Alexa R. Tartaglini

I’m super excited to announce that I’ll be starting a PhD in Computer Science at @Stanford this upcoming fall! Stay posted for (hopefully) cool work on visual abstraction, emergence of symbols in DNNs, & cognitively-inspired interpretability 🟦🔴

I'll be attending @NeurIPSConf from December 10-15 and presenting this work with @Michael_Lepori. Please reach out if you'd like to chat about interpretability, cognition, or anything really! #NeurIPS2024

New chapter with @cameronjbuckner on interventionist methods for interpreting deep neural networks. We review and discuss the significance of recent developments in interpretability research on DNNs from a philosophical perspective. 1/6 philpapers.org/rec/MILIMF-2

Cognitive science proposes plausible explanations of behavior. But did you know that some behavioral patterns logically imply that certain neural representations *must* exist? New paper w/ Randy Gallistel. Implications for neuroscience and machine learning onlinelibrary.wiley.com/doi/10.1111/ej…

Glad to announce our new preprint with C. Hillar, D. Kragic, and @naturecomputes ! arxiv.org/abs/2312.08550 We show via group theory how Fourier features emerge in invariant neural networks -- a step towards a mathematical understanding of representational universality. 🧵1/n

The first publication of my PhD and my first 10-rated review! Thrilled to share our @NeurIPSConf'23 Oral finding large differences in frequency tuning between humans and neural networks, which strongly explain shape bias and robustness! arxiv.org/pdf/2309.13190… 🧵(1/4)

How should we build models more aligned with human cognition? To induce more human-like behaviors & representations, let’s train embodied, interactive agents in rich, ethologically-relevant environments. w/ @aran_nayebi, @vansteenkiste_s, & Matt Jones psyarxiv.com/a35mt/

Big language models lead to big drama. Nice article discussing progress in engineering more efficient, small models, and opportunities for modeling child language acquisition through much smaller, more natural input data scientificamerican.com/article/when-i…

Really enjoyed working on this project! We show that neural networks are capable of learning genuinely abstract same-different relations — no explicit symbolic processing required. Next step: uncovering abstract relation circuits in vision models?