Filters








62,284 Hits in 3.4 sec

Learning Perceptual Inference by Contrasting [article]

Chi Zhang, Baoxiong Jia, Feng Gao, Yixin Zhu, Hongjing Lu, Song-Chun Zhu
2019 arXiv   pre-print
Combining all the elements, we propose the Contrastive Perceptual Inference network (CoPINet) and empirically demonstrate that CoPINet sets the new state-of-the-art for permutation-invariant models on  ...  Inspired by cognitive studies, we equip our model with a simple inference module that is jointly trained with the perception backbone.  ...  Learning Perceptual Inference by Contrasting Chi Zhang?,1,4 , Baoxiong Jia?  ... 
arXiv:1912.00086v1 fatcat:invw7cwzu5asdgdhirimn4ysqa

SAPNet: Segmentation-Aware Progressive Network for Perceptual Contrastive Deraining [article]

Shen Zheng, Changjie Lu, Yuxiong Wu, Gaurav Gupta
2021 arXiv   pre-print
Furthermore, we introduce a perceptual contrastive loss (PCL) and a learned perceptual image similarity loss (LPISL) to regulate model learning.  ...  To address this issue, in this paper, we present a segmentation-aware progressive network (SAPNet) based upon contrastive learning for single image deraining.  ...  contrastive loss (PCL), dilation, learning rate decay and learned perceptual image similarity loss (LPISL).  ... 
arXiv:2111.08892v2 fatcat:giv3wx2h3vbk3mk7hh2azde3fe

The role of abstraction in non-native speech perception

Bozena Pajak, Roger Levy
2014 Journal of Phonetics  
We argue that these results support a view of perceptual reorganization as the consequence of learners' hierarchical inductive inferences about the structure of the language's sound system: infants not  ...  Specifically, we show that the knowledge of a language with short and long vowel categories leads to enhanced discrimination of non-native consonant length contrasts.  ...  This research was supported by NIH Training Grant T32-DC-000041 from the Center for Research in Language at UC San Diego to B.P. and NIH Training Grant T32-DC000035 from the Center for Language Sciences  ... 
doi:10.1016/j.wocn.2014.07.001 pmid:25197153 pmcid:PMC4153394 fatcat:alp2u74iong2bmvjbh552zrq4m

Perceptual learning as improved probabilistic inference in early sensory areas

Vikranth R Bejjanki, Jeffrey M Beck, Zhong-Lin Lu, Alexandre Pouget
2011 Nature Neuroscience  
Therefore, the key to the neural basis of perceptual learning may have less to do with how tuning curves change and more to do with how the connectivity is adjusted to improve the inference performed by  ...  Here we argue that perceptual learning might be due to improved probabilistic inference induced by changes at the sensory processing stage rather than at the decision stage (at least in the case of orientation  ... 
doi:10.1038/nn.2796 pmid:21460833 pmcid:PMC3329121 fatcat:pyzbudr37baodejtqnoxulvh4e

Hybrid Predictive Coding: Inferring, Fast and Slow [article]

Alexander Tschantz, Beren Millidge, Anil K Seth, Christopher L Buckley
2022 arXiv   pre-print
It proposes that perceptual beliefs are furnished by sequentially minimising "prediction errors" - the differences between predicted and observed data.  ...  We demonstrate that our hybrid predictive coding model combines the benefits of both amortized and iterative inference -- obtaining rapid and computationally cheap perceptual inference for familiar data  ...  In contrast, predictive coding suggests that the brain solves perception by modelling how perceptual representations z generate sensory data x, which is a fundamentally top-down process.  ... 
arXiv:2204.02169v2 fatcat:ay3micqq4bdxjf4u65edozinyq

Belief states and categorical-choice biases determine reward-based learning under perceptual uncertainty [article]

Rasmus Bruckner, Hauke R. Heekeren, Dirk Ostwald
2020 biorxiv/medrxiv   pre-print
We found that both factors influenced participants' behavior, which was similarly captured in Bayesian-inference and Q-learning models.  ...  In natural settings, learning and decision making often takes place under considerable perceptual uncertainty.  ...  ., R.B. was supported by the International Max Planck Research School LIFE, Berlin, Germany. CRediT author statement  ... 
doi:10.1101/2020.09.18.303495 fatcat:x5veamvwcfajzgzrgpobppzqwy

Choice variability and suboptimality in uncertain environments

Valentin Wyart, Etienne Koechlin
2016 Current Opinion in Behavioral Sciences  
This variability is usually hypothesized as noise at the periphery of inferential processes, namely sensory noise in perceptual tasks and stochastic exploration in reward-guided learning, or as suboptimal  ...  Making decisions under uncertainty, from perceptual judgments to reward-guided choices, requires combining multiple pieces of decision-relevant information -a cognitive process modeled as statistical inference  ...  By contrast, the intrinsic stochasticity of inference imprecisions (i.e., the 'variance' term) reflects the effective precision at which inference is performed.  ... 
doi:10.1016/j.cobeha.2016.07.003 fatcat:2f2vizehizce5dy6fgdupo5o4i

