/neuralnetworks.thought-experiments

Observations and notes to understand the workings of neural network models and other thought experiments using Tensorflow

Primary LanguageJupyter NotebookMIT LicenseMIT

neuralnetworks.thought-experiments

A repo of observations and notes to understand the workings of neural network models and other simple thought experiments using Tensorflow.

  • Activations - Notes on activation functions with experimental results to compare models on MNIST and CIFAR10
  • Generative Models - Observations on generative machine learning and results using Auto Encoders, VAEs and GANs
  • Model Pruning - Results on doing pruning in neural networks. (mainly OBD as of now.)