Towards reasoning based representations: Deep Consistence Seeking Machine

Lörincz, András; Csákvári, Máté; Fóthi, Ábel; Milacski, Zoltán Ádám; Sárkány, András; Tősér, Zoltán

doi:10.1016/j.cogsys.2017.08.004

Cited by 6 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the pre-processing procedure the steps of the episodic description were applied. Similarly to our previous works [16,17,18], for temporal segmentation we used the Group Fused LASSO [4] method to detect change-points cooccurring across the dimensions of multivariate signals. Then segments were compared with the Global Alignment Kernel (GAK) technique [6], able to compare different length segments by using time warping.…”

Section: Results: Description Of Illustrative Examplesmentioning

confidence: 99%

“…Furthermore, the driver may train the system for personal use if their behavior is monitored. See for instance the examples provided in [16], which include talking to a person in the car or over the phone, or drinking. In this case the driver can train the system conditioned on their behavior, by providing feedback if the warning signal is not needed.…”

Section: Discussionmentioning

confidence: 99%

“…In this paper we build upon our previous works. In [16] we presented a framework of cognition that combines deep neural networks (DNNs) with facts and rules to correct recognition errors and obtain consistent and deterministic event descriptions. In our follow-up work [17], based on motivations from neuroscience and psychology, we introduced an architecture called declarative description that combines DNNs and unsupervised machine learning techniques to provide explanation and reasoning about ongoing situations in a spatio-temporal context.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cognitive Modeling Approach for Dealing with Challenges in Cyber-Physical Systems

Rill

Lörincz

2019

Studia UBB Informatica

Self Cite

View full text Add to dashboard Cite

In this paper, inspired by our previous works, we propose an architecture for the design and realization of cyber-physical systems (CPS) that considers the spatio-temporal context of events, promotes anomaly detection, facilitates efficient human-computer interaction and is capable of discovering novel human and/or machine knowledge. We view deep neural networks as smart sensors and sensory data from the environment represents the semantic and episodic input to a consistency seeking component of the cyber-space. Starting from a knowledge base infused with a deterministic world assumption, this module can detect anomalies and correct estimation errors by combining the outputs of multiple sensors. We also exploit an episodic description of ongoing situations by integrating temporal segmentation with kernel and low-dimensional embedding based methods. We demonstrate parts of the architecture through illustrative examples on our self-collected driving dataset. Our framework can be related to cognitive science foundations and may facilitate reliable functioning of CPS through integrating traditional AI and deep learning methods with deterministic models and reasoning tools. We expect that such knowledge base and cognition driven approaches of joining deep neural networks will be adopted in complex CPS. This looks like a scalable, and beneficial match between human knowledge and the exploding deep learning technologies.

show abstract

Section: Results: Description Of Illustrative Examplesmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cognitive Modeling Approach for Dealing with Challenges in Cyber-Physical Systems

Rill

Lörincz

2019

Studia UBB Informatica

Self Cite

View full text Add to dashboard Cite

show abstract

“…In turn, the presence or absence of components or the quality of the learned components does influence cognitive strategy via the feedforward estimation of the available sparse components (Sprechmann, Bronstein, and Sapiro, 2015) and (Lőrincz et al, 2016). In addition, if holistic, i.e., more complex, recognition is impaired, then component-based recognition followed by inferences may become typical that helps to train the holistic learning process as illustrated in (Lőrincz et al, 2018).…”

Section: Weak Central Coherence Theorymentioning

confidence: 99%

“…Component learning enables the 'recognition-bycomponents' process (Biederman, 1987), which is less fragile (but slower) than holistic recognition; see, e.g., the examples in (Lőrincz et al, 2018). An impaired component system forms a bottleneck for the flexible responses required in diverse situations in two ways: (i) practiced solutions are rigid but safe, whereas (ii) novel combinations are hard to develop due to imprecise component formation.…”

Section: Cognitive Dysfunctionmentioning

confidence: 99%

Colors of Autism Spectrum: A Single Paradigm Explains the Heterogeneity in Autism Spectrum Disorder

Lörincz¹

2018

Preprint

View full text Add to dashboard Cite

We propose a theory of ASD as a condition of comorbid cognitive impairments that corrupt the learning, encoding, and manipulation of episodic and semantic memories. We consider (i) episodic and semantic memory functions of the entorhinal-hippocampal complex, (ii) constraints on the transfer and encoding of these memory components into neocortical areas, and (iii) the demands of cognitively manipulating memories in distributed computations being necessary for goaloriented interactions. In ASD, learning and cognitive challenges manifest in diverse ways but especially in high-complexity-model predictive control tasks with latent variables. ASD impairments in social interactions represent a prototypical example. Social interactions are at the high end of complexity and require processes (i) -(iii) to work in a concerted fashion due to the need for the learning and estimation of many, sometimes latent, parameters, including emotions, intention, physical and mental capabilities as well as the predictive modeling of these parameters for decision making and timed-action series. We put forth the idea that autism is a result of an arbitrary combination of otherwise not prominent corruptions in processes (i)-(iii). Together, these corruptions may severely impair intelligence and slow down learning, especially in highcomplexity learning tasks. Over time, slow learning may spare the spontaneous learning-by-doing method -namely, repetitive behavioral patterns, whereas behavioral failures related to complex tasks can restrict interest in such task, thus inducing a fear of novelty; conversely, the fear of novelty restricts interest and can slow learning down. We embed our thoughts into a predictive autoencoding, goal-oriented model of a deterministic world. We compare this model to others, such as the noisy brain model, the Bayesian prior theory, the mirror neuron theory and the weak central coherence theory. We argue that the predictive autoencoder model of the deterministic world harmonizes with these other models and embraces them in a straightforward way. AUTHOR SUMMARYThe core of our arguments is based on the autoencoder model of the entorhinal-hippocampal complex and its role in forming declarative memories. We argue that social behavior and language usage are highly complex cognitive tasks involving the encoding, learning, and manipulation of declarative memories with latent variables. All these processes can be corrupted in many ways. Corruptions may manifest as epilepsy, schizophrenia, attention deficit, and depression, among other disorders. However, if these symptoms are weak but co-occur, then the most strongly affected behavioral feature is the ability to solve complex cognitive tasks. This condition can be brought about by diverse combinations of impairments that sum up in corrupted social behavior the most.

show abstract

Understanding and explaining convolutional neural networks based on inverse approach

kwon

Koo²,

Cho³

2023

Cognitive Systems Research

View full text Add to dashboard Cite

Towards reasoning based representations: Deep Consistence Seeking Machine

Cited by 6 publications

References 22 publications

Cognitive Modeling Approach for Dealing with Challenges in Cyber-Physical Systems

Cognitive Modeling Approach for Dealing with Challenges in Cyber-Physical Systems

Colors of Autism Spectrum: A Single Paradigm Explains the Heterogeneity in Autism Spectrum Disorder

Understanding and explaining convolutional neural networks based on inverse approach

Contact Info

Product

Resources

About

Towards reasoning based representations: Deep Consistence Seeking Machine

Cited by 6 publications

References 22 publications

Cognitive Modeling Approach for Dealing with Challenges in Cyber-Physical Systems

Cognitive Modeling Approach for Dealing with Challenges in Cyber-Physical Systems

Colors of Autism Spectrum: A Single Paradigm Explains the Heterogeneity&nbsp;in Autism Spectrum Disorder

Understanding and explaining convolutional neural networks based on inverse approach

Contact Info

Product

Resources

About

Colors of Autism Spectrum: A Single Paradigm Explains the Heterogeneity in Autism Spectrum Disorder