Why do we remember some events but forget others? In our recent work published at @NatureComms, @AudreyDuarte15 and I used machine learning to simultaneously quantify multiple cognitive components of episodic memory. 1/11.

Glad to see our recent work has been featured in @thedailytexan!!.

Generate videos in just a few seconds. Try Grok Imagine, free for a limited time.

If you're going to #CNS2025, please stop by my poster (C36) on Sunday evening to find out more about this paper and episodic memory's multidimensional scrutiny! 🤓 @CogNeuroNews.

RT @AudreyDuarte15: This paper is finally out! An amazing effort by @SoroushMirjali2 who used a novel ML approach to covertly asses the mul….

RT @aipulserx: How can machine learning help us understand why we remember some events but forget others by analyzing the multiple cognitiv….

I'd like to sincerely thank @jalewpea, @furranko, and Tzyy-Ping Jung for the helpful discussion and Chuu Nyan and Sahana Ram for assisting with the EEG data collection. Lastly, a huge shoutout to my advisor, @AudreyDuarte15 for her endless guidance and support :) 11/11.

Overall, not only does this study shed light on the multidimensionality of memory, which is important for basic science, but it also opens avenues for future implications in terms of real-world interventions to improve memory. 10/11.

Crucially, the idea of teasing apart a cognitive process into its cognitive components is not restricted to the episodic memory domain and the approach of this study also offers avenues for neuroscientists who are interested in other cognitive domains. 9/11.

We also found that the neural evidence of high levels of perception, sustained attention, and selective attention were higher for events preceded by a hit than events preceded by a miss. Similar results were found when comparing the events based on the next event's success. 8/11

We investigated whether the sources' involvement fluctuated depending on how long the participant had been performing the encoding task. We found that as the time-on-task increased, the level of perception, sustained, and selective attention significantly decreased. 7/11

To better define brain states associated with memory success, it is also important to know how long a participant has been encoding events (i.e., the “time-on-task” effect) and whether the previously presented event was successfully encoded (i.e., the encoding “history”). 6/11.

By leveraging the sources in a stepwise manner, we could quantify the extent to which each source improved the memory classification performance. While not independent from each other, each three sources explained a unique additional variance of encoding-related activity. 5/11

We found that this multidimensional treatment of memory decoding improved prediction performance compared to traditional, unidimensional, methods. 4/11

Using a machine learning algorithm known as “transfer learning”, we leveraged visual perception, sustained attention, and selective attention brain states (i.e., the "sources") to predict memory performance from trial-to-trial encoding electroencephalography (EEG) activity. 3/11

Previous studies attempting to decode successful vs. unsuccessful encoding brain states have met with limited success, potentially due, in part, to assessing episodic memory as a unidimensional process, despite evidence that multiple domains contribute to episodic encoding. 2/11.

RT @AudreyDuarte15: Postdoctoral positions in the cognitive neuroscience of memory at UT Austin! Please share

RT @AudreyDuarte15: New paper led by @rebeccaa_cutler where we show that semantic memory space becomes denser with age. .

RT @AudreyDuarte15: New paper from the lab, now open access, investigating interactive effects of age and depression on executive function….

RT @AudreyDuarte15: New review from our lab about relationships between sleep and episodic memory in racially minoritized adults is now ope….

RT @vpmurty: We are hiring 2 RAs in the AML (now at University of Oregon) with an anticipated start date of late summer/early fall. I promi….