in mind such industrial demands as computing efficiency and simple factory-floor operation, the control layers are parameterized by means of functional operators consisting of pieces of compiled code that can be passed as parameters between the layers. The required interplay between application-specific programs and built-in motion control is thereby efficiently accomplished. The results from experimental evaluation and several case studies suggest the architecture to be very useful also in an industrial context.

show abstract

A domain-specific software architecture for adaptive intelligent systems

Cited by 95 publications

References 22 publications

Approach to an FPGA embedded, autonomous object recognition system: run-time learning and adaptation

Approach to an FPGA embedded, autonomous object recognition system: run-time learning and adaptation

Software Design and Architecture The once and future focus of software engineering

Integrated architecture for industrial robot programming and control

Contact Info

Product

Resources

About