T. J. van Gelder and L. Niklasson. On being systematically connectionist. Mind and Language, 9:288--302, 1994.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....per sentence asymptote for this corpus after exposure to about 500 sentences (Figure 4, bottom) Novel inputs; systematicity. An important characteristic of a cognitive representation scheme is its systematicity, measured by the ability to deal properly with structurally related items (see [7] for a definition and discussion) We have assessed the systematicity of the ADIOS model by splitting the corpus generated by the grammar of Figure 3 into training and test sets. After training the model on the former, we examined the representations of unseen sentences from the test set. A ....

....generated by the grammar of Figure 3 into training and test sets. After training the model on the former, we examined the representations of unseen sentences from the test set. A typical result appears in Figure 5; the general finding was of Level 3 systematicity according to the nomenclature of [7]. This example can be also understood using the concept of generating novel sentences from patterns, explained in detail below; the novel sentence (Beth is playing on Sunday) can be produced by the same pattern (#173) that accounts for the familiar sentence (the horse is playing on Thursday) that ....

[Article contains additional citation context not shown here]

T. J. van Gelder and L. Niklasson. On being systematically connectionist. Mind and Language, 9:288--302, 1994.

....the horns of the dilemma, by either claiming that Classical architecture is not needed to account for human language and concepts, or (less commonly) by denying that implementing Classical architecture renders connectionism redundant. Despite the number of such responses, conventional wisdom, as [Niklasson and van Gelder, 1994] notes, still has it that there is some fundamental limitation to connectionism as an architecture for cognition. Non connectionists are unconvinced by the many replies to Fodor and Pylyshyn, and even many connectionists are at a loss to say how Fodor and Pylyshyn s arguments can be answered, ....

Niklasson, L. and van Gelder, T. (1994). On being systematically connectionist. Mind and Language, 9:288-302.

.... Chater, 1994) In addition, since about 1990, a number of publications have described networks which achieve some degree of syntactic or semantic systematicity (cf. Chalmers, 1990; Christiansen and Chater, 1994; Elman, 1998; Hadley, 1994a, 1994b; Hadley Hayward, 1997; Hadley Cardei, 1999; Niklasson and van Gelder, 1994; Phillips, 1994) Overwhelmingly, this research on systematicity has focused on the capacity of connectionist networks to generalize the use or interpretation of terms to novel syntactic positions within sentences. However, as explained in (Hadley, 1994b and Hadley, in press) the forms of ....

Niklasson, L.F. and van Gelder, T., 1994, On being systematically connectionist. Mind and Language, 9: 288-302.

....Processing. CRG was established in 1991 and has been conducting basic research on the implications of an ANN approach to cognition (Boden Narayanan, 1993, 1994; Boden 1994, 1996; Boden Niklasson, 1995; Niklasson Boden, 1997; Niklasson, 1993, 1996; Niklasson Sharkey, 1992, 1994, 1997; Niklasson van Gelder, 1994a, 1994b) and adaptive robotics (Ziemke, 1996a, 1996b, 1996c, 1996d, 1997a, 1997b, strm Ziemke, 1997, Sharkey Ziemke, 1999) In addition to this CRG members have also applied ANN techniques to real world problems such as radar signal processing, in particular oil spill detection (in cooperation ....

.... involving practical applications of ANNs; fish stock prediction (HS IDA EA 96 102) classification of logs for automatic separation in a saw mill (HS IDA EA 96 103) and construction of a work bench for parallel implementations (HS IDA EA 97 104) CRG has also organized two prior conferences (Niklasson Boden, 1994, 1995) and hosted Europe s premier ANN conference International Conference on Artificial Neural Networks (ICANN) September 1998 (Niklasson, Boden Ziemke, 1998) Moreover, Sharkey and Ziemke organized an IEE workshop on biorobotics in February 1998. In addition, CRG members serve on the ....

Niklasson, L. F. and van Gelder, T., (1994), On Being Systematically Connectionist, Mind and Language, vol. 9., no. 3., Blackwell Publishers.

