Contextual effects in sensorimotor adaptation adhere to associative learning rules

Abstract

Traditional associative learning tasks focus on the formation of associations between salient events and arbitrary stimuli that predict those events. This is exemplified in cerebellar-dependent delay eyeblink conditioning, where arbitrary cues such as a tone or light act as conditioned stimuli (CSs) that predict aversive sensations at the cornea (unconditioned stimulus [US]). Here, we ask if a similar framework could be applied to another type of cerebellar-dependent sensorimotor learning - sensorimotor adaptation. Models of sensorimotor adaptation posit that the introduction of an environmental perturbation results in an error signal that is used to update an internal model of a sensorimotor map for motor planning. Here, we take a step toward an integrative account of these two forms of cerebellar-dependent learning, examining the relevance of core concepts from associative learning for sensorimotor adaptation. Using a visuomotor adaptation reaching task, we paired movement-related feedback (US) with neutral auditory or visual contextual cues that served as CSs. Trial-by-trial changes in feedforward movement kinematics exhibited three key signatures of associative learning: differential conditioning, sensitivity to the CS-US interval, and compound conditioning. Moreover, after compound conditioning, a robust negative correlation was observed between responses to the two elemental CSs of the compound (i.e. overshadowing), consistent with the additivity principle posited by theories of associative learning. The existence of associative learning effects in sensorimotor adaptation provides a proof-of-concept for linking cerebellar-dependent learning paradigms within a common theoretical framework.

Keywords: associative learning; cerebellum; context; forward model; human; neuroscience; sensorimotor adaptation.

Figure 1.. Task design.

(A) Reaching task. Participants reach from a start location (white circle) to a target (blue dot). Online feedback is provided by a cursor (white dot). The target is displayed in a fixed location for the entire experiment (location varied across participants). After a random delay, a tone or a light (white frame) is presented, serving as the movement imperative. The participant is instructed to move directly to the target. The cue persists until the radial position of the hand reaches the target distance. The hand is not visible during the reach; instead, feedback is provided only by the cursor. (B) Components and timing of the reaching task described as conditioning events. The tone and light imperatives serve as conditioned stimuli (CSs), and the cursor feedback is the unconditioned stimulus (US). In our experiments, the radial position of the cursor is aligned with the hand, but the angular position is fixed (‘clamped’), appearing either 15° away from the target (resulting in an error signal) when paired with one of the CS’s (CS+) or at the target when paired with the other CS (CS−). After repeated pairings of the CS+ and US, a conditioned response (CR) develops, leading to an adaptive feedforward movement response in a direction opposite to the rotated feedback. Note that we include an unconditioned response (UR) in the schematic, what we assume is an online, automatic corrective response to the visual error. However, because participants are instructed to move fast, the UR is negligible.

Figure 2.. Experiment 1: differential conditioning.

(A) Experimental protocol. During acquisition (white background), a 15° clamp (clockwise [CW]/counterclockwise [CCW], counterbalanced across participants) was associated with CS+ (e.g. a tone) and a 0° clamp with CS− (e.g. a light; counterbalancing the associations with the tone and light across participants). During the probe phase (gray background), the CS+ and CS− were presented without feedback. Throughout the entire experiment, CS+ and CS− trials were randomly interleaved. (B) Mean heading angle (N=16) as a function of trial number. Clamped feedback was presented on all trials during the acquisition phase (white background) and absent on all trials in the probe phase (gray background). Shaded region represents SEM. (C and D) Experimental results for trial-by-trial change (Δ) in heading angle (mean ± SEM) during the acquisition (C) and probe (D) phases. Left panels present the results of a two-way repeated-measures ANOVA for an adaptation effect (main effect of trial n−1, dark vs light blue) and a Pavlovian effect (main effect of the presented CS on the current trial n, filled vs empty bars). The black outlined bar and violin plot (right panel) present the Pavlovian effect, i.e., the subtraction of heading angle changes between CS+ and CS− trials (mean and 95% CI). (E and F) Rescorla-Wagner model simulation results during the acquisition (E), and probe (F) phases are consistent with the experimental results. Dots and thin lines represent individual participants. CS, conditioned stimulus.

Figure 3.. Simulations of the Pavlovian effect due to differential conditioning in Experiment 1.

Simulations of the current trial Pavlovian effect, the difference between the change in heading angle on CS+ and CS− trials, for different parameter values as predicted by the Rescorla-Wagner model (left side). The results for the acquisition phase are shown on top and probe phase on bottom. Contours represent the mean ± SEM of the Pavlovian effect from Experiment 1. All parameter values for the state-space model fail to predict a differential response on the current trial for CS+ and CS− trials (right side). CS, conditioned stimulus.

Figure 4.. Model comparison.

