Episode 10: Deep Neural Networks in Julia with Flux.jl

David and Randy explore deep neural networks in Julia using Flux.jl by recreating Grant Sanderson's model for predicting handwritten digits in the MNIST data set. We also show how to visualize model results and training performance in TensorBoard using the TensorBoardLogging.jl package.

Links:

• Grant Sanderson's (3blue1brown) Neural networks playlist (YouTube)
• Neural Network and Deep Learning (Free online book)
• Flux.jl Website
• TensorBoard website
• TensorBoardLogger.jl (GitHub)
• TensorBoardLogger.jl (Docs)

Episode source