Download
This course concerns the latest techniques in deep learning and representation learning, focusing on supervised and unsupervised deep learning, embedding methods, metric learning, convolutional and recurrent nets, with applications to computer vision, natural language understanding, and speech recognition. The prerequisites include DS-GA 1001 Intro to Data Science or a graduate-level machine learning course. To be able to follow the exercises, you are going to need a laptop with Miniconda (a minimal version of Anaconda) and several Python packages installed. The following instruction would work as is for Mac or Ubuntu Linux users, Windows users would need to install and work in the Git BASH terminal. JupyterLab has a built-in selectable dark theme, so you only need to install something if you want to use the classic notebook interface.
Features
- Jupyter Notebooks are used throughout the lectures for interactive data exploration and visualisation
- This notebook repository now has a companion website
- Basics of supervised learning, neural nets, and deep learning
- Convolutional neural network and its applications
- Regularization tricks, optimization tricks, and understanding how deep learning works
- Visualization of neural networks parameter transformation and fundamental concepts of convolution
Project Samples
