Title :
Grounding Symbols: Labelling and Resolving Pronoun Resolution with fLIF Neurons
Author :
Jamshed, Fawad ; Huyck, Christian
Author_Institution :
Middlesex Univ., London, UK
Abstract :
If a system can represent knowledge symbolically, and ground those symbols in an environment, then it has access to a vast range of data from that environment. The system described in this paper acts in a simple virtual world. It is implemented solely in fatiguing Leaky Integrate and Fire neurons; views the environment; processes natural language commands; plans; and acts. Visual representations are labeled, using a Hebbian learning rule, thus gaining associations with symbols. The labelling is done using simultaneous presentation of the label and a corresponding visual item. These grounded symbols can be useful in reference resolution. Both experiments perform perfectly on all tests.
Keywords :
Hebbian learning; natural language processing; virtual reality; Hebbian learning rule; fLIF neuron; labelling; natural language command; pronoun resolution; symbol grounding problem; virtual world; visual item; visual representation; Biological system modeling; Content addressable storage; Equations; Fatigue; Fires; Grounding; Hebbian theory; Labeling; Natural languages; Neurons;
Conference_Titel :
Machine Learning and Applications, 2009. ICMLA '09. International Conference on
Conference_Location :
Miami Beach, FL
Print_ISBN :
978-0-7695-3926-3
DOI :
10.1109/ICMLA.2009.97