1. |
|
|
2. |
- Jacobsson, Henrik, et al.
(author)
-
Reducing Complexity of Rule Extraction from Prediction RNNs trough Domain Interaction
- 2003
-
Reports (other academic/artistic)abstract
- This paper presents a quantitative investigation of the differences between rule extraction through breadth first search and through sampling the states of the RNN in interaction with its domain. We show that for an RNN trained to predict symbol sequences in formal grammar domains, the breadth first search is especially inefficient for languages sharing properties with realistic real world domains. We also identify some important research issues, needed to be resolved to ensure further development in the field of rule extraction from RNNs.
|
|
3. |
- Jirenhed, Dan-Anders, et al.
(author)
-
Exploring Internal Simulation of Perception in Mobile Robots
- 2001
-
In: Lund University Cognitive Studies. ; 86, s. 107-113
-
Conference paper (peer-reviewed)abstract
- Based on a neuroscientific hypothesis, this paper explores the possibility of an ‘inner world’ based on internal simulation of perception. We present three sets of experiments with a possible minimal model, using a simulated Khepera robot controlled by a simple recurrent connectionist network. Using an evolutionary algorithm the robots are trained on increasingly complex tasks. In the first experiment, serving as a baseline, robots are simply trained to map sensory input to motor output such that they move around in an environment without collisions. In the second experiment robots are additionally trained on predicting the next time step’s sensory input. In the third experiment, finally, the robot’s own prediction replaces the actual sensory input in order to investigate its capability to act ‘blindly’, i.e. in the temporary absence of external stimuli. Although only the first two experiments give positive results, we conclude that the experimental framework presented here should turn out useful in the investigation of more complex artificial neural models.
|
|
4. |
- Montebelli, Alberto, et al.
(author)
-
The Cognitive Body : from Dynamic Modulation to Anticipation
- 2003
-
In: Anticipatory Behavior in Adaptive Learning Systems. - : Springer. - 9783540404293 ; , s. 132-151
-
Book chapter (peer-reviewed)abstract
- Starting from the situated and embodied perspective on the study of cognition as a source of inspiration, this paper programmatically outlines a path towards an experimental exploration of the role of the body in a minimal anticipatory cognitive architecture. Cognition is here conceived and synthetically analyzed as a broadly extended and distributed dynamic process emerging from the interplay between a body, a nervous system and their environment. Firstly, we show how a non-neural internal state, crucially characterized by slowly changing dynamics, can modulate the activity of a simple neurocontroller. The result, emergent from the use of a standard evolutionary robotic simulation, is a selforganized, dynamic action selection mechanism, effectively operating in a context dependent way. Secondly, we show how these characteristics can be exploited by a novel minimalist anticipatory cognitive architecture. Rather than a direct causal connection between the anticipation process and the selection of the appropriate behavior, it implements a model for dynamic anticipation that operates via bodily mediation (bodily-anticipation hypothesis). This allows the system to swiftly scale up to more complex tasks never experienced before, achieving flexible and robust behavior with minimal adaptive cost.
|
|
5. |
- Sharkey, Noel, et al.
(author)
-
Life, Mind, and Robots : The Ins and Outs of Embodied Cognition
- 2000
-
In: Hybrid Neural Systems. - Berlin, Heidelberg : Springer. - 3540673059 - 9783540673057 - 9783540464174 ; , s. 313-332
-
Conference paper (peer-reviewed)abstract
- Many believe that the major problem facing traditional arti-ficial intelligence (and the functional theory of mind) is how to connect intelligence to the outside world. Some turned to robotic functionalism and a hybrid response, that attempts to rescue symbolic functionalism by grounding the symbol system with a connectionist hook to the world. Others turned to an alternative approach, embodied cognition, that emer-ged from an older tradition in biology, ethology, and behavioural model-ling. Both approaches are contrasted here before a detailed exploration of embodiment is conducted. In particular we ask whether strong embo-diment is possible for robotics, i.e. are robot\minds" similar to animal minds, or is the role of robotics to provide a tool for scientific explora-tion, a weak embodiment? We define two types of embodiment, Loebian and Uexkullian, that express two different views of the relation between body, mind and behaviour. It is argued that strong embodiment, either Loebian or Uexkullian, is not possible for present day robotics. However, weak embodiment is still a useful way forward. © 2000 Springer-Verlag Berlin Heidelberg.
|
|
6. |
- Susi, Tarja, et al.
