an interesting look into google's rank brain
TRANSCRIPT
RANK BRAINBy. Jeff Pickle
Digital Marketing Specialist
GOOGLE’S ARTIFICIAL INTELLIGENCE
RANK BRAIN EXPLAINED Google has used word frequency, word distance,
and world knowledge based on co-occurrences to connect the many relations between words to serve up answers to search queries.
But now, due to the recent breakthroughs in language translation and image recognition, Google has turned to powerful neural networks that have the ability to connect the best answers to the millions of search queries Google receives daily.
GOOGLE’S NEURAL NETWORK Rank Brain:
● Is the name of the Google neural network that scans content and is able to understand the relationships between words and phrases on the web.
Google’s neural network: Larry Page stated ; ● “The ultimate search engine
will understand everything in the world.”
● Google intends to carry this plan out using computer science algorithms and their vast database of human knowledge.
WHY IS THIS BETTER THAN PREVIOUS METHODS?
HOW IS IT BETTER? RankBrain is a better
method because it is a deep learning self-improving system.
It trains itself on pages within the Google index
It looks for relationships between the search queries and content contained within the Google index.
HOW DOES IT DO THIS?
INNER WORKINGS OF RANKBRAIN
RankBrain works because of Neural Networks
These networks are good at conducting reading comprehension based on examples and detecting patterns
Thanks to Google’s vast database of website documents it is able to provide a large-scale level of training sets.
INNER WORKINGS OF RANKBRAIN
HOW DOES GOOGLE CONDUCT TRAINING?
Google changes key phrases or words into mathematical entities called vectors which act as signals.
RankBrain then runs an evaluation similar to the cloze test. ● Cloze test: is a reading comprehension activity where words are emitted
from a passage and then filled back in.
CLOZE TEST
With a cloze test, there may be many possible answers, ● But on-going training from a
vast data set allows for a better understanding of the linguistic relationships of these entities.
HERE’S AN EXAMPLE: The movie broke all
(entity1) over the weekend.
Hollywood’s biggest stars were out on the red carpet at the (entity2) premiere.
After deciphering all of the intricate patterns of the vectors, RankBrain can deliver an answer to a query such as “Which movie had the biggest opening at the box office?”
By using vector signals from entities that point to the search result entity receiving the most attention.
IN CONCLUSION It does this without any specific coding, without
rules, or semantic markup. Even for queries that may be vague in nature, the
neural network is able to outperform even humans. With RankBrain, meaning is inferred from use. As training and comprehension improves, it can
focus on the best content that it believes will answer a search query.
As a result, RankBrain can understand search queries never seen before.