Skip to main content

Machine Learning And Deep Learning Algorithms from Scratch

In this repository, major machine learning and deep learning algorithms are implemented from scratch. From scratch meaning without using external machine learning libraries. All of the below mentioned algorithms are implemented in Python, Linear Regression is also implemented in C++. The API structure is similar to the Scikit-Learn library and Tensorflow Keras API.


Algorithms:

Supervised Learning:

  1. Linear Regression
  2. K-nearest Neighbours
  3. Support Vector Machine
  4. Artificial Neural Networks

Unsupervised Learning:

  1. K-Means Clustering
  2. Mean Shift Clustering

Deep Learning:

Neural Networks added with ReLU, Softmax Activations and Categorical Cross Entropy losses, and Optimizers such as SGD, Adam.

To use this implementation:

pip install open-nn-python

Release files for AgainML 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for AgainML 0.1.1
File Size Uploaded
AgainML-0.1.1.tar.gz 7.4 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for AgainML 0.1.1
File Interpreter ABI Platform
AgainML-0.1.1-py3-none-any.whl Python 3 none any Details

Total release size: 15.3 kB

Release files / AgainML-0.1.1.tar.gz

Download URL AgainML-0.1.1.tar.gz
Size 7.4 kB
Tags Source
SHA-256 checksum
How to use checksums
959103c8988642cafd0e13fc38a2e17c753e69e63fa181b5126c0bd20889ebbe
BLAKE2b-256 checksum
How to use checksums
7852e3f169f105bd5a93b1881e0e14fa6fa31df78c782fa9890b91a8c7906c60
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.10.8

Release files / AgainML-0.1.1-py3-none-any.whl

Download URL AgainML-0.1.1-py3-none-any.whl
Size 7.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
dac40433aed3ba1e0eea44c28960cefd1f45cdf6c6071732d16f33ba17b98d94
BLAKE2b-256 checksum
How to use checksums
209ffd1e56f5c409703a26c2098f13bacc1b8c27c449a15c58c18a679bef4321
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.10.8

Release history Release notifications | RSS feed

This release

0.1.1 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page