scholarly journals Critical evidence for the prediction error theory in associative learning

2015 ◽  
Vol 5 (1) ◽  
Author(s):  
Kanta Terao ◽  
Yukihisa Matsumoto ◽  
Makoto Mizunami
2021 ◽  
Author(s):  
Matthew S Price

Leukocyte telomere shortening is a useful biomarker of biological and cellular age that occurs at an accelerated rate in anxiety disorders and posttraumatic stress disorder (PTSD). Intriguingly, inhibitory learning — the systematic exposure to noxious stimuli that serves as a basis for many treatments for anxiety, phobia, and PTSD —reduces relative telomeres attrition rates and increases protective telomerase activity in a manner predictive of treatment response. How does inhibitory learning, a behavioral strategy, modulate organismal chromosomal activity? Inhibitory learning may induce repeated mismatch between treatment expectations, intrasession states, and eventual outcome. Nevertheless, inhibitory learning can incentivize repetition of the behavior. Thus, this paper aims to conceptualize inhibitory learning as involving a ‘prediction error feedback loop’, i.e., a series of self-perpetuating prediction errors — mismatches between expectations and outcomes — that enhances neural inhibitory regulation to effectuate extinction. Inhibitory learning is necessarily predicated upon an opposing process – excitatory learning – that may be conceptualized as a prediction error feedback loop that operates in reverse to inhibitory learning and enhances neural excitability as arousal. Together, excitatory and inhibitory learning may be elements of an associative learning prediction error feedback loop responsible for modulating neural bioenergetic rates, leading to changes in downstream cellular signaling that could explain reduced or increased rates of leukocyte telomere shortening and telomerase activity from each behavioral strategy, respectively.


2020 ◽  
Vol 32 (3) ◽  
pp. 508-514 ◽  
Author(s):  
Sagi Jaffe-Dax ◽  
Alex M. Boldin ◽  
Nathaniel D. Daw ◽  
Lauren L. Emberson

Recent findings have shown that full-term infants engage in top–down sensory prediction, and these predictions are impaired as a result of premature birth. Here, we use an associative learning model to uncover the neuroanatomical origins and computational nature of this top–down signal. Infants were exposed to a probabilistic audiovisual association. We find that both groups (full term, preterm) have a comparable stimulus-related response in sensory and frontal lobes and track prediction error in their frontal lobes. However, preterm infants differ from their full-term peers in weaker tracking of prediction error in sensory regions. We infer that top–down signals from the frontal lobe to the sensory regions carry information about prediction error. Using computational learning models and comparing neuroimaging results from full-term and preterm infants, we have uncovered the computational content of top–down signals in young infants when they are engaged in a probabilistic associative learning.


2006 ◽  
Vol 17 (1) ◽  
pp. 61-84 ◽  
Author(s):  
Andrew Smith ◽  
Ming Li ◽  
Sue Becker ◽  
Shitij Kapur

2019 ◽  
Author(s):  
Melissa J. Sharpe ◽  
Hannah M. Batchelor ◽  
Lauren E. Mueller ◽  
Chun Yun Chang ◽  
Etienne J.P. Maes ◽  
...  

AbstractDopamine neurons fire transiently in response to unexpected rewards. These neural correlates are proposed to signal the reward prediction error described in model-free reinforcement learning algorithms. This error term represents the unpredicted or ‘excess’ value of the rewarding event. In model-free reinforcement learning, this value is then stored as part of the learned value of any antecedent cues, contexts or events, making them intrinsically valuable, independent of the specific rewarding event that caused the prediction error. In support of equivalence between dopamine transients and this model-free error term, proponents cite causal optogenetic studies showing that artificially induced dopamine transients cause lasting changes in behavior. Yet none of these studies directly demonstrate the presence of cached value under conditions appropriate for associative learning. To address this gap in our knowledge, we conducted three studies where we optogenetically activated dopamine neurons while rats were learning associative relationships, both with and without reward. In each experiment, the antecedent cues failed to acquired value and instead entered into value-independent associative relationships with the other cues or rewards. These results show that dopamine transients, constrained within appropriate learning situations, support valueless associative learning.


Author(s):  
Lisa Bortolotti

In this chapter, the author argues that delusional beliefs that are elaborated—often emerging in people who attract a diagnosis of schizophrenia—have the potential for epistemic innocence. Delusional beliefs are strenuously resistant to counterevidence. However, when they are adopted to explain a puzzling experience that might compromise the agents’ capacity to interact with their environment, delusional beliefs contribute to restoring some aspects of cognitive performance by temporarily reducing anxiety. On the prediction-error theory of delusion formation, it is further believed that the adoption of a delusional explanation helps resume the processes of automated learning compromised by inaccurate prediction-error signalling. Depending on their content, some delusional beliefs may also support an attitude of curiosity and self-efficacy that is more conducive to the acquisition of new information than the previous state of uncertainty and self-doubt.


2020 ◽  
Author(s):  
Ayla Aksoy-Aksel ◽  
Andrea Gall ◽  
Anna Seewald ◽  
Francesco Ferraguti ◽  
Ingrid Ehrlich

AbstractDopaminergic signaling plays an important role in associative learning including fear and extinction learning. Dopaminergic midbrain neurons encode prediction error-like signals when threats differ from expectations. Within the amygdala, GABAergic intercalated cell (ITC) clusters receive the densest dopaminergic projections, but their physiological consequences are incompletely understood. ITCs are important for fear extinction, a function thought to be supported by activation of ventromedial cluster ITCs that inhibit central amygdala fear output. In mice, we reveal two distinct mechanisms how mesencephalic dopaminergic afferents control ITCs. Firstly, they co-release GABA to mediate rapid, direct inhibition. Secondly, dopamine suppresses inhibitory interactions between distinct ITC clusters via presynaptic D1-receptors. Early extinction training augments both, GABA co-release onto dorso-medial ITCs and dopamine-mediated suppression of dorso- to ventromedial inhibition between ITC clusters. These findings provide novel insights into dopaminergic mechanisms shaping the activity balance between distinct ITC clusters that could support their opposing roles in fear behavior.


2011 ◽  
Vol 42 (1) ◽  
pp. 161-171 ◽  
Author(s):  
T. P. Freeman ◽  
C. J. A. Morgan ◽  
T. Beesley ◽  
H. V. Curran

BackgroundAddicts show both reward processing deficits and increased salience attribution to drug cues. However, no study to date has demonstrated that salience attribution to drug cues can directly modulate inferences of reward value to non-drug cues. Associative learning depends on salience: a more salient predictor of an outcome will ‘overshadow’ a less salient predictor of the same outcome. Similarly, blocking, a demonstration that learning depends on prediction error, can be influenced by the salience of the cues employed.MethodThis study investigated whether salient drug cues might interact with neutral cues predicting financial reward in an associative learning task indexing blocking and overshadowing in satiated smokers (n=24), abstaining smokers (n=24) and non-smoking controls (n=24). Attentional bias towards drug cues, craving and expired CO were also indexed.ResultsAbstaining smokers showed drug cue induced overshadowing, attributing higher reward value to drug cues than to neutral cues that were equally predictive of reward. Overshadowing was positively correlated with expired CO levels, which, in turn, were correlated with craving in abstainers. An automatic attentional bias towards cigarette cues was found in abstainers only.ConclusionsThese findings provide the first evidence that drug cues interact with reward processing in a drug dependent population.


Sign in / Sign up

Export Citation Format

Share Document