Search for: All records

The Electron-Ion Collider (EIC), a state-of-the-art facility for studying the strong force, is expected to begin commissioning its first experiments in 2028. This is an opportune time for artificial intelligence (AI) to be included from the start at this facility and in all phases that lead up to the experiments. The second annual workshop organized by the AI4EIC working group, which recently took place, centered on exploring all current and prospective application areas of AI for the EIC. This workshop is not only beneficial for the EIC, but also provides valuable insights for the newly established ePIC collaboration at EIC. This paper summarizes the different activities and R&D projects covered across the sessions of the workshop and provides an overview of the goals, approaches and strategies regarding AI/ML in the EIC community, as well as cutting-edge techniques currently studied in other experiments.

 

Equivariant representation is necessary for the brain and artificial perceptual systems to faithfully represent the stimulus under some (Lie) group transformations. However, it remains unknown how recurrent neural circuits in the brain represent the stimulus equivariantly, nor the neural representation of abstract group operators. The present study uses a one-dimensional (1D) translation group as an example to explore the general recurrent neural circuit mechanism of the equivariant stimulus representation. We found that a continuous attractor network (CAN), a canonical neural circuit model, self-consistently generates a continuous family of stationary population responses (attractors) that represents the stimulus equivariantly. Inspired by the Drosophila’s compass circuit, we found that the 1D translation operators can be represented by extra speed neurons besides the CAN, where speed neurons’ responses represent the moving speed (1D translation group parameter), and their feedback connections to the CAN represent the translation generator (Lie algebra). We demonstrated that the network responses are consistent with experimental data. Our model for the first time demonstrates how recurrent neural circuitry in the brain achieves equivariant stimulus representation. 

The modes of Pacific decadal-scale variability (PDV), traditionally defined as statistical patterns of variance, reflect to first order the ocean's integration (i.e., reddening) of atmospheric forcing that arises from both a shift and a change in strength of the climatological (time-mean) atmospheric circulation. While these patterns concisely describe PDV, they do not distinguish among the key dynamical processes driving the evolution of PDV anomalies, including atmospheric and ocean teleconnections and coupled feedbacks with similar spatial structures that operate on different timescales. In this review, we synthesize past analysis using an empirical dynamical model constructed from monthly ocean surface anomalies drawn from several reanalysis products, showing that the PDV modes of variance result from two fundamental low-frequency dynamical eigenmodes: the North Pacific–central Pacific (NP-CP) and Kuroshio–Oyashio Extension (KOE) modes. Both eigenmodes highlight how two-way tropical–extratropical teleconnection dynamics are the primary mechanisms energizing and synchronizing the basin-scale footprint of PDV. While the NP-CP mode captures interannual- to decadal-scale variability, the KOE mode is linked to the basin-scale expression of PDV on decadal to multidecadal timescales, including contributions from the South Pacific.