Preparation breeds success: Brain activity predicts remembering

Abstract

Successful retrieval of episodic information is thought to involve the adoption of memory states that ensure that stimulus events are treated as episodic memory cues (retrieval mode) and which can bias retrieval toward specific memory contents (retrieval orientation). The neural correlates of these memory states have been identified in many neuroimaging studies, yet critically there is no direct evidence that they facilitate retrieval success. We cued participants before each test item to prepare to complete an episodic (retrieve the encoding task performed on the item at study) or a non-episodic task. Our design allowed us to separate event-related potentials (ERPs) elicited by the preparatory episodic cue according to the accuracy of the subsequent memory judgment. We predicted that a correlate of retrieval orientation should be larger in magnitude preceding correct source judgments than that preceding source errors. This hypothesis was confirmed. Preparatory ERPs at bilateral frontal sites were significantly more positive-going when preceding correct source judgments than when preceding source errors or correct responses in a non-episodic baseline task. Furthermore this effect was not evident prior to recognized items associated with incorrect source judgments. This pattern of results indicates a direct contribution of retrieval orientation to the recovery of task-relevant information and highlights the value of separating preparatory neural activity at retrieval according to subsequent memory accuracy. Moreover, at a more general level this work demonstrates the important role of pre-stimulus processing in ecphory, which has remained largely neglected to date.

Keywords: Episodic memory; Event-related potentials (ERPs); Preparation; Retrieval mode; Retrieval orientation.

Fig. 1

Grand average ERP waveforms (N = 24) time-locked to switch trial cues preceding Episodic Hit-Hits, Episodic Errors and Non-Episodic Hits at the 10 anterior sites analyzed.

Fig. 2

Topographic maps showing the scalp distributions of cue-related ERP effects on switch trials between 800 and 1900 ms. Data were formed by subtracting averaged ERP amplitudes associated with the response conditions indicated above each scalp map. Each map is scaled proportionately between the minimum and maximum values denoted. The maps were computed using a spherical spline interpolation (Perrin, Pernier, Bertrand, & Echallier, 1989).

Fig. 3

Grand average ERP waveforms (N = 16) time-locked to switch trial cues preceding Episodic Hit-Hits, Episodic Hit-Misses and Non-Episodic Hits at the 10 anterior sites analyzed.

Fig. 4

Topographic map showing the scalp distribution of the Episodic Hit-Hits condition minus Episodic Hit-Misses on switch trials between 800 and 1900 ms. The map is scaled proportionately between the minimum and maximum values denoted.