The sum of squares residuals (SSR) and Akaike information criterion (AIC) difference between the Rescorla-Wagner (RW) and the state-space (SS) models for each participant of Experiment 1.

Figure 5.. Dynamics of adaptation and Pavlovian effects.

(A) Time course of the mean weights (least squares regression β) of the adaptation (trial n−1, gray) and Pavlovian (trial n, blue) effects in Experiment 1 as predicted by the Rescorla-Wagner model (solid lines) and the state-space model (dotted lines). (B) Time course of the mean weights of the adaptation and Pavlovian effects as derived from fits of the experimental results. Shaded regions represent SEM.

Figure 6.. Experiment 2: Pavlovian effect in differential conditioning is abolished when the delay between the conditioned stimulus (CS) and unconditioned stimulus (US) is long.

(A) Illustration of trial events and their timing. By using a separate stimulus for the CS (tone or light) and the imperative (target changed from gray to blue), a delay of ~1000 was imposed between the CS and US. The yellow background highlights the design difference from Experiment 1 (and Experiment 3 below). (B) Mean heading angle (N=64) as a function of trial number. Shaded region represents SEM. (C and D) Trial-by-trial change in heading angle (mean ± SEM) during the acquisition (C) and probe (D) phases. Left panels present the results of a two-way repeated-measures ANOVA for an adaptation effect (main effect of trial n−1, dark vs light colors) and a Pavlovian effect (main effect of the presented CS on the current trial n, filled vs empty bars). The black outlined bars and violin plots (right panel) present the Pavlovian effect, i.e., the subtraction of heading angle changes between CS+ and CS− trials (mean and 95% CI). Dots and thin lines represent individual participants.

Figure 7.. Experiments 3: Pavlovian effect in differential conditioning is observed when the conditioned stimulus (CS) and imperative cue occur simultaneously.

(A) Illustration of trial events and their timing. The green background highlights the design difference from Experiment 2, namely the simultaneous presentation of the CS and the movement imperative. (B) Mean heading angle (N=64) as a function of trial number. Shaded region represents SEM. (C and D) Trial-by-trial change in heading angle (mean ± SEM) during the acquisition (C) and probe (D) phases. Left panels present the results of a two-way repeated-measures ANOVA for an adaptation effect (main effect of trial n−1, dark vs light colors) and a Pavlovian effect (main effect of the presented CS on the current trial n, filled vs empty bars). The black outlined bars and violin plots (right panel) present the Pavlovian effect, i.e., the subtraction of heading angle changes between CS+ and CS− trials (mean and 95% CI). Shaded regions and error bars represent SEM. Dots and thin lines represent individual participants.

Figure 8.. Experiment 4: compound conditioning.

(A) During acquisition, a tone and light were presented simultaneously (compound conditioned stimulus [CS]), serving as the imperative signal for the reaching movement. They were paired with a 15° clamp on all acquisition trials (white background). During the probe phase (gray background), no feedback was provided, and the CSs were presented either together (compound CS) or alone (single CS; tone or light). (B) Mean heading angle (N=22) as a function of trial number. Shaded region represents SEM. (C) Experimental results for the Δ heading angle (median ± SEM) during the probe phase, showing a positive relative change for the compound CS on the current trial n (filled bar) and a negative relative change for each of its elements (empty bars). Friedman test: χ²[2]=9.82, p=0.007. (D) Predictions from the Rescorla-Wagner model for trial-by-trial Δ heading angle during the probe phase. The two elements were assumed to have equal weight in the simulation. (E) Scatter plot showing the between-participant trade-off in terms of the associative strength of the two CSs (the dotted black line represents the unity line). (F) The Δ heading angle (mean ± SEM) after pooling the two single-CS conditions, and the results of a two-way repeated-measures ANOVA for the effects of the previous CS type (compound vs singleton, dark and light pink, respectively) and current CS (filled and empty bars). Thin lines represent individual participants.

Author response image 1.. Experiment 2: task design (A) The task design of Experiment 1 where the CS (tone or light) was the imperative signal.

(B) Task design of Experiment 2. To test the temporal specificity of the Pavlovian effect, a color change of the target served as the imperative. This allowed us to impose a delay of ~1,000 between the CS and US.

Author response image 2.. Differential conditioning: Rescorla-Wagner predictions and experimental results.

(A) Rescorla-Wagner predictions for the change in heading angle during the probe phase in differential conditioning. The model predicts no interaction between the CSs presented on trial n-1 and trial n (the dotted arrows that represent the Pavlovian effect are parallel). (B, C) Experimental results from the probe phase in Experiment 1 (B) and Experiment 3 (C).

Author response image 3.. Time course of heading angle in Experiment 1 on CS+ (light blue) and CS-(dark blue) trials.

.