The Experts below are selected from a list of 255 Experts worldwide ranked by ideXlab platform
Setsuo Ohsuga - One of the best experts on this subject based on the ideXlab platform.
-
PRICAI - The gap between Symbol and non-Symbol Processing: an attempt to represent a database by predicate formulae
2000Co-Authors: Setsuo OhsugaAbstract:The gap between Symbol Processing and non-Symbol Processing is investigated. Predicate logic and neural network were selected as the typical Symbol and non-Symbol Processing respectively. An intermediate form was introduced to represent both of them in the same framework. Using this intermediate form the characteristics of these two methods of representation and Processing are analyzed and compared. Then the syntax of predicate logic is expanded in order to reduce this gap. A way of applying this extended logic to database in order to represent it in a few predicate formulae is discussed.
-
the gap between Symbol and non Symbol Processing an attempt to represent a database by predicate formulae
Pacific Rim International Conference on Artificial Intelligence, 2000Co-Authors: Setsuo OhsugaAbstract:The gap between Symbol Processing and non-Symbol Processing is investigated. Predicate logic and neural network were selected as the typical Symbol and non-Symbol Processing respectively. An intermediate form was introduced to represent both of them in the same framework. Using this intermediate form the characteristics of these two methods of representation and Processing are analyzed and compared. Then the syntax of predicate logic is expanded in order to reduce this gap. A way of applying this extended logic to database in order to represent it in a few predicate formulae is discussed.
-
The Gap between Symbol and Non-Symbol Processing
PRICAI 2000 Topics in Artificial Intelligence, 2000Co-Authors: Setsuo OhsugaAbstract:The gap between Symbol Processing and non-Symbol Processing is investigated. Predicate logic and neural network were selected as the typical Symbol and non-Symbol Processing respectively. An intermediate form was introduced to represent both of them in the same framework. Using this intermediate form the characteristics of these two methods of representation and Processing are analyzed and compared. Then the syntax of predicate logic is expanded in order to reduce this gap. A way of applying this extended logic to database in order to represent it in a few predicate formulae is discussed.
-
Symbol Processing by non Symbol processor
Pacific Rim International Conference on Artificial Intelligence, 1996Co-Authors: Setsuo OhsugaAbstract:A way of Processing Symbolic information by non-Symbol processor is discussed Current computer is designed to process only Symbolic information. The first objective of this paper is to discuss that some information is lost by the use of Symbolic expression in compensation of its simplicity and this lost part of information often plays an important role in the real world. Some concepts, the detail of which could not be described well in Symbolic language, have been identified and given names such as intuition, emotion, etc. But these concepts have been left out of scientific research because of the lack of scientific method to study them. For most of the existing scientific areas have been developed depending upon Symbolic knowledge. The second objective of this paper is therefore to find a cue for enabling this study by developing a method to process nonSymbolic information together with Symbolic information in the same system.
-
PRICAI - Symbol Processing by Non-Symbol Processor
Lecture Notes in Computer Science, 1996Co-Authors: Setsuo OhsugaAbstract:A way of Processing Symbolic information by non-Symbol processor is discussed Current computer is designed to process only Symbolic information. The first objective of this paper is to discuss that some information is lost by the use of Symbolic expression in compensation of its simplicity and this lost part of information often plays an important role in the real world. Some concepts, the detail of which could not be described well in Symbolic language, have been identified and given names such as intuition, emotion, etc. But these concepts have been left out of scientific research because of the lack of scientific method to study them. For most of the existing scientific areas have been developed depending upon Symbolic knowledge. The second objective of this paper is therefore to find a cue for enabling this study by developing a method to process nonSymbolic information together with Symbolic information in the same system.
Alexander Klippel - One of the best experts on this subject based on the ideXlab platform.
-
Spatial Symbol systems and spatial cognition: A computer science perspective on perception-based Symbol Processing
Behavioral and Brain Sciences, 1999Co-Authors: Christian Freksa, Thomas Barkowsky, Alexander KlippelAbstract:People often solve spatially presented cognitive problems more easily than their nonspatial counterparts. We explain this phenomenon by characterizing space as an inter-modality that provides common structure to different specific perceptual modalities. The usefulness of spatial structure for knowledge Processing on different levels of granularity and for interaction between internal and external processes is described. Map representations are discussed as examples in which the usefulness of spatially organized Symbols is particularly evident. External representations and processes can enhance internal representations and processes effectively when the same structures and principles can be implicitly assumed.
Barry L. Kalman - One of the best experts on this subject based on the ideXlab platform.
