100 Research Papers in 100 Days (LM Edition)
This is Part III of 100 in 100 series: Language Modeling: ~30 papers NLP Edition: ~40 papers Images Edition: ~30 papers Language Modeling (LM, NMT, Seq2Seq) »
This is Part III of 100 in 100 series: Language Modeling: ~30 papers NLP Edition: ~40 papers Images Edition: ~30 papers Language Modeling (LM, NMT, Seq2Seq) »
Wide & Deep Learning for Recommender Systems (Cheng, Koc, Harmsen, Shaked, Chandra, Aradhye, Anderson, et. al.) While deep learning is great for many things, it's progress »
Microsoft Research dominates Speech-to-Text Achieving Human Parity in Conversational Speech Recognition (W. Xiong, J. Droppo, X. Huang, F. Seide, M. Seltzer, A. Stolcke, D. Yu, G. »
(aka. Living a Successful Life) One way to look at training a neural network is that you are minimizing a cost function to increase accuracy. This »
Building a product can be quite simple, but the best ones include insights from human behavior, algorithmic efficiency, and usability. To start, an engineer might build »