Confidence through consensus: a neural mechanism for uncertainty monitoring

Abstract

Models that integrate sensory evidence to a threshold can explain task accuracy, response times and confidence, yet it is still unclear how confidence is encoded in the brain. Classic models assume that confidence is encoded in some form of balance between the evidence integrated in favor and against the selected option. However, recent experiments that measure the sensory evidence's influence on choice and confidence contradict these classic models. We propose that the decision is taken by many loosely coupled modules each of which represent a stochastic sample of the sensory evidence integral. Confidence is then encoded in the dispersion between modules. We show that our proposal can account for the well established relations between confidence, and stimuli discriminability and reaction times, as well as the fluctuations influence on choice and confidence.

Figure 1. A schematic representation of the model.

(A) shows the decision mechanism. Sensory input of the competing alternatives is fed into the N separate modules. Each module is constructed by an ANN with two populations that have recurrent excitation and lateral inhibition, and receive the external sensory input from one of the two alternatives, and a baseline of noisy background input from other regions of the brain that are not task specific. All the populations are interconnected across modules. This interconnection is regulated by parameter IC. Each module casts a vote in favor of one option depending on the competition’s outcome. When an option is voted by more than half the modules (represented with a star), it is selected as the response. (B) shows the confidence mechanism. All modules integrate evidence and commit to a global choice at a certain time. At that time, the dispersion amongst the selected options firing rate, σ_dv is estimated, and its value is transmitted to an external layer. This layer assigns the binary confidence report randomly with a sigmoid probability that depends on the dispersion estimate.

Figure 2. How IC affects σ_dv’s ability to encode confidence.

(A,B) show the model’s accuracy (i.e. the average correct trials) and response times as a function of stimuli discriminability for several IC values. The different IC values are represented with different colors as shown in the lateral color bar. The black data points are for . It is clear that different IC values do not affect the relation between these variables. (C–E) show the average σ_dv for different IC values as a function of discriminability, average RT and average accuracy. In (C,D), square markers indicate averaged values over correct trials and crosses correspond to averaged values over incorrect trials. It is clear that σ_dv is correlated with discriminability, RT and accuracy for low IC values, and the correlation vanishes for high IC’s. It is also clear that for low discriminabilities, σ_dv is on average higher, hence confidence will be lower. In C, it is clear that error trials have higher average σ_dv for all discriminabilities, and thus will be associated with lower confidence reports. However, σ_dv’s increase in error trials does not affect the functional relation between σ_dv and RT, as is clear from (D).

Figure 3

(A,B) Schematic of the relation between the fraction of modules in the counter range, FMC, and σ_dv. The counter range is placed between λ and . When an option is selected, the median firing rate is equal to λ and the FMC is inversely related to σ_dv. (C) measures the relation between average σ_dv and average FMC for different discriminabilities and several IC values. The different IC values are represented with different colors as shown in the lateral color bar. The black data points are for . (D–F) show FMC as a function of stimuli discriminability, average RT and accuracy. It is clear that average FMC is inversely correlated to σ_dv, hence for small IC’s FMC is correlated with discriminability, RT and accuracy. However, the inverse relation with σ_dv associates large FMC to high confidence and small FMC to low confidence.

Figure 4. Asymmetric influence of sensory fluctuations to the model’s decision output.

The top panels schematically show the two stimulation protocols (SP 1 and SP 2). SP 1 has a brief positive fluctuation in favor of (A), SP 2 has the a fluctuation of opposite sign and equal strength against (B). (A) Shows the network’s accuracy for both SPs. (B) shows a single module’s mean vote time under the both SPs. (C–E) show the network’s average RT, σ_dv and FMC under both SPs.

Figure 5

(A) A trial of the luminance task. Two patches of flickering bars (updated at 25 Hz) were presented until participants made a response. Participants indicated which patch is brighter and the confidence in their decision with a single manual response. (B) Spatiotemporal profile of the luminance signal. The red vertical line represents the fixation point, and the four columns to each side indicate the luminance in time of the four bars in each patch, numbered from the fovea to the periphery. (C,D) show the subject’s decision and confidence kernels respectively.

Figure 6. Behavioral fit results.

(A) Subjects and model’s fitted decision kernels. (B) Subjects and simulations fitted accuracy grouped by confidence reports. (C) Subjects and model’s confidence kernels. In (A,C), time is measured from stimulus onset, and the shaded areas indicate standard deviation around the mean.