Freenets: Learning Layerfree Neural Network Topologies
Y Varun, R Madhavan - openreview.net
We propose a novel data driven approach to neural architectures based on information
flows in a Neural Connectivity Graph (NCG). This technique gives rise to a category of …
flows in a Neural Connectivity Graph (NCG). This technique gives rise to a category of …
[PDF][PDF] Analysis of Heuristics for Neural Architecture Search
R Wu - cs.toronto.edu
Neural architecture search (NAS) algorithms are a handy tool in the automated construction
of effective deep learning models in information processing tasks such as classification …
of effective deep learning models in information processing tasks such as classification …