Adaptive Resonance Theory: How a brain learns to consciously attend, learn, and recognize a changing world

Grossberg, Stephen

doi:10.1016/j.neunet.2012.09.017

Cited by 427 publications

(329 citation statements)

References 313 publications

Supporting

Mentioning

315

Contrasting

Unclassified

Order By: Relevance

“…These findings fit neatly with and support current conceptual and computational models of psychotic symptoms (8)(9)(10)(11)(12). For instance, it has been hypothesized that a single core disturbance relating to the balance between bottom-up and top-down processing can explain both the hallucinatory experiences and the bizarre delusional beliefs of psychotic patients (8,11).…”

Section: Discussionsupporting

confidence: 83%

“…Conceptual and computational models of psychosis have hypothesized that an imbalance in the combination of bottom-up sensory evidence and top-down prior knowledge is at the core of this altered state of mind (8)(9)(10)(11)(12). According to such models, at the perceptual level, an undue reliance on prior knowledge in perception may lead to the emergence of aberrant perceptions such as hallucinations.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Shift toward prior knowledge confers a perceptual advantage in early psychosis and psychosis-prone healthy individuals

Teufel

Subramaniam

Dobler

et al. 2015

Proc. Natl. Acad. Sci. U.S.A.

236

240

View full text Add to dashboard Cite

Many neuropsychiatric illnesses are associated with psychosis, i.e., hallucinations (perceptions in the absence of causative stimuli) and delusions (irrational, often bizarre beliefs). Current models of brain function view perception as a combination of two distinct sources of information: bottom-up sensory input and top-down influences from prior knowledge. This framework may explain hallucinations and delusions. Here, we characterized the balance between visual bottom-up and top-down processing in people with early psychosis (study 1) and in psychosis-prone, healthy individuals (study 2) to elucidate the mechanisms that might contribute to the emergence of psychotic experiences. Through a specialized mental-health service, we identified unmedicated individuals who experience early psychotic symptoms but fall below the threshold for a categorical diagnosis. We observed that, in early psychosis, there was a shift in information processing favoring prior knowledge over incoming sensory evidence. In the complementary study, we capitalized on subtle variations in perception and belief in the general population that exhibit graded similarity with psychotic experiences (schizotypy). We observed that the degree of psychosis proneness in healthy individuals, and, specifically, the presence of subtle perceptual alterations, is also associated with stronger reliance on prior knowledge. Although, in the current experimental studies, this shift conferred a performance benefit, under most natural viewing situations, it may provoke anomalous perceptual experiences. Overall, we show that early psychosis and psychosis proneness both entail a basic shift in visual information processing, favoring prior knowledge over incoming sensory evidence. The studies provide complementary insights to a mechanism by which psychotic symptoms may emerge.visual perception | psychosis | top-down processing | predictive coding | schizophrenia

show abstract

Section: Discussionsupporting

confidence: 83%

mentioning

confidence: 99%

Shift toward prior knowledge confers a perceptual advantage in early psychosis and psychosis-prone healthy individuals

Teufel

Subramaniam

Dobler

et al. 2015

Proc. Natl. Acad. Sci. U.S.A.

236

240

View full text Add to dashboard Cite

show abstract

“…Adaptive Resonance Theory (ART) is a theory about how the brain autonomously learns to categorize, recognize, and predict objects and events in a dynamic environment [9]. It explains how a human brain acts as a self-organizing system that can rapidly learn huge amounts of data in real time from a changing world but still conduct it in a stable manner without catastrophically forgetting previously learnt knowledge.…”

Section: Principles Of Adaptive Resonance Theorymentioning

confidence: 99%

Dynamic and Incremental Exploration Strategy in Fusion Adaptive Resonance Theory for Online Reinforcement Learning

