article
Deep learning remains somewhat of a mysterious art even for frequent practitioners, because we usually run complex experiments on large datasets, which obscures basic relationships between dataset, hyperparameters, and performance. The goal of this notebook is to provide some basic intuition of deep neural networks by running very simple experiments on small datasets that help understand trends that occur generally on larger datasets. Read More ›
article
Denoising signal and data is one of the most important problems in data science and electrical engineering. Here, I provide a high-level breakdown of 3 ways to think about this problem. Read More ›
news
Have you used PCA? Then you need to try our contrastive PCA. Read More ›
news
We are organizing the 2017 machine learning in compbio (MLCB) workshop at NIPS. Submit your papers at https://mlcb.github.io/! Read More ›