-
Hybrid Neural Systems - Holistic Symbol Processing and the Sequential RAAM: An Evalutation
Lecture Notes in Computer Science, 2000Co-Authors: James A. Hammerton, Barry L. KalmanAbstract:In recent years connectionist researchers have demonstrated many examples of holistic Symbol Processing, where Symbolic structures are operated upon as a whole by a neural network, by using a connectionist compositional representation of the structures. In this paper the ability of the Sequential RAAM (SRAAM) to generate representations that support holistic Symbol Processing is evaluated by attempting to perform Chalmers’ syntactic transformations using it. It is found that the SRAAM requires a much larger hidden layer for this task than the RAAM and that it tends to cluster its hidden layer states close together, leading to a representation that is fragile to noise. The lessons for connectionism and holistic Symbol Processing are discussed and possible methods for improving the SRAAM’s performance suggested.
Jonathan D. Cohen - One of the best experts on this subject based on the ideXlab platform.
-
Emergent Symbols through Binding in External Memory
arXiv: Artificial Intelligence, 2020Co-Authors: Taylor W. Webb, Ishan Sinha, Jonathan D. CohenAbstract:A key aspect of human intelligence is the ability to infer abstract rules directly from high-dimensional sensory data, and to do so given only a limited amount of training experience. Deep neural network algorithms have proven to be a powerful tool for learning directly from high-dimensional data, but currently lack this capacity for data-efficient induction of abstract rules, leading some to argue that Symbol-Processing mechanisms will be necessary to account for this capacity. In this work, we take a step toward bridging this gap by introducing the Emergent Symbol Binding Network (ESBN), a recurrent network augmented with an external memory that enables a form of variable-binding and indirection. This binding mechanism allows Symbol-like representations to emerge through the learning process without the need to explicitly incorporate Symbol-Processing machinery, enabling the ESBN to learn rules in a manner that is abstracted away from the particular entities to which those rules apply. Across a series of tasks, we show that this architecture displays nearly perfect generalization of learned rules to novel entities given only a limited number of training examples, and outperforms a number of other competitive neural network architectures.
-
A Memory-Augmented Neural Network Model of Abstract Rule Learning.
arXiv: Artificial Intelligence, 2020Co-Authors: Ishan Sinha, Taylor W. Webb, Jonathan D. CohenAbstract:Human intelligence is characterized by a remarkable ability to infer abstract rules from experience and apply these rules to novel domains. As such, designing neural network algorithms with this capacity is an important step toward the development of deep learning systems with more human-like intelligence. However, doing so is a major outstanding challenge, one that some argue will require neural networks to use explicit Symbol-Processing mechanisms. In this work, we focus on neural networks' capacity for arbitrary role-filler binding, the ability to associate abstract "roles" to context-specific "fillers," which many have argued is an important mechanism underlying the ability to learn and apply rules abstractly. Using a simplified version of Raven's Progressive Matrices, a hallmark test of human intelligence, we introduce a sequential formulation of a visual problem-solving task that requires this form of binding. Further, we introduce the Emergent Symbol Binding Network (ESBN), a recurrent neural network model that learns to use an external memory as a binding mechanism. This mechanism enables Symbol-like variable representations to emerge through the ESBN's training process without the need for explicit Symbol-Processing machinery. We empirically demonstrate that the ESBN successfully learns the underlying abstract rule structure of our task and perfectly generalizes this rule structure to novel fillers.
-
Indirection and Symbol-like Processing in the prefrontal cortex and basal ganglia
Proceedings of the National Academy of Sciences of the United States of America, 2013Co-Authors: Trent Kriete, David C. Noelle, Jonathan D. Cohen, Randall C. O'reillyAbstract:The ability to flexibly, rapidly, and accurately perform novel tasks is a hallmark of human behavior. In our everyday lives we are often faced with arbitrary instructions that we must understand and follow, and we are able to do so with remarkable ease. It has frequently been argued that this ability relies on Symbol Processing, which depends critically on the ability to represent variables and bind them to arbitrary values. Whereas Symbol Processing is a fundamental feature of all computer systems, it remains a mystery whether and how this ability is carried out by the brain. Here, we provide an example of how the structure and functioning of the prefrontal cortex/basal ganglia working memory system can support variable binding, through a form of indirection (akin to a pointer in computer science). We show how indirection enables the system to flexibly generalize its behavior substantially beyond its direct experience (i.e., systematicity). We argue that this provides a biologically plausible mechanism that approximates a key component of Symbol Processing, exhibiting both the flexibility, but also some of the limitations, that are associated with this ability in humans.
Christian Freksa - One of the best experts on this subject based on the ideXlab platform.
-
Spatial Symbol systems and spatial cognition: A computer science perspective on perception-based Symbol Processing
Behavioral and Brain Sciences, 1999Co-Authors: Christian Freksa, Thomas Barkowsky, Alexander KlippelAbstract:People often solve spatially presented cognitive problems more easily than their nonspatial counterparts. We explain this phenomenon by characterizing space as an inter-modality that provides common structure to different specific perceptual modalities. The usefulness of spatial structure for knowledge Processing on different levels of granularity and for interaction between internal and external processes is described. Map representations are discussed as examples in which the usefulness of spatially organized Symbols is particularly evident. External representations and processes can enhance internal representations and processes effectively when the same structures and principles can be implicitly assumed.
