Back to first pageBack to first page Centre for Artificial Intelligence of UNL
Browse our site
You are here:

Publication details

Go back
Publication details
Main information
Towards Encoding Background Knowledge with Temporal Extent into Neural Networks
September 2010
HanMarques2010
Neuro-symbolic integration merges background knowledge and neural networks to provide a more effective learning system. It uses the Core Method as a means to encode rules. However, this method has several drawbacks in dealing with rules that have temporal extent. First, it demands some interface with the world which buffers the input patterns so they can be represented all at once. This imposes a rigid limit on the duration of patterns and further suggests that all input vectors be the same length (…) (and) it cannot encode rules having preconditions satisfied at non-deterministic time points – an important class of rules. This paper presents novel methods for encoding such rules, thereby improves and extends the power of the state-of-the-art neuro-symbolic integration.
In proceedings
Nuno Marques, Han The Anh
Yaxin Bi, Mary-Anne Williams and
Proceedings of the 4th International Conference on Knowledge Science, Engineering and Management
LNCS
Springer
-
6291
-
-
-
-
http://www.springerlink.com/content/978-3-642-15279-5/
Export formats
Nuno Marques and Han The Anh, Towards Encoding Background Knowledge with Temporal Extent into Neural Networks, in: Yaxin Bi and Mary-Anne Williams and (eds), Proceedings of the 4th International Conference on Knowledge Science, Engineering and Management, LNCS, Springer, Vol. 6291, (http://www.springerlink.com/content/978-3-642-15279-5/), September 2010.
<a href="/people/members/view.php?code=9ac1f1682cb91b20d9fbfb8e659b0819" class="author">Nuno Marques</a> and <a href="/people/members/view.php?code=cdc7090d1f84f56c0671baa36e87bd77" class="author">Han The Anh</a>, <b>Towards Encoding Background Knowledge with Temporal Extent into Neural Networks</b>, in: Yaxin Bi and Mary-Anne Williams and (eds), <u>Proceedings of the 4th International Conference on Knowledge Science, Engineering and Management</u>, LNCS, <a href="http://www.springer.com" title="Link to external entity..." target="_blank" class="publisher">Springer</a>, Vol. 6291, (<a href="http://www.springerlink.com/content/978-3-642-15279-5/" target="_blank">url</a>), September 2010.
@inproceedings {HanMarques2010, author = {Nuno Marques and Han The Anh}, editor = {Yaxin Bi and Mary-Anne Williams and}, title = {Towards Encoding Background Knowledge with Temporal Extent into Neural Networks}, booktitle = {Proceedings of the 4th International Conference on Knowledge Science, Engineering and Management}, series = {LNCS}, publisher = {Springer}, volume = {6291}, url = {http://www.springerlink.com/content/978-3-642-15279-5/}, abstract = {Neuro-symbolic integration merges background knowledge and neural networks to provide a more effective learning system. It uses the Core Method as a means to encode rules. However, this method has several drawbacks in dealing with rules that have temporal extent. First, it demands some interface with the world which buffers the input patterns so they can be represented all at once. This imposes a rigid limit on the duration of patterns and further suggests that all input vectors be the same length (…) (and) it cannot encode rules having preconditions satisfied at non-deterministic time points – an important class of rules. This paper presents novel methods for encoding such rules, thereby improves and extends the power of the state-of-the-art neuro-symbolic integration.}, month = {September}, year = {2010}, }
Publication's urls
/publications/view.php?code=b89003aace72b2cd340ce69b8d304ed4
/publications/view.php?code=HanMarques2010
Go back
Centre for Artificial Intelligence of UNL
Departamento de Informática, FCT/UNL
Quinta da Torre 2829-516 CAPARICA - Portugal
Tel. (+351) 21 294 8536 FAX (+351) 21 294 8541

Fundacao_FCT