# Inference in neural networks using conditional mean-field methods

arXiv: https://arxiv.org/abs/2107.06850 · HTML: https://mlsanity.com/paper/2107.06850/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jul 2021.

## Built on by (most cited first, 1 of 1)

- [Dynamical Mean-Field Theory of Self-Attention Neural Networks](https://mlsanity.com/paper/2406.07247/) (2024)

## Abstract (arXiv)

We extend previous mean-field approaches for non-equilibrium neural network models to estimate correlations in the system. This offers a powerful tool for approximating the system dynamics as well as a fast method to infer network parameters from observations. We develop our method in an asymmetric kinetic Ising model and test its performance on 1) synthetic data generated by an asymmetric version of the Sherrington Kirkpatric model and 2) recordings of in vitro neuron spiking activity from the mouse somatosensory cortex. We find that our mean-field method outperforms previous ones in estimating networks correlations and successfully reconstructs network dynamics from data near a phase transition showing large fluctuations.