Digests » 73
Take the time to learn something new. Click here to discover how to get 40% off your entire purchase at manning.com!
this week's favorite
Today’s paper choice is a wonderful summary of lessons learned integrating around 150 successful customer facing applications of machine learning at Booking.com. Oddly enough given the paper title, the six lessons are never explicitly listed or enumerated in the body of the paper, but they can be inferred from the division into sections.
In this paper, we investigate the problem of training neural machine translation (NMT) systems with a dataset of more than 40 billion bilingual sentence pairs, which is larger than the largest dataset to date by orders of magnitude. Unprecedented challenges emerge in this situation compared to previous NMT work, including severe noise in the data and prohibitively long training time. We propose practical solutions to handle these issues and demonstrate that large-scale pretraining significantly improves NMT performance. We are able to push the BLEU score of WMT17 Chinese-English dataset to 32.3, with a significant performance boost of +3.2 over existing state-of-the-art results.
Data is everywhere, especially in our daily life. For instance, when we are deciding what kind of apple to buy. I believe if you are a price-sensitive person, your final decision will base on the price. However, if you were a more quality-seeking person, you would buy an apple that is imported from a country that is famous for producing apples. From this situation, we can see that we are making decisions base on data unconsciously in daily life.
Artificial intelligence can help us to solve some of society’s most difficult challenges and create a safer, healthier and more prosperous world for all. I’ve already shared the exciting possibilities in the fields of healthcare and agriculture in previous posts. But there may be no area where the possibilities are more interesting – or more important – than education and skills.
A Brownian Motion (BM), without the "fractional" part, is a motion where the position of a given object over time changes in random increments (imagine a sequence of "position+=white_noise();"). Formally, BM is the integral of white noise. These movements define paths that are random yet (statistically) selfsimilar, ie, a zoomed-in version of the path resembles the whole path. A Fractional Brownian Motion is a similar process in which the increments are not completely independent from each other, but there's some sort of memory to the process.