1. What contributions have the authors mentioned in the paper "A (somewhat) new solution to the variable binding problem" ?
The authors propose a set of alternatives to temporal synchrony mechanisms that instead use short signatures.
read more
A (somewhat) new solution to the variable binding problem
TL;DR: This work proposes a set of alternatives to temporal synchrony mechanisms that instead use short signatures, which serves two functions: it allows us to explore an additional biologically plausible alternative, and it allows to extend and improve the capabilities of these models.
read more
Abstract: To perform automatic, unconscious inference, the human brain must solve the binding problem by correctly grouping properties with objects. Temporal binding models like SHRUTI already suggest much of how this might be done in a connectionist and localist way by using temporal synchrony. We propose a set of alternatives to temporal synchrony mechanisms that instead use short signatures. This serves two functions: it allows us to explore an additional biologically plausible alternative, and it allows us to extend and improve the capabilities of these models. These extensions model the human ability to both perform unification and handle multiple instantiations of logical terms. To verify our model's feasibility, we simulate it with a computer system modeling simple, neuron-like computations.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Most frequently asked questions
Figures
Figure 1: A predicate that represents working-memory “own” relationships, connected to a fact representing long-term knowledge of “John owns book 117” 
Figure 2: Detail of a mediator that implies its consequent when its antecedents match 
Figure 5: Details of the Predicate Input Structure 
Figure 3: The fluent binder: the fluent registers are dynamically linked to objects in the ontology; the mediators’ roles are linked to the fluent binder in order to request fluent allocation; and the fluent binder keeps track of the current phase of the ontology and broadcasts this to facts as needed 
Figure 4: Overview of inference with multiple clusters 
Table 1: Subtasks and Possible Solutions
Citations
The neural binding problem(s)
TL;DR: This review discusses the current state of work on General Coordination, Visual Feature-Binding, Variable Binding, and the SubjectiveUnity of Perception.
159
Best-fit constructional analysis
Jerome A. Feldman,John Bryant +1 more
- 01 Jan 2008
TL;DR: This dissertation describes a process called best-fit constructional analysis and the associated implementation called the Constructional Analyzer, which takes an utterance as input and performs deep semantic analysis, mapping the utterance onto its most likely interpretation.
53
•Journal Article
Marker-passing inference in the scone knowledge-base system
TL;DR: The Scone knowledge-base system as discussed by the authors implements search and inference operations using a set of marker-passing algorithms, originally designed for a massively parallel hardware architecture but now implemented completely in software.
26
A dynamic binding mechanism for retrieving and unifying complex predicate-logic knowledge
Gadi Pinkas,Priscila M. V. Lima,Shimon Cohen +2 more
- 11 Sep 2012
TL;DR: It is shown how to encode, retrieve and process complex structures equivalent to First-Order Logic (FOL) formulae, with Artificial Neural Networks (ANNs) designed for energy-minimization.
10
References
•Journal Article
The magical number seven, plus or minus two: some limits on our capacity for processing information
TL;DR: The theory of information as discussed by the authors provides a yardstick for calibrating our stimulus materials and for measuring the performance of our subjects and provides a quantitative way of getting at some of these questions.
23.5K
•Book
The magical number seven plus or minus two: some limits on our capacity for processing information
George A. Miller
- 01 Jan 1956
TL;DR: The theory provides us with a yardstick for calibrating the authors' stimulus materials and for measuring the performance of their subjects, and the concepts and measures provided by the theory provide a quantitative way of getting at some of these questions.
The magical number 4 in short-term memory: a reconsideration of mental storage capacity.
TL;DR: A wide variety of data on capacity limits suggesting that the smaller capacity limit in short-term memory tasks is real is brought together and a capacity limit for the focus of attention is proposed.
Gorillas in our midst: sustained inattentional blindness for dynamic events.
TL;DR: A new study builds on classic studies of divided visual attention to examine inattentional blindness for complex objects and events in dynamic scenes and suggests that the likelihood of noticing an unexpected object depends on the similarity of that object to other objects in the display and on how difficult the priming monitoring task is.