Summary: wvabrinskas/Neuron: A neural network library for Swift

Neuron performs gradient descent operations using Tensor objects and their accompanying TensorContext .

Building the MNIST dataset

NOTE: Be sure to import NeuronDatasets to get the MNIST and other datasets.

We pass in the Adam Optimizer we defined earlier, the number of epochs to train for, the batch size, and the number of multi-threaded workers to use.

Trained on MNIST 7’s for 10 epochs.

Tensor

The main backbone of Neuron is the Tensor object.

Similar Articles

wvabrinskas/Neuron: A neural network library for Swift

A neural network library for Swift . Contribute to wvabrinskas/Neuron development by creating an account on GitHub.

Read the complete article at: github.com