Bayesian reconstruction of memories stored in neural networks from their connectivity

Abstract

The advent of comprehensive synaptic wiring diagrams of large neural circuits has created the field of connectomics and given rise to a number of open research questions. One such question is whether it is possible to reconstruct the information stored in a recurrent network of neurons, given its synaptic connectivity matrix. Here, we address this question by determining when solving such an inference problem is theoretically possible in specific attractor network models and by providing a practical algorithm to do so. The algorithm builds on ideas from statistical physics to perform approximate Bayesian inference and is amenable to exact analysis. We study its performance on three different models, compare the algorithm to standard algorithms such as PCA, and explore the limitations of reconstructing stored patterns from synaptic connectivity.

arXiv commentCode available at https://github.com/sgoldt/reconstructing_memories

References in corpus (17)

• Community detection in graphs
• Message Passing Algorithms for Compressed Sensing
• Spectral redemption: clustering sparse networks
• Linking connectivity, dynamics and computations in low-rank recurrent neural networks
• Statistical physics of inference: Thresholds and algorithms
• Phase transition in the detection of modules in sparse networks
• The largest eigenvalue of rank one deformation of large Wigner matrices
• Probabilistic Reconstruction in Compressed Sensing: Algorithms, Phase Diagrams, and Threshold Achieving Matrices
• MMSE of probabilistic low-rank matrix estimation: Universality with respect to the output channel
• Constrained Low-rank Matrix Estimation: Phase Transitions, Approximate Message Passing and Applications
• The interplay between randomness and structure during learning in RNNs
• Statistical limits of dictionary learning: random matrix theory and the spectral replica method
• Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising
• Glassy nature of the hard phase in inference problems
• Approximate Survey Propagation for Statistical Inference
• Adapting to Unknown Noise Distribution in Matrix Denoising
• Streaming Bayesian inference: theoretical limits and mini-batch approximate message-passing

Cited by in corpus (2)

• Matrix factorization with neural networks
• Evidence of Replica Symmetry Breaking under the Nishimori conditions in epidemic inference on graphs