Goal Shifts Structure Memories and Prioritize Event-defining Information in Memory.

Every day, we encounter far more information than we could possibly remember. Thus, our memory systems must organize and prioritize the details from an experience that can adaptively guide the storage and retrieval of specific episodic events. Prior work has shown that shifts in internal goal states can function as event boundaries, chunking experiences into distinct and memorable episodes. In addition, at short delays, memory for contextual information at boundaries has been shown to be enhanced compared with items within each event. However, it remains unclear if these memory enhancements are limited to features that signal a meaningful transition between events. To determine how changes in dynamic goal states influence the organization and content of long-term memory, we designed a 2-day experiment in which participants viewed a series of black-and-white objects surrounded by a color border on a two-by-two grid. The location of the object on the grid determined which of two tasks participants performed on a given trial. To examine if distinct types of goal shifts modulate the effects of event segmentation, we changed the border color, the task, or both after every four items in a sequence. We found that goal shifts influenced the temporal memory in a manner consistent with the formation of distinct events. However, for subjective memory representations in particular, these effects differed by the type of event boundary. Furthermore, to examine if goal shifts lead to the prioritization of goal-relevant features in longer lasting memories, we tested the source memory for each object's color and grid location both immediately and after a 24-hr delay. On the immediate test, boundaries enhanced the memory for all concurrent source features compared with nonboundary items, but only if those boundaries involved a goal shift. In contrast, after a delay, the source memory was selectively enhanced for the feature relevant to the goal shift. These findings suggest that goals can adaptively structure memories by prioritizing contextual features that define a unique episode in memory.

Adaptive Repulsion of Long-Term Memory Representations Is Triggered by Event Similarity.

We tested whether similarity between events triggers adaptive biases in how those events are remembered. We generated pairs of competing objects that were identical except in color and varied the degree of color similarity for the competing objects. Subjects (N = 123 across four experiments) repeatedly studied and were tested on associations between each of these objects and corresponding faces. As expected, high color similarity between competing objects created memory interference for object-face associations. Strikingly, high color similarity also resulted in a systematic bias in how the objects themselves were remembered: Competing objects with highly similar colors were remembered as being further apart (in color space) than they actually were. This repulsion of color memories increased with learning and served a clear adaptive purpose: Greater repulsion was associated with lower associative-memory interference. These findings reveal that similarity between events triggers adaptive-memory distortions that minimize interference.

Adaptive Memory Distortions Are Predicted by Feature Representations in Parietal Cortex.

Similarity between memories is a primary cause of interference and forgetting. Exaggerating subtle differences between memories is therefore a potential mechanism for reducing interference. Here, we report a human fMRI study (n = 29, 19 female) that tested whether behavioral and neural expressions of memories are adaptively distorted to reduce interference. Participants learned and repeatedly retrieved object images, some of which were identical except for subtle color differences. Behavioral measures of color memory revealed exaggeration of differences between similar objects. Importantly, greater memory exaggeration was associated with lower memory interference. fMRI pattern analyses revealed that color information in parietal cortex was stronger during memory recall when color information was critical for discriminating competing memories. Moreover, greater representational distance between competing memories in parietal cortex predicted greater color memory exaggeration and lower memory interference. Together, these findings reveal that competition between memories induces adaptive, feature-specific distortions in parietal representations and corresponding behavioral expressions.SIGNIFICANCE STATEMENT Similarity between memories is a primary cause of interference and forgetting. Here, we show that, when remembering highly similar objects, subtle differences in the features of these objects are exaggerated in memory to reduce interference. These memory distortions are reflected in, and predicted by, overlap of activity patterns in lateral parietal cortex. These findings provide unique insight into how memory interference is resolved and specifically implicate lateral parietal cortex in representing feature-specific memory distortions.

Interference between overlapping memories is predicted by neural states during learning.

One of the primary contributors to forgetting is interference from overlapping memories. Intuitively, this suggests-and prominent theoretical models argue-that memory interference is best avoided by encoding overlapping memories as if they were unrelated. It is therefore surprising that reactivation of older memories during new encoding has been associated with reduced memory interference. Critically, however, prior studies have not directly established why reactivation reduces interference. Here, we first developed a behavioral paradigm that isolates the negative influence that overlapping memories exert during memory retrieval. We then show that reactivating older memories during the encoding of new memories dramatically reduces this interference cost at retrieval. Finally, leveraging multiple fMRI decoding approaches, we show that spontaneous reactivation of older memories during new encoding leads to integration of overlapping memories and, critically, that integration during encoding specifically reduces interference between overlapping, and otherwise competing, memories during retrieval.

Overlap among Spatial Memories Triggers Repulsion of Hippocampal Representations.