Subagdja

2016

Jurnal Ilmu Komputer dan Informasi

View full text Add to dashboard Cite

One of the fundamental challenges in reinforcement learning is to setup a proper balance between exploration and exploitation to obtain the maximum cummulative reward in the long run. Most protocols for exploration bound the overall values to a convergent level of performance. If new knowledge is inserted or the environment is suddenly changed, the issue becomes more intricate as the exploration must compromise the pre-existing knowledge. This paper presents a type of multi-channel adaptive resonance theory (ART) neural network model called fusion ART which serves as a fuzzy approximator for reinforcement learning with inherent features that can regulate the exploration strategy. This intrinsic regulation is driven by the condition of the knowledge learnt so far by the agent. The model offers a stable but incremental reinforcement learning that can involve prior rules as bootstrap knowledge for guiding the agent to select the right action. Experiments in obstacle avoidance and navigation tasks demonstrate that in the configuration of learning wherein the agent learns from scratch, the inherent exploration model in fusion ART model is comparable to the basic E-greedy policy. On the other hand, the model is demonstrated to deal with prior knowledge and strike a balance between exploration and exploitation. Keywords: Reinforcement Learning, Exploration Strategy, Adaptive Resonance Theory AbstrakSalah satu permasalahan mendasar dari Reinforcement Learning adalah mengatur keseimbangan antara eksplorasi dan eksploitasi untuk mendapatkan ganjaran (reward) maksimal secara kumulatif dalam jangka waktu yang lama. Ketika pengetahuan awal diikutsertakan, masalah muncul karena eksplorasi yang dilakukan harus dikompromikan dengan pengetahuan sebelumnya yang telah dipelajari. Makalah ini menampilkan salah satu jenis jaringan saraf tiruan adaptive resonance theory (ART) berkanal ganda yang dikenal juga dengan sebutan fusion ART yang juga merupakan aproksimator Fuzzy untuk reinforcement learning dengan kemampuan meregulasi strategi eksplorasi sebagai sifat dasarnya. Model ini menawarkan proses pembelajaran yang stabil tetapi inkremental serta mampu melibatkan pengetahuan awal yang memilih aksi yang benar. Eksperimen menggunakan navigasi dan menghindari rintangan sebagai domain masalah menunjukkan bahwa konfigurasi pembelajaran menggunakan sifat dasar untuk meregulasi eksplorasi sebanding dengan metoda umum yang menggunakan aturan Egreedy. Di lain pihak, model yang diusulkan ini juga menunjukkan kemampuan dalam menggunakan pengetahuan awal serta mencapai keseimbangan dalam eksplorasi dan eksploitasi pengetahuan.

show abstract

“…To overcome this issue, some unsupervised neural networks have been developed, including self-organizing competitive neural networks, self-organizing feature map neural networks, and adaptive resonance theory networks. They are all used for implementing pattern recognition without training samples [16] to [18]. Regarding this matter, an adaptive resonance theory (ART) neural network can not only recognize objects in a way similar to a brain learning autonomously, but also can solve the plasticity-stability dilemma [18].…”

Section: Introductionmentioning

confidence: 99%

“…They are all used for implementing pattern recognition without training samples [16] to [18]. Regarding this matter, an adaptive resonance theory (ART) neural network can not only recognize objects in a way similar to a brain learning autonomously, but also can solve the plasticity-stability dilemma [18]. Its algorithm can accept new input patterns adaptively without modifying the trained neural network and/or increasing memory capacity with the species of samples.…”

Section: Introductionmentioning

confidence: 99%

Crack Fault Detection for a Gearbox Using Discrete Wavelet Transform and an Adaptive Resonance Theory Neural Network

Liu

et al. 2015

SV-JME

View full text Add to dashboard Cite

show abstract

Adaptive Resonance Theory: How a brain learns to consciously attend, learn, and recognize a changing world

Cited by 427 publications

References 313 publications

Shift toward prior knowledge confers a perceptual advantage in early psychosis and psychosis-prone healthy individuals

Shift toward prior knowledge confers a perceptual advantage in early psychosis and psychosis-prone healthy individuals

Dynamic and Incremental Exploration Strategy in Fusion Adaptive Resonance Theory for Online Reinforcement Learning

Crack Fault Detection for a Gearbox Using Discrete Wavelet Transform and an Adaptive Resonance Theory Neural Network

Contact Info

Product

Resources

About