Skip to content

Latest commit

 

History

History
21 lines (19 loc) · 563 Bytes

README.md

File metadata and controls

21 lines (19 loc) · 563 Bytes

Neural networks with Theano and Lasagne

Syllabus

  1. Theano basics
  • Symbolic variables/tensors, expressions
  • Functions, shared variables and updates
  1. Overview of Lasagne
  • Layer classes and building a network
  • Objectives, optimizers, and training
  1. Convolutional neural networks
  • Image classification
  • Fine-tuning a pretrained network
  • Style transfer (“Neural Art”)
  1. Recurrent neural networks
  • Language model (text generation)
  • CNN + RNN (image captioning)
  1. Extending Lasagne
  • Defining custom Layers