(author)
-
Beyond the bounds of cognition
- 2003
-
In: Proceedings of the 25th Annual Conference of the Cognitive Science Society. ; , s. 1134-1139
-
Conference paper (peer-reviewed)abstract
- One of the questions that frequently comes up in discussions of situated, embodied and distributed cognition,is where to draw the boundary between cognisers and their environment. Adams,and,Aizawa (2001) have recently formulated a critique of what they consider a “radical view of tool use”, i.e., the view of tools as part of the cognitive system. We analyse their critique and show that much of what they consider ‘radical’ turns out to be compatible with what they consider 'common sense'. Hence, we argue that much of the debate boils down to a disagreement over different uses of the term 'cognitive', whereas there is growing agreement about the central role that agent-environment interaction in general, and tool use in particular, plays in cognitive processes. We therefore suggest to drop the 'bounds of cognition' debate, and conclude by raising what we consider more important questions in the study of cognitive tool use.
|
|
7. |
- Susi, Tarja, et al.
(author)
-
Beyond the bounds of cognition
- 2003
-
In: Proceedings of the 25th Annual Conference of the Cognitive Science Society. ; , s. 1134-1139
-
Conference paper (peer-reviewed)
|
|
8. |
- Ziemke, Tom, et al.
(author)
-
Blind Adaptive Behavior Based on Internal Simulation of Perception
- 2002
-
Reports (other academic/artistic)abstract
- This paper presents experiments, based on a neuroscientific hypothesis, exploring the possibility of an 'inner world' based on internal simulation of perception rather than an explicit representational world model. First a series of initial experiments is discussed, in which recurrent neural networks were evolved to (a) control collision-free corridor following behavior in a simulated Khepera robot, and (b) predict the next time step's sensory input as accurately as possible. Attempts to let the robot act 'blindly', repeatedly using its own prediction instead of the real sensory input, were not particularly successful. This motivated the second series of experiments, on which this paper focuses. A feed-forward network was used which, as above, controlled behavior and predicted sensory input. However, weight evolution was now guided by the sole fitness criterion of successful, 'blind' corridor following behaviour, including timely turns, as above using as input only own predictions rather than real sensory input. The trained robot is in some cases actually able to move 'blindly' in a simple environment for hundreds of time steps, successfully handling several multi-step turns. Somewhat surprisingly, however, it does so based on self-generated input that is very different from the actual sensory values.
|
|
9. |
|
|
10. |
- Ziemke, Tom
(author)
-
Embodied AI as Science : Embodied Models of Cognition, or Both?
- 2004
-
In: Embodied Artificial Intelligence. - Berlin, Heidelberg : Springer. - 9783540224846 - 9783540278337 ; , s. 27-36
-
Book chapter (other academic/artistic)abstract
- This paper discusses the identity of embodied AI, i.e. it asks the question exactly what it is that makes AI research embodied. From an engineering perspective, it is fairly clear that embodied AI is about robotic, i.e. physically embodied systems. From the scientific perspective of AI as building models of natural cognition or intelligence, however, things are less clear. On the one hand embodied AI seems to be about physically embodied, i.e. robotic models of cognition. On the other hand the term lsquoembodiedrsquo seems to signify the type of intelligence modeled and/or the conception of (embodied) cognition that is underlying the modeling. In either case, it appears that embodied AI, as it currently stands, might be too narrowly conceived since each of these perspectives is addressed only partially.
|
|