Modern Methods in Associative Memory: Modern Methods in Associative Memory: AM and broader AI

Dmitry Krotov, Benjamin Hoover, Parikshit Ram

International Conference on Machine Learning 2025 · Tutorial

This talk, delivered by Parikshit Ram, delves into **associative memory (AM)** networks, reframing them not as abstract theoretical constructs from physics or neuroscience, but as tangible machine learning models applicable to a wide array of tasks. While the broader tutorial covered AM from various angles, Ram's specific focus is on interpreting AM within a standard machine learning framework, drawing parallels to familiar models like linear regression, support vector machines, and neural networks. This perspective allows for the exploration of how AM can be leveraged for conventional machine learning problems such as classification, regression, and clustering, as well as novel generative capabilities.

AI review

A technically competent tutorial segment that reframes classical associative memory within modern ML vocabulary and introduces a genuinely interesting result — the Epanechnikov kernel's simultaneous memorization and generation behavior. The random features connection to Rahimi and Recht is clean and well-motivated, and the differentiable reinterpretation of energy descent as a recurrent network is a useful pedagogical move. The Epanechnikov finding is the most novel contribution and deserves follow-up, but the talk as described stops short of providing the theoretical machinery needed to…