# The space of functions computed by deep layered machines

The ability of deep neural networks to generalize can be unraveled using path integral methods to compute their typical Boolean functions.

Submitted to *Physical Review Letters* (2020)

A. Mozeika, B. Li, D. Saad

We study the space of Boolean functions computed by random layered machines, including deep neural networks, and Boolean circuits. Investigating recurrent and layered feed-forward architectures, we find that the spaces of functions realized by both architectures are the same. We show that, depending on the initial conditions and computing elements used, the entropy of Boolean functions computed by deep layered machines is either monotonically increasing or decreasing with growing depth, and characterize the space of functions computed at the large depth limit.

#### Network valuation in financial systems

P. Barucca, M. Bardoscia, F. Caccioli, M. D’Errico, G. Visentin, G. Caldarelli, S. Battiston

*Mathematical Finance*

#### The space of functions computed by deep layered machines

A. Mozeika, B. Li, D. Saad

Sub. to *Physical Review Letters*

#### Replica analysis of overfitting in generalized linear models

T. Coolen, M. Sheikh, A. Mozeika, F. Aguirre-Lopez, F. Antenucci

Sub. to *Journal of Physics A*

#### Degree-correlations in a bursting dynamic network model

F. Vanni, P. Barucca

*Journal of Economic Interaction and Coordination*

#### Phase transition creates the geometry of the continuum from discrete space

R. Farr, T. Fink

*Physical Review E*

#### Intelligently chosen interventions have potential to outperform the diode bridge in power conditioning

F. Liu, Y. Zhang, O. Dahlsten, F. Wang

*Scientific Reports *

123 / 123 papers