.... the connectionists argued for non concatenative subsymbolic representations that were spatially rather than syntactically structured [45] Several connectionists argued this case by building connectionist models that demonstrated systematicity of subsymbolic representation in some form or other [12, 14, 31, 32]. So far as we have stated it, the debate was one within the remit of the functional theory of mind. But the connectionists also had mathematical learning techniques that were based on abstract models of neural computation. Thus the representations and their spatial organisation could be learned ....

L. Niklasson and T. van Gelder. On being systematically connectionist. Mind and Language, 3:288--302, 1994.

.... plausible inference [5] English to Spanish translation [14] sequential parsing [47] DRAFT PAPER FOR COMMENTS 6 necessary inference [3] and the manipulation of Horn clauses [11] Much of this research continues as the Connectionists penetrate further and further into Cognitivist territory [34]. Nonetheless, the problems dealt with in cognitive tasks have been for in vacuo domains where the inputs to the nets have come from binary abstractions of the domain designed by the researchers (one of the Brooks criticisms of the abstractions in AI) The internal representations were then ....

L. Niklasson and T. van Gelder. On being systematically connectionist. Mind and Language, 3:288--302, 1994.

....to recursion. 5 There are two classes of models which may potentially provide such alternatives both of which learn to process language from experience, rather than implementing a prespecified set of symbolic rules. The first, less ambitious, class (e.g. Chalmers, 1990; Hanson Kegl, 1987; Niklasson van Gelder, 1994; Pollack, 1988, 1990; Stolcke, 1991) attempts to learn grammar from tagged sentences. Thus, the network is trained on sentences which are associated with some kind of grammatical structure and the task is to learn to assign the appropriate grammatical structure to novel sentences. This means ....

Niklasson, L. & van Gelder (1994). On being systematically connectionist. Mind and Language, 9, 288--302.

....professor s writings. If you can imagine this, then, goes the argument, this is what CCS and AI are all about: the ability to reason and be creative, within a language that can be understood, even if that language needs translating for others to understand. 1994; Christiansen and Chater, 1994; Niklasson and van Gelder, 1994). 4 But there are two types of neuroscience. On the one hand, reductionists in general accept that, even after reduction to a neuroscientific basis, mental processes do exist and can be described in their own terms. 5 This is to be contrasted with eliminative neuroscientists, who believe that ....

Niklasson, L.F. and van Gelder, T. (1994). On being systematically connectionist. Mind and Language, 9(3), 288--302.

....that such regularities are an inherent part of human cognitive activity, and thus that connectionism could not be an adequate cognitive architecture until it accounted for this phenomena. Many attempts have been made to meet this challenge (e.g. Smolensky, 1990; Christiansen and Chater, 1994; Niklasson and van Gelder, 1994), but the critics have not been satisfied (Fodor and McLaughlin, 1990; Hadley, 1994a; Hadley, 1994b) 1 Such difficulties have lead some connectionists investigating higher level cognitive activities to propose extensions to standard connectionist architectures. One such investigation developed ....

Niklasson, L.F. and van Gelder, T. (1994). On being systematically connectionist. Mind and Language, 9(3):288--302.

....structured representations or apply processes sensitive to this structure without resorting to symbolic representations. Rather than accepting the implementational role for connectionism, the validity of the premises of these claims were questioned (Goschke and Koppelberg, 1991; van Gelder and Niklasson, 1994; It is, however, generally accepted by connectionists that human thought to some degree obeys the so called compositionality and systematicity principles. Thus, much research has focused on explicitly achieving these principles in connectionist hardware, and also supplying connectionist ....

....and systematicity principles. Thus, much research has focused on explicitly achieving these principles in connectionist hardware, and also supplying connectionist explanations to them (Smolensky, 1987; Smolensky, 1990; van Gelder, 1990; Pollack, 1990; Chalmers, 1990; Niklasson and Sharkey, 1992; Niklasson and van Gelder, 1994; Phillips, 1994; The success of these connectionist counter examples was questioned by Hadley (1994a) His concern was that the success in many of them could be explained by how the training sets were constructed. He therefore provided a learning based re formulation of systematicity in the ....

[Article contains additional citation context not shown here]

Niklasson, L. and van Gelder, T. (1994). On being systematically connectionist. Mind and Language, 9(3).

