Combining Visual Attention, Object Recognition and Associative Information Processing in a NeuroBotic System

Fay, Rebecca; Kaufmann, Ulrich; Knoblauch, Andreas; Markert, Heiner; Palm, Günther

doi:10.1007/11521082_8

Cited by 14 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The full complexity of cognition would then arise from many such modules interacting. Operational cell assemblies of this kind have been used to implement language and behavioural components on robots (Fay et al 2005;Knoblauch et al 2005a, b;Markert and Palm 2006;Markert et al 2005Markert et al , 2007. They can also well be implemented in modern neural hardware (Indiveri 2007;Schemmel et al 2004;Wijekoon and Dudek 2008) and may therefore form a programming paradigm for future computing hardware (Palm 1982;Wennekers 2006).…”

Section: Introductionmentioning

confidence: 97%

Syntactic sequencing in Hebbian cell assemblies

Wennekers

Palm

2009

Cogn Neurodyn

Self Cite

View full text Add to dashboard Cite

Hebbian cell assemblies provide a theoretical framework for the modeling of cognitive processes that grounds them in the underlying physiological neural circuits. Recently we have presented an extension of cell assemblies by operational components which allows to model aspects of language, rules, and complex behaviour. In the present work we study the generation of syntactic sequences using operational cell assemblies timed by unspecific trigger signals. Syntactic patterns are implemented in terms of hetero-associative transition graphs in attractor networks which cause a directed flow of activity through the neural state space. We provide regimes for parameters that enable an unspecific excitatory control signal to switch reliably between attractors in accordance with the implemented syntactic rules. If several target attractors are possible in a given state, noise in the system in conjunction with a winner-takes-all mechanism can randomly choose a target. Disambiguation can also be guided by context signals or specific additional external signals. Given a permanently elevated level of external excitation the model can enter an autonomous mode, where it generates temporal grammatical patterns continuously.

show abstract

Section: Introductionmentioning

confidence: 97%

Syntactic sequencing in Hebbian cell assemblies

Wennekers

Palm

2009

Cogn Neurodyn

Self Cite

View full text Add to dashboard Cite

show abstract

“…The details of the neuron model and the learning rule are given in Appendix A. The complete layout of all modules comprising our system (as of today) is described in Fay et al (2004). In order to demonstrate the functionality of the cortical network we have embedded it into a simple robot scenario.…”

Section: Introductionmentioning

confidence: 99%

Modelling of syntactical processing in the cortex

2007

Self Cite

View full text Add to dashboard Cite

“…Closely related to our work are the approaches of Arbib [12], Roy [13], Kirchmar and Edelmann [14] and of Billard and Hayes [15]. However, to our knowledge this is the first robot control architecture including simple language understanding, visual object recognition and action planning, that is realized completely by neural networks [11] and that is able to resolve ambiguities and to learn new words during performance [10]. It also represents the first real-time functional simulation of populations of spiking neurons in more than ten cortex areas in cooperation.…”

Section: Discussionmentioning

confidence: 80%

“…To show the correct semantical understanding of parsed sentences by the system, the model is embedded into a robot [11]. Therefore, the system is extended by a neural action planning part, some simple motor programs (e.g.…”

Section: Discussionmentioning

confidence: 99%

“…Our approach to language understanding should be understood in the context of a larger model that integrates language understanding, visual object recognition, and action planning in a functional, large-scale neural network in a robotics scenario Parts of the presented work have been developed earlier within the MirrorBot project of the European Union 1 , and results on sentence understanding [10] and the robotics application [11] have been published earlier. Most other approaches deal only with one of the aspects mentioned above at a time.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Sentence Understanding and Learning of New Words with Large-Scale Neural Networks

Markert

Kayikci

Palm

Artificial Neural Networks in Pattern Recognition

Self Cite

View full text Add to dashboard Cite

We have implemented a speech command system which can understand simple command sentences like "Bot lift ball" or "Bot go table" using hidden Markov models (HMMs) and associative memories with sparse distributed representations. The system is composed of three modules: (1) A set of HMMs is used on phoneme level to get a phonetic transcription of the spoken sentence, (2) a network of associative memories is used to determine the word belonging to the phonetic transcription and (3) a neural network is used on the sentence level to determine the meaning of the sentence. The system is also able to learn new object words during performance.

show abstract

Combining Visual Attention, Object Recognition and Associative Information Processing in a NeuroBotic System

Cited by 14 publications

References 12 publications

Syntactic sequencing in Hebbian cell assemblies

Syntactic sequencing in Hebbian cell assemblies

Modelling of syntactical processing in the cortex

Sentence Understanding and Learning of New Words with Large-Scale Neural Networks

Contact Info

Product

Resources

About