Cognitive Architectures for Sensory Processing

Prı́ncipe, José C.; Chalasani, Rakesh

doi:10.1109/jproc.2014.2307023

Cited by 13 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our approach is different from the existing studies on cognitive neuroscience where the learning is considered at a neuron and brain elements (visual cortex, hypothalamus, etc.) level [10], [11]. It is also significantly different from the large body of literature on perception in a psychological context where the studies are qualitative and descriptive [1]- [4].…”

Section: Introductionmentioning

confidence: 81%

“…Associations in learning have been studied earlier from psychological point of view, e.g. in [10]. In computational intelligence, the fuzzy set theory [5] was proposed to represent mathematically the subjective preferences and claims to deal with perception.…”

Section: The Concept Of the Proposed Methodsmentioning

confidence: 99%

“…of the type of hierarchical Kalman filters type is more suitable; this will be studied in further works. For example, in [10], emotions were not considered and the study was limited to a single sensory (video) input. According to the proposed CyberMind approach, autonomous learning process maps the observable PVs which represent individual-and context/temporal-specific emotions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cybernetics of the Mind: Learning Individual's Perceptions Autonomously

Angelov

Iglesias

et al. 2017

IEEE Syst. Man Cybern. Mag.

View full text Add to dashboard Cite

In this paper, we describe an approach to computational modelling and autonomous learning of the perception of sensory inputs by individuals. A hierarchical process of summarization of raw data with heterogeneous nature is proposed. At the lower layer of the hierarchy, the raw data autonomously forms semantically meaningful concepts.Instead of clustering based on the visual or audio similarity, the concepts are being formed at the second layer of the hierarchy based on the observed physiological variables (PVs) like heartbeat, skin conductance, etc. and mapped to the emotional state of the individual. Wearable sensors were used in the experiments. Methodologically, we used the recently introduced Empirical Data Analytics (EDA) computational framework and the data partitioning method within EDA to form the data clouds (cluster-like formations with no pre-defined shape) autonomously and used AnYa type of IF-THEN fuzzy rule-based models to describe the mapping of the observable PVs to the emotional states. Multi-modal typicality distributions, which have properties like pdf and indicate the empirical likelihood distributions of the data, can be further derived without making prior restrictive assumptions traditionally required in statistical approaches. The quality of the classifier is evaluated by a confusion matrix and classification rate/precision. The experimental results are very encouraging: for this extremely complicated problem, we got 74.58% correct classification results without any pre-training.

show abstract

Section: Introductionmentioning

confidence: 81%

Section: The Concept Of the Proposed Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cybernetics of the Mind: Learning Individual's Perceptions Autonomously

Angelov

Iglesias

et al. 2017

IEEE Syst. Man Cybern. Mag.

View full text Add to dashboard Cite

show abstract

“…Hierarchical architectures have been extensively studied in the machine learning community in the last decades. One of the most recent examples is the Deep Predictive Coding Networks (DPCN) [42], a neural-inspired hierarchical generative model which is effective on modeling sensory data.…”

Section: Hierarchical Architecture On Change-point or Concept Drift D...mentioning

confidence: 99%

Concept drift detection and adaptation with hierarchical hypothesis testing

Abraham

Wang³

et al. 2019

Journal of the Franklin Institute

View full text Add to dashboard Cite

A fundamental issue for statistical classification models in a streaming environment is that the joint distribution between predictor and response variables changes over time (a phenomenon also known as concept drifts), such that their classification performance deteriorates dramatically. In this paper, we first present a hierarchical hypothesis testing (HHT) framework that can detect and also adapt to various concept drift types (e.g., recurrent or irregular, gradual or abrupt), even in the presence of imbalanced data labels. A novel concept drift detector, namely Hierarchical Linear Four Rates (HLFR), is implemented under the HHT framework thereafter. By substituting a widely-acknowledged retraining scheme with an adaptive training strategy, we further demonstrate that the concept drift adaptation capability of HLFR can be significantly boosted. The theoretical analysis on the Type-I and Type-II errors of HLFR is also performed. Experiments on both simulated and real-world datasets illustrate that our methods outperform state-of-the-art methods in terms of detection precision, detection delay as well as the adaptability across different concept drift types.

show abstract

“…where A ∈ R n×n is the state transition matrix. Sparse coding can be used to build encoders in deep learning structures for extracting invariant features from input images [14], and dynamic sparse coding may be used for building encoders in deep predictive coding networks for feature extraction from video streams [12], [15]. In [16], a semantic learning system was designed for tagging mobile images.…”

Section: Introductionmentioning

confidence: 99%

Metalearning: Sparse Variable-Structure Automata

Fekri,

Safavi,

Zadeh

et al. 2021

Preprint

View full text Add to dashboard Cite

Dimension of the encoder output (i.e., the code layer) in an autoencoder is a key hyper-parameter for representing the input data in a proper space. This dimension must be carefully selected in order to guarantee the desired reconstruction accuracy. Although overcomplete representation can address this dimension issue, the computational complexity will increase with dimension. Inspired by non-parametric methods, here, we propose a metalearning approach to increase the number of basis vectors used in dynamic sparse coding on the fly. An actor-critic algorithm is deployed to automatically choose an appropriate dimension for feature vectors regarding the required level of accuracy. The proposed method benefits from online dictionary learning and fast iterative shrinkage-thresholding algorithm (FISTA) as the optimizer in the inference phase. It aims at choosing the minimum number of bases for the overcomplete representation regarding the reconstruction error threshold. This method allows for online controlling of both the representation dimension and the reconstruction error in a dynamic framework.

show abstract

Cognitive Architectures for Sensory Processing

Cited by 13 publications

References 27 publications

Cybernetics of the Mind: Learning Individual's Perceptions Autonomously

Cybernetics of the Mind: Learning Individual's Perceptions Autonomously

Concept drift detection and adaptation with hierarchical hypothesis testing

Metalearning: Sparse Variable-Structure Automata

Contact Info

Product

Resources

About