minimalANN
How to use?
Example :- Suppose this is the network architecture-
To implement the above architecture, we can use the following code -
import numpy as np
import minimalANN.network as network
import minimalANN.layer as layer
nn = network.NeuralNetwork()
nn.layers.append(layer.Layer(1, 2, "sigmoid"))
nn.layers[0].weights = np.array([[-0.27], [-0.41]])
nn.layers[0].bias = np.array([[-0.48], [-0.13]])
nn.layers.append(layer.Layer(2, 1, "linear"))
nn.layers[1].weights = np.array([[0.09, -0.17]])
nn.layers[1].bias = np.array([[0.48]])
X = np.array([[1]])
y = np.array([1.707])
nn = nn.train(X, y, 1)
print(nn.weights)
1 maintainer
Metadata
1 maintainer
Release files for minimalANN 1.0.8
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| minimalann-1.0.8.tar.gz | 4.2 kB | With provenance | Details for minimalann-1.0.8.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| minimalann-1.0.8-py3-none-any.whl | Python 3 | none | any | Details for minimalann-1.0.8-py3-none-any.whl |
Total release size: 10.0 kB
Release files / minimalann-1.0.8.tar.gz
| Download URL | minimalann-1.0.8.tar.gz |
|---|---|
| Size | 4.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d0e243ac17c18b06d5176eec68eb11455ccdd483bfe12344c0ff09f108a0a805
|
|
BLAKE2b-256 checksum How to use checksums |
749d9873ed549d7837c7ec78136127ccaf3c8a924befb04cb6e1fb38d9dbf342
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 23, 2025.
Transparency logRelease files / minimalann-1.0.8-py3-none-any.whl
| Download URL | minimalann-1.0.8-py3-none-any.whl |
|---|---|
| Size | 5.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c1e39d69ff39831d9f11b7ce4b4aa9f954e4585ec12475a72a2004d55a6a19f1
|
|
BLAKE2b-256 checksum How to use checksums |
a5e0a606db9fc16e02e298f45a1f32114f52eee7e4d63ca66bb9b6294691b08e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 23, 2025.
Transparency logSecurity for minimalANN 1.0.8
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for minimalann-1.0.8.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 23, 2025.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
