Introduction to using and understanding deep neural networks, their application to visual object recognition, and software tools for building deep neural network models.
Taught by: Phillip Isola, MIT
- Learning in deep neural networks (1:26:25)
- Code for exercises - Click on link to download, open MATLAB, change current directory to the downloaded folder, and then run setup; (this compiles the C code needed for MatConvNet). If you have difficulties, confirm that you have a working C compiler (check that the MATLAB mex command works). You may need to install Windows SDK and/or try using a more recent version of MATLAB.
- Inceptionism: Going Deeper into Neural Networks - New Google blog post on visualizing CNNs
- Stanford "Unsupervised Feature Learning and Deep Learning" tutorial
- CS231n: Convolutional Neural Networks for Visual Recognition
- Hacker's guide to Neural Networks
- Metacademy's Deep Learning From the Bottom Up