Andrew Trask's book Grokking Deep Learning is the perfect place to begin your deep learning journey. It teaches you to build deep learning from scratch rather than just learn the “black box” API of some library or framework. In this book you’ll train your own neural networks to see and understand images, translate text into different languages, and even write like Shakespeare!
The book uses Python and its math-supporting library NumPy to implement convolutional neural networks, RNN, and LSTM. This post is to announce the Julia companion to the book. Julia is a new and promising language that offers the dynamic nature of Python as well as the performance of C/C++.
You can find the Julia notebooks here. Please try them out and file issues if you find any.