....processes sensitive to this structure without resorting to symbolic representations. Rather than accepting the implementational role for connectionism, suggested by Fodor and Pylsyhyn, the validity of the premises of these claims has been questioned (Goschke and Koppelberg, 1991; van Gelder and Niklasson, 1994; Matthews, 1994) It is, however, generally accepted by connectionists that human thought to some degree obeys the socalled compositionality and systematicity principles. In addition, further evidence of systematicity in human subjects has recently been supplied by Phillips and Halford (1997) and ....

.... and Halford et al. 1998) Thus, much research has focused on explicitly achieving these principles in connectionist hardware, and also supplying connectionist explanations to them (Smolensky, 1987; Smolensky, 1990; van Gelder, 1990; Pollack, 1990; Chalmers, 1990; Niklasson and Sharkey, 1992; Niklasson and van Gelder, 1994; Phillips, 1994; Browne and Pilkington, 1994) The success of these connectionist counter examples was questioned by Hadley (1994a) His concern was that the success in many of them could be explained by how the training sets were constructed. Hadley furthered the debate by providing a ....

[Article contains additional citation context not shown here]

Niklasson, L. and van Gelder, T. (1994). On being systematically connectionist. Mind and Language, 9(3):288-302.

....processes sensitive to this structure without resorting to symbolic representations. Rather than accepting the implementational role for connectionism, suggested by Fodor and Pylsyhyn, the validity of the premises of these claims has been questioned (Goschke and Koppelberg, 1991; van Gelder and Niklasson, 1994; Matthews, 1994) It is, however, generally accepted by connectionists that human thought to some degree obeys the socalled compositionality and systematicity principles. In addition, further evidence of systematicity in human subjects has recently been supplied by Phillips and Halford (1997) and ....

.... and Halford et al. 1998) Thus, much research has focused on explicitly achieving these principles in connectionist hardware, and also supplying connectionist explanations to them (Smolensky, 1987; Smolensky, 1990; van Gelder, 1990; Pollack, 1990; Chalmers, 1990; Niklasson and Sharkey, 1992; Niklasson and van Gelder, 1994; Phillips, 1994; Browne and Pilkington, 1994) The success of these connectionist counter examples was questioned by Hadley (1994a) His concern was that the success in many of them could be explained by how the training sets were constructed. Hadley furthered the debate by providing a ....

[Article contains additional citation context not shown here]

Niklasson, L. and van Gelder, T. (1994). On being systematically connectionist. Mind and Language, 9(3):288--302.

.... the structure of the represented expression) They point out that connectionists can neither exhibit nor supply a novel explanation to these principles (cf. Fodor and McLaughlin, 1990) The validity of the premises of these claims has been questioned (Goschke and Koppelberg, 1991; van Gelder and Niklasson, 1994). However, it is generally accepted also by connectionists that human thought obeys the so called compositionality and systematicity principles. 1 Thus, much research has focused on explicitly achieving these principles in purely connectionist hardware, and also supplying a purely connectionist ....

....principles. 1 Thus, much research has focused on explicitly achieving these principles in purely connectionist hardware, and also supplying a purely connectionist explanation to them (Smolensky, 1987; van Gelder, 1990; Smolensky, 1990; Pollack, 1990; Chalmers, 1990; Niklasson and Sharkey, 1992; Niklasson and van Gelder, 1994). This paper assumes that Fodor and Pylyshyn have identified essential parts of what is required for being considered a model of the mind. However, along the lines of previous research (van Gelder, 1990; Clark, 1993; Sharkey and Jackson, 1994) it is here questioned whether these principles only ....

[Article contains additional citation context not shown here]

Niklasson, L. and van Gelder, T. (1994). On being systematically connectionist. Mind and Language, 9(3).

No context found.

Niklasson, Lars F., and van Gelder, Tim. On Being Systematically Connectionist. In Mind and Language, vol. 9., no. 3., Blackwell Publishing, Oxford, 1994.

No context found.

Niklasson, Lars and van Gelder, Tim, 1994. "On Being Systematically Connectionist." Mind and Language 9:288--302.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC