SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1810.07348 · 2018

Autonomous Deep Learning: Continual Learning Approach for Dynamic Environments

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

The feasibility of deep neural networks (DNNs) to address data stream problems still requires intensive study because of the static and offline nature of conventional deep learning approaches. A deep continual learning algorithm, namely autonomous deep learning (ADL), is proposed in this paper. Unlike traditional deep learning methods, ADL features a flexible structure where its network structure can be constructed from scratch with the absence of an initial network structure via the self-constructing network structure. ADL specifically addresses catastrophic forgetting by having a different-depth structure which is capable of achieving a trade-off between plasticity and stability. Network significance (NS) formula is proposed to drive the hidden nodes growing and pruning mechanism. Drift detection scenario (DDS) is put forward to signal distributional changes in data streams which induce the creation of a new hidden layer. The maximum information compression index (MICI) method plays an important role as a complexity reduction module eliminating redundant layers. The efficacy of ADL is numerically validated under the prequential test-then-train procedure in lifelong environments using nine popular data stream problems. The numerical results demonstrate that ADL consistently outperforms recent continual learning methods while characterizing the automatic construction of network structures.

For agents

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

get_harvested_code_for_paper("1810.07348")
get_code_for_paper("1810.07348")
have("1810.07348")

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

curl https://syntology.ai/api/ran/1810.07348.json

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

[![Syntology run record](https://syntology.ai/api/ran/1810.07348.svg)](https://syntology.ai/paper/1810.07348)

Connect an agent — have() is free.