A Multi-channel Episodic Memory Model for Human Action Learning and Recognition

2018 ◽  
Author(s):  
Kunpei Kato ◽  
Wei Hong Chin ◽  
Yuichiro Toda ◽  
Naoyuki Kubota
Keyword(s):  
Episodic Memory ◽  
Action Learning ◽  
Human Action ◽  
Memory Model

scholarly journals The minimalist grammar of action

2012 ◽  
Vol 367 (1585) ◽  
pp. 103-117 ◽  
Author(s):  
Katerina Pastra ◽  
Yiannis Aloimonos
Keyword(s):  
Computational Models ◽  
Reference Model ◽  
Action Learning ◽  
Human Action ◽  
Human Cognition ◽  
Neural Basis ◽  
Biologically Inspired ◽  
Language Structure ◽  
Minimalist Grammar ◽  
Temporal Sequences

Language and action have been found to share a common neural basis and in particular a common ‘syntax’, an analogous hierarchical and compositional organization. While language structure analysis has led to the formulation of different grammatical formalisms and associated discriminative or generative computational models, the structure of action is still elusive and so are the related computational models. However, structuring action has important implications on action learning and generalization, in both human cognition research and computation. In this study, we present a biologically inspired generative grammar of action, which employs the structure-building operations and principles of Chomsky's Minimalist Programme as a reference model. In this grammar, action terminals combine hierarchically into temporal sequences of actions of increasing complexity; the actions are bound with the involved tools and affected objects and are governed by certain goals. We show, how the tool role and the affected-object role of an entity within an action drives the derivation of the action syntax in this grammar and controls recursion, merge and move, the latter being mechanisms that manifest themselves not only in human language, but in human action too.

scholarly journals Skeleton-Based Human Action Recognition through Third-Order Tensor Representation and Spatio-Temporal Analysis

Inventions ◽  
2019 ◽  
Vol 4 (1) ◽  
pp. 9 ◽  
Author(s):  
Panagiotis Barmpoutis ◽  
Tania Stathaki ◽  
Stephanos Camarinopoulos
Keyword(s):  
Action Recognition ◽  
Sparse Matrices ◽  
Action Learning ◽  
Human Action Recognition ◽  
Singular Values ◽  
Temporal Analysis ◽  
Human Action ◽  
Depth Sensors ◽  
Subspace Iteration ◽  
Spatio Temporal

Given the broad range of applications from video surveillance to human–computer interaction, human action learning and recognition analysis based on 3D skeleton data are currently a popular area of research. In this paper, we propose a method for action recognition using depth sensors and representing the skeleton time series sequences as higher-order sparse structure tensors to exploit the dependencies among skeleton joints and to overcome the limitations of methods that use joint coordinates as input signals. To this end, we estimate their decompositions based on randomized subspace iteration that enables the computation of singular values and vectors of large sparse matrices with high accuracy. Specifically, we attempt to extract different feature representations containing spatio-temporal complementary information and extracting the mode-n singular values with regards to the correlations of skeleton joints. Then, the extracted features are combined using discriminant correlation analysis, and a neural network is used to recognize the action patterns. The experimental results presented use three widely used action datasets and confirm the great potential of the proposed action learning and recognition method.

scholarly journals The Generalized Quantum Episodic Memory Model

2016 ◽  
Vol 41 (8) ◽  
pp. 2089-2125 ◽  
Author(s):  
Jennifer S. Trueblood ◽  
Pernille Hemmer
Keyword(s):  
Episodic Memory ◽  
Memory Model

scholarly journals Evaluative conditioning as memory-based judgment

2018 ◽  
Author(s):  
Christoph Stahl ◽  
Frederik Aust
Keyword(s):  
Episodic Memory ◽  
Future Development ◽  
Formal Model ◽  
Evaluative Conditioning ◽  
Present Approach ◽  
Process Models ◽  
Dual Process ◽  
Memory Model ◽  
Challenges And Opportunities ◽  
Attitude Learning

The article proposes a view of evaluative conditioning (EC) as resulting from judgments based on learning instances stored in memory. It is based on the formal episodic memory model MINERVA 2. Additional assumptions specify how the information retrieved from memory is used to inform specific evaluative dependent measures. The present approach goes beyond previous accounts in that it uses a well-specified formal model of episodic memory; it is however more limited in scope as it aims at explaining EC phenomena that do not involve reasoning processes. The article illustrates how the memory-based-judgment view accounts for several empirical findings in the EC literature that are often discussed as evidence for dual-process models of attitude learning. It sketches novel predictions, discusses limitations of the present approach, and identifies challenges and opportunities for its future development.

scholarly journals Evaluative Conditioning as Memory-Based Judgment

2018 ◽  
Vol 13 (3) ◽  
Author(s):  
Christoph Stahl ◽  
Frederik Aust
Keyword(s):  
Episodic Memory ◽  
Future Development ◽  
Formal Model ◽  
Evaluative Conditioning ◽  
Present Approach ◽  
Process Models ◽  
Dual Process ◽  
Memory Model ◽  
Challenges And Opportunities ◽  
Attitude Learning

The article proposes a view of evaluative conditioning (EC) as resulting from judgments based on learning instances stored in memory. It is based on the formal episodic memory model MINERVA 2. Additional assumptions specify how the information retrieved from memory is used to inform specific evaluative dependent measures. The present approach goes beyond previous accounts in that it uses a well-specified formal model of episodic memory; it is however more limited in scope as it aims to explain EC phenomena that do not involve reasoning processes. The article illustrates how the memory-based-judgment view accounts for several empirical findings in the EC literature that are often discussed as evidence for dual-process models of attitude learning. It sketches novel predictions, discusses limitations of the present approach, and identifies challenges and opportunities for its future development.

Sign in / Sign up

Export Citation Format

Share Document