Learning to generate classifiers

03/30/2018
by   Nicholas Guttenberg, et al.
0

We train a network to generate mappings between training sets and classification policies (a 'classifier generator') by conditioning on the entire training set via an attentional mechanism. The network is directly optimized for test set performance on an training set of related tasks, which is then transferred to unseen 'test' tasks. We use this to optimize for performance in the low-data and unsupervised learning regimes, and obtain significantly better performance in the 10-50 datapoint regime than support vector classifiers, random forests, XGBoost, and k-nearest neighbors on a range of small datasets.

READ FULL TEXT
research
08/20/2023

Developing a Machine Learning-Based Clinical Decision Support Tool for Uterine Tumor Imaging

Uterine leiomyosarcoma (LMS) is a rare but aggressive malignancy. On ima...
research
09/07/2018

Simple coarse graining and sampling strategies for image recognition

A conceptually simple way to recognize images is to directly compare tes...
research
08/25/2018

Improving the results of string kernels in sentiment analysis and Arabic dialect identification by adapting them to your test set

Recently, string kernels have obtained state-of-the-art results in vario...
research
06/28/2020

K-Nearest Neighbour and Support Vector Machine Hybrid Classification

In this paper, a novel K-Nearest Neighbour and Support Vector Machine hy...
research
08/23/2022

Why Deep Learning's Performance Data Are Misleading

This is a theoretical paper, as a companion paper of the keynote talk at...
research
10/25/2017

The Heterogeneous Ensembles of Standard Classification Algorithms (HESCA): the Whole is Greater than the Sum of its Parts

Building classification models is an intrinsically practical exercise th...
research
07/18/2022

Interpolation, extrapolation, and local generalization in common neural networks

There has been a long history of works showing that neural networks have...

Please sign up or login with your details

Forgot password? Click here to reset