ap6yc / deepart Goto Github PK

A repository containing implementations and experiments for the upcoming paper Deep Adaptive Resonance.

Documentation	Testing Status	Zenodo DOI

• Table of Contents
• Basic Usage
• Attribution
  • Authors
  • Datasets
  • Assets
  • Quotes

For detailed usage, please read the documentation.

The DeepART project is a Julia project, so its use follows typical Julia usage. The DeepART project also utilizes DrWatson.jl for organizing and running simulations.

The library code for the project is contained in src/, while all experiments are enumerated in scripts. Each folder therein contains a simple README for the order of running experiments.

For example, after installing Julia on your system, you instantiate this project with

using Pkg; Pkg.activate(); Pkg.instantiate()

and run an experiment interactively with

include("scripts/1_baselines/single/conv.jl")

or through the terminal with

julia --project="." "scripts/1_baselines/single/conv.jl"

• Sasha Petrenko - [email protected] - @AP6YC

• Indoor Scene Recognition
  • Direct Link

• Deep-learning icons created by Freepik - Flaticon (deep-learning_2080961)
• Unlearned Font

To achieve great things, two things are needed: a plan and not quite enough time

-- Leonard Bernstein