DeepAI AI Chat
Log In Sign Up

Neural Architecture Search From Fréchet Task Distance

by   Cat P. Le, et al.
Duke University
Stanford University

We formulate a Fréchet-type asymmetric distance between tasks based on Fisher Information Matrices. We show how the distance between a target task and each task in a given set of baseline tasks can be used to reduce the neural architecture search space for the target task. The complexity reduction in search space for task-specific architectures is achieved by building on the optimized architectures for similar tasks instead of doing a full search without using this side information. Experimental results demonstrate the efficacy of the proposed approach and its improvements over the state-of-the-art methods.


page 1

page 2

page 3

page 4

page 5

page 9

page 10

page 11


Neural Architecture Search From Task Similarity Measure

In this paper, we propose a neural architecture search framework based o...

Automated Architecture Search for Brain-inspired Hyperdimensional Computing

This paper represents the first effort to explore an automated architect...

Landscape of Neural Architecture Search across sensors: how much do they differ ?

With the rapid rise of neural architecture search, the ability to unders...

A Multi-criteria Approach to Evolve Sparse Neural Architectures for Stock Market Forecasting

This study proposes a new framework to evolve efficacious yet parsimonio...

Evolving Search Space for Neural Architecture Search

The automation of neural architecture design has been a coveted alternat...

Deep Multimodal Neural Architecture Search

Designing effective neural networks is fundamentally important in deep m...

Self-Constructing Neural Networks Through Random Mutation

The search for neural architecture is producing many of the most excitin...