SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1702.08833 · 2017

Learning Deep Nearest Neighbor Representations Using Differentiable Boundary Trees

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Nearest neighbor (kNN) methods have been gaining popularity in recent years in light of advances in hardware and efficiency of algorithms. There is a plethora of methods to choose from today, each with their own advantages and disadvantages. One requirement shared between all kNN based methods is the need for a good representation and distance measure between samples. We introduce a new method called differentiable boundary tree which allows for learning deep kNN representations. We build on the recently proposed boundary tree algorithm which allows for efficient nearest neighbor classification, regression and retrieval. By modelling traversals in the tree as stochastic events, we are able to form a differentiable cost function which is associated with the tree's predictions. Using a deep neural network to transform the data and back-propagating through the tree allows us to learn good representations for kNN methods. We demonstrate that our method is able to learn suitable representations allowing for very efficient trees with a clearly interpretable structure.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1702.08833")
get_code_for_paper("1702.08833")
have("1702.08833")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1702.08833.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1702.08833.svg)](https://syntology.ai/paper/1702.08833)

Connect an agent — have() is free.