Skip to main content

A simple numpy based neural network library inspired by Tensorflow/Keras.

Project description

bren is a custom numpy based library, powered by automatic differentiation, inspired by Tensorflow/Keras, which allows users to build small scale simple neural networks. It's analogous yet simpler design to the Keras api allows users to produce, train and save their own models, with custom components, without having to learn an entirely new structure.

bren is part of a sequence of neural network from scratch projects and a successor to the neural-network-from-scratch-v2, with one major update being the integration of automatic differentitation. Automatic differentiation allows for the real-time determination of derivatives during back propagation and reduces the need for users to couple mathematical computation with derivatives as was required in the previous projects.

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

bren-0.1.4.tar.gz (31.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

bren-0.1.4-py3-none-any.whl (44.8 kB view details)

Uploaded Python 3

File details

Details for the file bren-0.1.4.tar.gz.

File metadata

  • Download URL: bren-0.1.4.tar.gz
  • Upload date:
  • Size: 31.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.4

File hashes

Hashes for bren-0.1.4.tar.gz
Algorithm Hash digest
SHA256 fadfaf103229ccb52258eda0a7cfd0cd7555f03a3314ec7f144c5522e671ffdd
MD5 12092999d064513475e3161a22de34dc
BLAKE2b-256 6b95417855a998f9ce7ccb3f32c92be84e76200dc60a5d4b44ebbdd4fe200b9f

See more details on using hashes here.

File details

Details for the file bren-0.1.4-py3-none-any.whl.

File metadata

  • Download URL: bren-0.1.4-py3-none-any.whl
  • Upload date:
  • Size: 44.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.4

File hashes

Hashes for bren-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 1f8512d587479f1e8bfe01b0aac84dcb104da9758cb1dc20bc5b9d5d35faa0a7
MD5 26f763f0798db6399982eb3189e8d22c
BLAKE2b-256 925a7349da64500ee924b8aa6b210a3ebe7a62f9854deea2448ec932a68f2337

See more details on using hashes here.

Supported by

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