Harvey, I. (1996). Untimed and misrepresented: connectionism and the computer metaphor. AISB Quarterly, 96, 20--27.  Home/Search   Document Details and Download   Summary   Related Articles   Check

.... This criticism extends not only the atomic nature of the symbolic representations of traditional AI, but also to the micro featural decomposition of the inputs to connectionist networks (Rumelhart McClelland, 1986) both of which are selected and organized in a priori manner by a human observer (Harvey, 1992). This remark is unquestionably correct but we claim that it is much less problematic than they would claim, especially in the context of connectionist networks. The sensory receptors from which the robot will gather its information about the environment are indeed chosen ahead of time by human ....

Harvey, I. (1992). Untimed and misrepresented : Connectionism and the computer metaphor. CSRP 245, University of Sussex.

....is based in part on inability to imagine how any non representational system could possibly exhibit cognitive performances. Within the dynamical approach, such systems can be not only imagined, they can be modelled and constructed (see, e.g. Beer, 1995a; Beer, 1995b; Freeman Skarda, 1990; Harvey, 1992; Husbands, Harvey Cliff, 1995; Skarda Freeman, 1987; Wheeler, 1994) 4.3 The Dynamical Hypothesis, Exposed. Summarizing these points yields the following compact formulation of the DH: For every kind of cognitive performance exhibited by a natural cognitive agent, there is some quantitative ....

Harvey, I. (1992) Untimed and misrepresented: Connectionism and the computer metaphor.

....as crucial boundaries. Thus consider the following experiment in evolutionary robotics, as performed by Harvey, Husbands, and Cliff (1994) 7 A visually guided robot was placed in a rectangular, walled, dark arena, that had 6 For other accounts with a similar flavour, see, e.g. Beer (1995) Harvey (1992), Kelso (1995) Thelen and Smith (1993) and Wheeler (1994) 7 Practitioners of evolutionary robotics use algorithms inspired by Darwinian evolution to design control systems for autonomous robots. Loosely speaking, the methodology is to set up a way of encoding robot control systems a white ....

.... X represents Y to Z since this makes representation look like a form of communication (op cit. 104) Arguments that insist that such and such an internal state cannot be a representation since it doesn t represent anything to the system itself (see, e.g. Beer, 1995; Brooks Stein, 1993; Harvey, 1992) seem to trade on this very confusion. For example, Brooks and Stein (1993, p.2) caution that the firing of a particular neuron, even if it is non accidentally associated with, say, the presence of red objects, is not thereby revealed as a representation of redness for the system itself. Instead, ....

Harvey, I. (1992). Untimed and misrepresented: Connectionism and the computer metaphor.

....published, primarily in conference proceedings, in versions more or less similar to the form they appear in here. Chapter 3 is an expansion of a paper originally jointly written with Phil Husbands (Husbands and Harvey 1992) Chapter 5 includes much that was first published as a Technical Report (Harvey 1992c) Chapter 5 includes much that was first published as a Technical Report (Harvey 1992c) The work in Chapter 6 first appeared in (Harvey 1992b) The work in Chapter 7 was presented at Artificial Life 3, in 1992, and is published in (Harvey 1993a) Chapter 9 appeared in similar form in (Harvey ....

....form they appear in here. Chapter 3 is an expansion of a paper originally jointly written with Phil Husbands (Husbands and Harvey 1992) Chapter 5 includes much that was first published as a Technical Report (Harvey 1992c) Chapter 5 includes much that was first published as a Technical Report (Harvey 1992c) The work in Chapter 6 first appeared in (Harvey 1992b) The work in Chapter 7 was presented at Artificial Life 3, in 1992, and is published in (Harvey 1993a) Chapter 9 appeared in similar form in (Harvey 1992a) Applications of these ideas to robots in simulation and in reality, discussed in ....

[Article contains additional citation context not shown here]

Inman Harvey. Untimed and misrepresented: Connectionism and the computer metaphor. Technical Report CSRP 245, School of Cognitive and Computing Sciences, Univ. of Sussex, 1992.

....as external observers we can best describe this as the interaction between two dynamical systems (the agent and the rest ) coupled together through sensors and actuators. This is the dynamical systems view of cognition , dating from the early cyberneticists and reemerging in recent years [1, 5, 9]. Why is an agent in such a coupled set of dynamical systems not an input output device, and hence not performing computations to generate appropriate outputs from snapshots of its sensory inputs One could analyse the dynamical system that constitutes the agent brain and body and ....

Harvey, I.: Untimed and misrepresented: Connectionism and the computer metaphor. Cognitive Science Research Paper CSRP245, University of Sussex, 1992.

No context found.

Harvey, I. (1996). Untimed and misrepresented: connectionism and the computer metaphor. AISB Quarterly, 96, 20--27.

No context found.

Harvey, I. (1996). Untimed and misrepresented: Connectionism and the computer metaphor. Newsletter of the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB Quarterly), (96):20--27.

No context found.

I. Harvey, Untimed and misrepresented: Connectionism and the computer metaphor, Cognitive Science Research Paper CSRP 245, School of Cognitive and Computing Sciences, University of Sussex, Brighton, November 1992.

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