Monte-Carlo-Neural-Nets
Overview
A very lightweight machine learning package.
Has models that use a unique and simple Monte Carlo approach to training. This method used is very generalizable and can therefore be extended to a variety of models both known and new.
The primary model, the NeuralNetwork class, is on par with other similar models such as the
MLPRegressor/MLPClassifier featured in SciKit-Learn, but has more customizability.
The current list of models avaliable and some of their features includes:
NeuralNetwork- Complete hidden layer size and activations customization
- Supports externally defined activation functions
- Allows customizing the input and output activations
- Easy-access hyperparam ranges for Optuna (via .get_param_ranges_for_optuna)
SoupRegressor- A unique combination of many various functions with trainable coefficients
- Typically on-par with the NeuralNetwork; slightly more interpretable
- Many hyperparams to adjust, with more to come
Some QoL functions and features included are:
TTSplit: Included train-test splittercross_val: Simple cross validation system- Built-in scorer functions with support for external functions
- Ability to save and load models at any point (.save & load_model)
- Ability to copy a model via .copy
GitHub and QuickStart
More explanations, examples, and technicals can be found on the GitHub page: https://github.com/SciCapt/Monte-Carlo-Neural-Nets
1 maintainer
Release files for mcnets 2.0.7
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| mcnets-2.0.7.tar.gz | 64.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| mcnets-2.0.7-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 131.7 kB
Release files / mcnets-2.0.7.tar.gz
| Download URL | mcnets-2.0.7.tar.gz |
|---|---|
| Size | 64.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d9fbebe1d8f7a38b1151822eadf26cebfeb0fc53ea46caa81ef539565c9b3f2a
|
|
BLAKE2b-256 checksum How to use checksums |
1dd519cca241ad2fdb148fa7785584d3885c5cb4919f2edf142721d235ddb7ec
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.0.0 CPython/3.8.8
|
Release files / mcnets-2.0.7-py3-none-any.whl
| Download URL | mcnets-2.0.7-py3-none-any.whl |
|---|---|
| Size | 67.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
da9a8987de1b7a1244c16c9066043ded98a94dd7b7797858bb3642e4a1619033
|
|
BLAKE2b-256 checksum How to use checksums |
2343f4c773bdb1d24f19fd7d074ece7778ac5d80d0f2e267a13e3bac43bdb0e2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.0.0 CPython/3.8.8
|
