Properties of the geometry of solutions and capacity of multi-layer neural networks with Rectified Linear Units activations

17 July 2019

Papers citing "Properties of the geometry of solutions and capacity of multi-layer neural networks with Rectified Linear Units activations"

7 / 7 papers shown

Title
High-dimensional manifold of solutions in neural networks: insights from statistical physics Enrico M. Malatesta 73 4 0 20 Feb 2025
Exact full-RSB SAT/UNSAT transition in infinitely wide two-layer neural networks B. Annesi Enrico M. Malatesta Francesco Zamponi 61 2 0 09 Oct 2024
Activation function dependence of the storage capacity of treelike neural networks Jacob A. Zavatone-Veth Cengiz Pehlevan 17 15 0 21 Jul 2020
Shaping the learning landscape in neural networks around wide flat minima Carlo Baldassi Fabrizio Pittorino R. Zecchina MLT 36 82 0 20 May 2019
Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemes Carlo Baldassi C. Borgs J. Chayes Alessandro Ingrosso Carlo Lucibello Luca Saglietti R. Zecchina 45 166 0 20 May 2016
Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses Carlo Baldassi Alessandro Ingrosso Carlo Lucibello Luca Saglietti R. Zecchina 42 127 0 18 Sep 2015
Origin of the computational hardness for learning with binary synapses Haiping Huang Y. Kabashima 43 54 0 08 Aug 2014