The Neural Correlates of Hierarchical Predictions for Perceptual Decisions

Veith A. Weilnhammer, Heiner Stuke, Philipp Sterzer, Katharina Schmack
2018 Journal of Neuroscience  
By inverting a Bayesian model of perceptual inference, we estimated individual hierarchical predictions, which significantly biased perceptual decisions under ambiguity.  ...  Our work fundamentally advances the mechanistic understanding of perceptual inference in the human brain.  ...  Crucially, here, we were interested in such perceptual expectations or priors that are formed by associative learning; that is, the subjects' continuously updated inference on the probabilistic coupling  ... 
doi:10.1523/jneurosci.2901-17.2018 pmid:29712780 pmcid:PMC6596123 fatcat:4qmdnehowra4xp4dpndrauc5wm

A Philosophical Analysis of the Updating Rule in a Bayesian Perceptual Learning Model

Yuki OZAKI
2021 Annals of the Japan Association for Philosophy of Science  
Human object perception is now widely called Bayesian inference or statistical inference, while obtaining a Bayesian quantitative model of human perceptual learning has become a primary goal for the consciousness  ...  Helmholtz's idea of perception as unconscious inference is formalized by Bayes' theorem.  ...  Introduction Bayesian models of human perceptual learning have been widely studied in re-cent times. Helmholtz's idea of perception as unconscious inference is formalized by Bayes' theorem.  ... 
doi:10.4288/jafpos.30.0_85 fatcat:esd2m5j5vza6zblrhxx6ehkywa

Electrophysiological indices reflect switches between Bayesian and heuristic strategies in perceptual learning [article]

Daniel Bennett, Karen Sasmita, Carsten Murawski, Stefan Bode
2017 bioRxiv   pre-print
These findings suggest that use of Bayesian inference in perceptual learning may depend on motivational state.  ...  We recorded electroencephalography from 23 participants performing a perceptual learning task with both monetary and a non-monetary instructive feedback conditions.  ...  As a result, learning was necessarily affected by perceptual uncertainty regarding the identity of the chosen contrast.  ... 
doi:10.1101/183665 fatcat:h7cf5xmiczey3lrld7roxcmiia

Page 800 of Psychological Abstracts Vol. 93, Issue 3 [page]

2006 Psychological Abstracts  
by the inference learning task demands in Experiment 1.  ...  —This research’s purpose was to contrast the repre- sentations resulting from learning of the same categories by either classifying instances or inferring instance features.  ... 

Delusions and the Role of Beliefs in Perceptual Inference

K. Schmack, A. Gomez-Carrillo de Castro, M. Rothkirch, M. Sekutowicz, H. Rossler, J.-D. Haynes, A. Heinz, P. Petrovic, P. Sterzer
2013 Journal of Neuroscience  
Here, we empirically validated a neurocognitive model that explains both the formation and the persistence of delusional beliefs in terms of altered perceptual inference.  ...  Delusional ideation was associated with less perceptual stability, but a stronger belief-induced bias on perception, paralleled by enhanced functional connectivity between frontal areas that encoded beliefs  ...  . • Delusions and Perceptual Inference  ... 
doi:10.1523/jneurosci.1778-13.2013 pmid:23966692 pmcid:PMC6618656 fatcat:6pgrpagbdbbsxdjymqczbdu5b4

Brain-Based Mechanisms Underlying Causal Reasoning [chapter]

Jonathan Fugelsang, Kevin N. Dunbar
2009 Neural Correlates of Thinking  
This can be contrasted with casual inference, which demands the learning of causal associations based on covariation experience.  ...  to infer basic characteristics about the objects that may be in conflict with the perceptual experience.  ... 
doi:10.1007/978-3-540-68044-4_16 fatcat:qyhk42nlwvhplkcdckxn46vdhe

Perceptual Learning: Cortical Changes When Cats Learn a New Trick

Yuka Sasaki, Joshua Gold, Takeo Watanabe
2010 Current Biology  
Upon a 'correct' response, the luminance contrast of the presented stimuli decreased.  ...  The perceptual learning experiment of Hua et al. [2]. In training, a cat had to choose the one stimulus that contained the same orientation as the pre-determined orientation.  ...  The results provide compelling evidence for changes in V1 neurons in association with perceptual learning. What can and what cannot be inferred from the results?  ... 
doi:10.1016/j.cub.2010.05.004 pmid:20619806 pmcid:PMC3815644 fatcat:omm64eaynvg7hoimcjmuyyqouu

Reinforcement of perceptual inference: reward and punishment alter conscious visual perception during binocular rivalry

Gregor Wilbertz, Joanne van Slooten, Philipp Sterzer
2014 Frontiers in Psychology  
We conclude that perceptual inference is an adaptive process that is shaped by its consequences.  ...  In two behavioral experiments, we used binocular rivalry to examine whether perceptual inference can be influenced by the association of perceptual outcomes with reward or punishment, respectively, in  ...  According to our hypothesis that perceptual inference is shaped by instrumental learning, we expected that reward should bias inference toward the associated perceptual outcome, leading to increased dominance  ... 
doi:10.3389/fpsyg.2014.01377 pmid:25520687 pmcid:PMC4253824 fatcat:rjiuvx5qxffovjijd7fd546srm
« Previous Showing results 1 — 15 out of 62,284 results