Across the domains of spatial navigation and episodic memory, the hippocampus is thought to play a critical role in disambiguating (pattern separating) representations of overlapping events. However, it is not fully understood how and why hippocampal patterns become separated. Here, we test the idea that event overlap triggers a "repulsion" among hippocampal representations that develops over the course of learning. Using a naturalistic route-learning paradigm and spatiotemporal pattern analysis of human fMRI data, we found that hippocampal representations of overlapping routes gradually diverged with learning to the point that they became less similar than representations of non-overlapping events. In other words, the hippocampus not only disambiguated overlapping events but formed representations that "reversed" the objective similarity among routes. This finding, which was selective to the hippocampus, is not predicted by standard theoretical accounts of pattern separation. Critically, because the overlapping route stimuli that we used ultimately diverged (so that each route contained overlapping and non-overlapping segments), we were able to test whether the reversal effect was selective to the overlapping segments. Indeed, once overlapping routes diverged (eliminating spatial and visual similarity), hippocampal representations paradoxically became relatively more similar. Finally, using a novel analysis approach, we show that the degree to which individual hippocampal voxels were initially shared across route representations was predictive of the magnitude of learning-related separation. Collectively, these findings indicate that event overlap triggers a repulsion of hippocampal representations-a finding that provides critical mechanistic insight into how and why hippocampal representations become separated.

Experience-dependent hippocampal pattern differentiation prevents interference during subsequent learning.

The hippocampus is believed to reduce memory interference by disambiguating neural representations of similar events. However, there is limited empirical evidence linking representational overlap in the hippocampus to memory interference. Likewise, it is not fully understood how learning influences overlap among hippocampal representations. Using pattern-based fMRI analyses, we tested for a bidirectional relationship between memory overlap in the human hippocampus and learning. First, we show that learning drives hippocampal representations of similar events apart from one another. These changes are not explained by task demands to discriminate similar stimuli and are fully absent in visual cortical areas that feed into the hippocampus. Second, we show that lower representational overlap in the hippocampus benefits subsequent learning by preventing interference between similar memories. These findings reveal targeted experience-dependent changes in hippocampal representations of similar events and provide a critical link between memory overlap in the hippocampus and behavioural expressions of memory interference.

Predicting the integration of overlapping memories by decoding mnemonic processing states during learning.

The hippocampal memory system is thought to alternate between two opposing processing states: encoding and retrieval. When present experience overlaps with past experience, this creates a potential tradeoff between encoding the present and retrieving the past. This tradeoff may be resolved by memory integration-that is, by forming a mnemonic representation that links present experience with overlapping past experience. Here, we used fMRI decoding analyses to predict when - and establish how - past and present experiences become integrated in memory. In an initial experiment, we alternately instructed subjects to adopt encoding, retrieval or integration states during overlapping learning. We then trained across-subject pattern classifiers to 'read out' the instructed processing states from fMRI activity patterns. We show that an integration state was clearly dissociable from encoding or retrieval states. Moreover, trial-by-trial fluctuations in decoded evidence for an integration state during learning reliably predicted behavioral expressions of successful memory integration. Strikingly, the decoding algorithm also successfully predicted specific instances of spontaneous memory integration in an entirely independent sample of subjects for whom processing state instructions were not administered. Finally, we show that medial prefrontal cortex and hippocampus differentially contribute to encoding, retrieval, and integration states: whereas hippocampus signals the tradeoff between encoding vs. retrieval states, medial prefrontal cortex actively represents past experience in relation to new learning.

The role of sleep in forming a memory representation of a two-dimensional space.

There is ample evidence from human and animal models that sleep contributes to the consolidation of newly learned information. The precise role of sleep for integrating information into interconnected memory representations is less well understood. Building on prior findings that following sleep (as compared to wakefulness) people are better able to draw inferences across learned associations in a simple hierarchy, we ask how sleep helps consolidate relationships in a more complex representational space. We taught 60 subjects spatial relationships between pairs of buildings, which (unknown to participants) formed a two-dimensional grid. Critically, participants were only taught a subset of the many possible spatial relations, which allowed them to potentially infer the remainder. After a 12 h period that either did or did not include a normal period of sleep, participants returned to the lab. We examined the quality of each participant's map of the two-dimensional space, and their knowledge of relative distances between buildings. After 12 h with sleep, subjects could more accurately map the full space than subjects who experienced only wakefulness. The incorporation of untaught, but inferable, associations was particularly improved. We further found that participants' distance judgment performance related to self-reported navigational style, but only after sleep. These findings demonstrate that consolidation over a night of sleep begins to integrate relations into an interconnected complex representation, in a way that supports spatial relational inference.