New Ideas for Brain Modelling 7

• URL: http://arxiv.org/abs/2011.02223v2
• Date: Sat, 15 May 2021 23:43:49 GMT
• Title: New Ideas for Brain Modelling 7
• Authors: Kieran Greer
• Abstract summary: This paper updates the cognitive model by creating two systems and unifying them over the same structure. It represents information at the semantic level only, where labelled patterns are aggregated into a 'type-set-match' form.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper updates the cognitive model, firstly by creating two systems and then unifying them over the same structure. It represents information at the semantic level only, where labelled patterns are aggregated into a 'type-set-match' form. It is described that the aggregations can be used to match across regions with potentially different functionality and therefore give the structure a required amount of flexibility. The theory is that if the model stores information which can be transposed in consistent ways, then that will result in knowledge and some level of intelligence. As part of the design, patterns have to become distinct and that is realised by unique paths through shared aggregated structures. An ensemble-hierarchy relation also helps to define uniqueness through local feedback that may even be an action potential. The earlier models are still consistent in terms of their proposed functionality, but some of the architecture boundaries have been moved to match them up more closely. After pattern optimisation and tree-like aggregations, the two main models differ only in their upper, more intelligent level. One provides a propositional logic for mutually inclusive or exclusive pattern groups and sequences, while the other provides a behaviour script that is constructed from node types. It can be seen that these two views are complimentary and would allow some control over behaviours, as well as memories, that might get selected.

Related papers

• A Recursive Bateson-Inspired Model for the Generation of Semantic Formal Concepts from Spatial Sensory Data [77.34726150561087]
  This paper presents a new symbolic-only method for the generation of hierarchical concept structures from complex sensory data. The approach is based on Bateson's notion of difference as the key to the genesis of an idea or a concept. The model is able to produce fairly rich yet human-readable conceptual representations without training.
  arXiv  Detail & Related papers  (2023-07-16T15:59:13Z)
• Prototype-based Embedding Network for Scene Graph Generation [105.97836135784794]
  Current Scene Graph Generation (SGG) methods explore contextual information to predict relationships among entity pairs. Due to the diverse visual appearance of numerous possible subject-object combinations, there is a large intra-class variation within each predicate category. Prototype-based Embedding Network (PE-Net) models entities/predicates with prototype-aligned compact and distinctive representations. PL is introduced to help PE-Net efficiently learn such entitypredicate matching, and Prototype Regularization (PR) is devised to relieve the ambiguous entity-predicate matching.
  arXiv  Detail & Related papers  (2023-03-13T13:30:59Z)
• Link Prediction with Attention Applied on Multiple Knowledge Graph Embedding Models [7.620967781722715]
  Knowledge graph embeddings map nodes into a vector space to predict new links, scoring them according to geometric criteria. No single model can learn all patterns equally well. In this paper, we combine the query representations from several models in a unified one to incorporate patterns that are independently captured by each model.
  arXiv  Detail & Related papers  (2023-02-13T10:07:26Z)
• Language Model Cascades [72.18809575261498]
  Repeated interactions at test-time with a single model, or the composition of multiple models together, further expands capabilities. Cases with control flow and dynamic structure require techniques from probabilistic programming. We formalize several existing techniques from this perspective, including scratchpads / chain of thought, verifiers, STaR, selection-inference, and tool use.
  arXiv  Detail & Related papers  (2022-07-21T07:35:18Z)
• The interplay between ranking and communities in networks [0.0]
  We present a generative model based on an interplay between community and hierarchical structures. It assumes that each node has a preference in the interaction mechanism and nodes with the same preference are more likely to interact. We demonstrate our method on synthetic and real-world data and compare performance with two standard approaches for community detection and ranking extraction.
  arXiv  Detail & Related papers  (2021-12-23T16:10:28Z)
• Hierarchical Variational Memory for Few-shot Learning Across Domains [120.87679627651153]
  We introduce a hierarchical prototype model, where each level of the prototype fetches corresponding information from the hierarchical memory. The model is endowed with the ability to flexibly rely on features at different semantic levels if the domain shift circumstances so demand. We conduct thorough ablation studies to demonstrate the effectiveness of each component in our model.
  arXiv  Detail & Related papers  (2021-12-15T15:01:29Z)
• Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones [64.75766944882389]
  We present ConE (Cone Embedding), a KG embedding model that is able to simultaneously model multiple hierarchical as well as non-hierarchical relations in a knowledge graph. In particular, ConE uses cone containment constraints in different subspaces of the hyperbolic embedding space to capture multiple heterogeneous hierarchies. Our approach yields new state-of-the-art Hits@1 of 45.3% on WN18RR and 16.1% on DDB14 (0.231 MRR)
  arXiv  Detail & Related papers  (2021-10-28T07:16:08Z)
• CoANE: Modeling Context Co-occurrence for Attributed Network Embedding [10.609715843964263]
  Attributed network embedding (ANE) is to learn low-dimensional vectors so that not only the network structure but also node attributes can be preserved. We propose a novel ANE model, Context Co-occurrence-aware Attributed Network Embedding (CoANE) The learning of context co-occurrence can capture the latent social circles of each node.
  arXiv  Detail & Related papers  (2021-06-17T04:31:02Z)
• A Generative Node-attribute Network Model for Detecting Generalized Structure [6.151348127802708]
  We propose a principle model (named GNAN) which can generate both topology information and attribute information. The new model can detect not only community structure, but also a range of other types of structure in networks. Experiments on both synthetic and real-world networks show that the new model is competitive with other state-of-the-art models.
  arXiv  Detail & Related papers  (2021-06-05T12:07:04Z)
• Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding [22.123001954919893]
  We propose an iterative framework named PRASE which is based on probabilistic reasoning and semantic embedding. The PRASE framework is compatible with different embedding-based models, and our experiments on multiple datasets have demonstrated its state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-05-12T11:27:46Z)
• Neural Production Systems [90.75211413357577]
  Visual environments are structured, consisting of distinct objects or entities. To partition images into entities, deep-learning researchers have proposed structural inductive biases. We take inspiration from cognitive science and resurrect a classic approach, which consists of a set of rule templates. This architecture achieves a flexible, dynamic flow of control and serves to factorize entity-specific and rule-based information.
  arXiv  Detail & Related papers  (2021-03-02T18:53:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.