Confidence and second-order errors in cortical circuits
- URL: http://arxiv.org/abs/2309.16046v3
- Date: Tue, 26 Mar 2024 20:58:15 GMT
- Title: Confidence and second-order errors in cortical circuits
- Authors: Arno Granier, Mihai A. Petrovici, Walter Senn, Katharina A. Wilmes,
- Abstract summary: Minimization of cortical prediction errors has been considered a key computational goal of the cerebral cortex.
We derive neural dynamics that minimize prediction errors under the assumption that cortical areas must not only predict the activity in other areas but also jointly project their confidence.
- Score: 1.2492669241902092
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Minimization of cortical prediction errors has been considered a key computational goal of the cerebral cortex underlying perception, action and learning. However, it is still unclear how the cortex should form and use information about uncertainty in this process. Here, we formally derive neural dynamics that minimize prediction errors under the assumption that cortical areas must not only predict the activity in other areas and sensory streams but also jointly project their confidence (inverse expected uncertainty) in their predictions. In the resulting neuronal dynamics, the integration of bottom-up and top-down cortical streams is dynamically modulated based on confidence in accordance with the Bayesian principle. Moreover, the theory predicts the existence of cortical second-order errors, comparing confidence and actual performance. These errors are propagated through the cortical hierarchy alongside classical prediction errors and are used to learn the weights of synapses responsible for formulating confidence. We propose a detailed mapping of the theory to cortical circuitry, discuss entailed functional interpretations and provide potential directions for experimental work.
Related papers
- Confidence Regulation Neurons in Language Models [91.90337752432075]
This study investigates the mechanisms by which large language models represent and regulate uncertainty in next-token predictions.
Entropy neurons are characterized by an unusually high weight norm and influence the final layer normalization (LayerNorm) scale to effectively scale down the logits.
token frequency neurons, which we describe here for the first time, boost or suppress each token's logit proportionally to its log frequency, thereby shifting the output distribution towards or away from the unigram distribution.
arXiv Detail & Related papers (2024-06-24T01:31:03Z) - NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical
Development Patterns of Preterm Infants [73.85768093666582]
We propose an explainable geometric deep network dubbed NeuroExplainer.
NeuroExplainer is used to uncover altered infant cortical development patterns associated with preterm birth.
arXiv Detail & Related papers (2023-01-01T12:48:12Z) - Learning Uncertainty with Artificial Neural Networks for Improved
Predictive Process Monitoring [0.114219428942199]
We distinguish two types of learnable uncertainty: model uncertainty due to a lack of training data and noise-induced observational uncertainty.
Our contribution is to apply these uncertainty concepts to predictive process monitoring tasks to train uncertainty-based models to predict the remaining time and outcomes.
arXiv Detail & Related papers (2022-06-13T17:05:27Z) - Brain Cortical Functional Gradients Predict Cortical Folding Patterns
via Attention Mesh Convolution [51.333918985340425]
We develop a novel attention mesh convolution model to predict cortical gyro-sulcal segmentation maps on individual brains.
Experiments show that the prediction performance via our model outperforms other state-of-the-art models.
arXiv Detail & Related papers (2022-05-21T14:08:53Z) - Learning Theory of Mind via Dynamic Traits Attribution [59.9781556714202]
We propose a new neural ToM architecture that learns to generate a latent trait vector of an actor from the past trajectories.
This trait vector then multiplicatively modulates the prediction mechanism via a fast weights' scheme in the prediction neural network.
We empirically show that the fast weights provide a good inductive bias to model the character traits of agents and hence improves mindreading ability.
arXiv Detail & Related papers (2022-04-17T11:21:18Z) - Hybrid Predictive Coding: Inferring, Fast and Slow [62.997667081978825]
We propose a hybrid predictive coding network that combines both iterative and amortized inference in a principled manner.
We demonstrate that our model is inherently sensitive to its uncertainty and adaptively balances balances to obtain accurate beliefs using minimum computational expense.
arXiv Detail & Related papers (2022-04-05T12:52:45Z) - Uncertainty-Aware Training for Cardiac Resynchronisation Therapy
Response Prediction [3.090173647095682]
Quantifying uncertainty of a prediction is one way to provide such interpretability and promote trust.
We quantify the data (aleatoric) and model (epistemic) uncertainty of a DL model for Cardiac Resynchronisation Therapy response prediction from cardiac magnetic resonance images.
We perform a preliminary investigation of an uncertainty-aware loss function that can be used to retrain an existing DL image-based classification model to encourage confidence in correct predictions.
arXiv Detail & Related papers (2021-09-22T10:37:50Z) - Learning Uncertainty with Artificial Neural Networks for Improved
Remaining Time Prediction of Business Processes [0.15229257192293202]
This paper is the first to apply these techniques to predictive process monitoring.
We found that they contribute towards more accurate predictions and work quickly.
This leads to many interesting applications, enables an earlier adoption of prediction systems with smaller datasets and fosters a better cooperation with humans.
arXiv Detail & Related papers (2021-05-12T10:18:57Z) - Relaxing the Constraints on Predictive Coding Models [62.997667081978825]
Predictive coding is an influential theory of cortical function which posits that the principal computation the brain performs is the minimization of prediction errors.
Standard implementations of the algorithm still involve potentially neurally implausible features such as identical forward and backward weights, backward nonlinear derivatives, and 1-1 error unit connectivity.
In this paper, we show that these features are not integral to the algorithm and can be removed either directly or through learning additional sets of parameters with Hebbian update rules without noticeable harm to learning performance.
arXiv Detail & Related papers (2020-10-02T15:21:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.