Skip to main content

A scikit-learn compatible neural network implementation

Project description


A scikit-learn compatible neural network implementation


pip install ultimate

Why Ultimate?

  • Support feature importance
  • Support missing values
  • Support am2x/a2m2x activation functions
  • Support softmax/hardmax/mse/hardmse loss functions
  • Support fc/add/conv/star operations

How To Use?

# let's use a simple example to learn how to use
from ultimate.mlp import MLP
import numpy as np

# generate sample
X = np.linspace(-np.pi, np.pi, num=5000).reshape(-1, 1)
Y = np.sin(X)
print(X.shape, Y.shape)

# fit and predict
mlp = MLP(layer_size=[X.shape[1], 8, 8, 8, 1], rate_init=0.02, loss_type="mse", epoch_train=100, epoch_decay=10, verbose=1), Y)
pred = mlp.predict(X)

# show the result
import matplotlib.pyplot as plt  
plt.plot(X, pred)

Project details

Release history Release notifications | RSS feed

Download files

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

Source Distributions

No source distribution files available for this release. See tutorial on generating distribution archives.

Built Distribution

ultimate-2.75.2-py2.py3-none-any.whl (104.0 kB view hashes)

Uploaded py2 py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page