1. tiny-dnn is a header-only deep learning framework for C++ that aims to be easy to introduce, have simple syntax, and support extensible backends. 2. It allows defining neural networks concisely using modern C++ features and supports common network types like MLPs and CNNs through simple syntax similar to Keras and TensorFlow. 3. The framework has optional performance-oriented backends like AVX
![Deep learning with C++ - an introduction to tiny-dnn](https://cdn-ak-scissors.b.st-hatena.com/image/square/9ccb9847081dc26aa2daca415add158e80b0892a/height=288;version=1;width=512/https%3A%2F%2Fcdn.slidesharecdn.com%2Fss_thumbnails%2Fdeeplearningwithc-anintroductiontotiny-dnn-161127092855-thumbnail.jpg%3Fwidth%3D640%26height%3D640%26fit%3Dbounds)