- The Rise of Vector Data - May 25, 2021.
Embedding models convert raw data such as text, images, audio, logs, and videos into vector embeddings (“vectors”) to be used for predictions, comparisons, and other cognitive-like functions.
- The Amazing Power of Word Vectors - May 18, 2016.
A fantastic overview of several now-classic papers on word2vec, the work of Mikolov et al. at Google on efficient vector representations of words, and what you can do with them.
Pages: 1 2
- Why Deep Learning Works – Key Insights and Saddle Points - Nov 3, 2015.
A quality discussion on the theoretical motivations for deep learning, including distributed representation, deep architecture, and the easily escapable saddle point.
- Talking Machine – 3 Deep Learning Gurus Talk about History and Future, part 2 - Mar 26, 2015.
Key ideas from a podcast with Deep Learning gurus Geoff Hinton, Yoshua Bengio, and Yann LeCun, where they explain the power of distributed representation and also propose a new open paper review process.