Skip to main content

AutoML utilizing Genetic Algorithms and Neural Networks

Project description

Blacklight

test Codacy Badge Codacy BadgePyPI - Downloads

Genetic algorithms in autoML.

This project aims to use Genetic Algorithms to optimize the topologies of Deep Neural Networks (DNNs) and explore new possibilities that traditional optimization techniques might overlook. The fitness function of the algorithm is the accuracy of the model, and the genes represent the individual topologies.

Installation

Make sure you have Python 3.9 or higher installed (not greater than 3.11).

Windows, Linux

  1. Create new virtual environment:
    • pip install -m virtualenv
    • python -m venv your_virtual_env_name
    • your_virtual_env_name\Scripts\activate
  2. Install Tensorflow:
    • pip install tensorflow
  3. Install the package:
    • pip install blacklight

MacOS (Intel)

  1. Create new virtual environment:
    • pip install -m virtualenv
    • python -m venv your_virtual_env_name
    • your_virtual_env_name\Scripts\activate
  2. Install Tensorflow:
    • pip install tensorflow-macos
    • pip install tensorflow-metal
  3. Install the package:
    • pip install blacklight

MacOS (Apple Silicon)

  1. Download Miniconda from: https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-arm64.sh
  2. Install Miniconda:
    • Navigate to downloads folder cd ~/Downloads
    • bash Miniconda3-latest-MacOSX-arm64.sh -b -p $HOME/miniconda
  3. Activate Miniconda:
    • source ~/miniconda/bin/activate
  4. Install TensorFlow dependencies:
    • conda install -c apple tensorflow-deps
  5. Install TensorFlow:
    • pip install tensorflow-macos
    • pip install tensorflow-metal
  6. Install the package:
    • pip install blacklight

Hypothesis

The hypothesis of this project is that DNN topologies will converge to either a local maximum or an absolute maximum over the evolution process, offering better performance than a DNN with randomly selected topology. For this experiment, the project will use equivalent activation functions (ReLU) and SGD for back-propagation, holding everything except the topology constant. Updated documentation coming soon.

Methodology

The project utilizes a genetic algorithm to evolve the topology of the DNN. The algorithm starts with a randomly generated population of DNN topologies and evaluates their fitness using the accuracy of the model. The fittest individuals are selected for reproduction, while the weaker ones are discarded. The offspring of the selected individuals are then created through crossover and mutation. This process is repeated for a specified number of generations, and the best-performing topology is chosen as the final output.

Documentation

Documentation can be found at https://blacklightlabs.github.io/blacklight/html/index.html

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

blacklight-0.1.11.tar.gz (54.3 kB view details)

Uploaded Source

Built Distribution

blacklight-0.1.11-py3-none-any.whl (64.9 kB view details)

Uploaded Python 3

File details

Details for the file blacklight-0.1.11.tar.gz.

File metadata

  • Download URL: blacklight-0.1.11.tar.gz
  • Upload date:
  • Size: 54.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.10.11 Linux/5.15.0-1041-azure

File hashes

Hashes for blacklight-0.1.11.tar.gz
Algorithm Hash digest
SHA256 8579fb3e5a4a4003e50551d7d30fc6e71384e3a6453bb4138994a83d3e355f23
MD5 52d52a015d4b69511c035549f7c236e4
BLAKE2b-256 193598c2e7f20b86c0530e14ab9ddc7b7e16bce3b5fd1dd48d1f2cee227c109c

See more details on using hashes here.

File details

Details for the file blacklight-0.1.11-py3-none-any.whl.

File metadata

  • Download URL: blacklight-0.1.11-py3-none-any.whl
  • Upload date:
  • Size: 64.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.10.11 Linux/5.15.0-1041-azure

File hashes

Hashes for blacklight-0.1.11-py3-none-any.whl
Algorithm Hash digest
SHA256 ef7e5b52f420cf29d962ec09fe8739e4d71676ac9bef565fb0fc0b662e80a32f
MD5 8f20f42e6288833583b1737c0aa14a46
BLAKE2b-256 18b5f82cad6d9d8a3cdab5572fc4d987fe79253c38c179b0bd71eecd2fd1e47c

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page