We present tutorials that cover the implementation of common model architectures:

  • Tutorial 1: MNIST with multi-layer perceptron (MLP) network
  • Tutorial 2: Object recognition with a convolutional neural network
  • Tutorial 3: Sentiment analysis with a recurrent neural network

In addition, we include several how-to guides for customizing neon and visualizing the results. We recommend reading the section on the neon backend as a prerequisite to these tutorials:

Since neon v2.0.0+ is now released with MKL backend support, we encourage users to use -b mkl on Intel CPUs for all the tutorial examples used.