DEC 25, 2019 10:48 AM PST

Integrating Deep Learning for Online Shopping

WRITTEN BY: Nouran Amin

As the holiday season approaches an end, all of us are familiar with online shopping. To shop on websites, we typically string a few words together to search for the products we want. However, what happens behind the scenes is coding on the next level that allows us to match these words with the right product. Such a process remains one of the biggest challenges in the information retrieval world, particularly among online shopping.

To address these challenges, scientists from Rice University have partnered with Amazon to leverage the power of compressed sensing and ‘slash’ the amount of time it takes to train computers for product search. Researchers began testing Amazons data set of more than 70 million queries for more than 49 million using an approach referred to as MACH which stands for ‘merged-average classifiers via hashing’ (MACH).

“Our training times are about 7-10 times faster, and our memory footprints are 2-4 times smaller than the best baseline performances of previously reported large-scale, distributed deep-learning systems,” said lead researcher Anshumali Shrivastava, an assistant professor of computer science at Rice.

“There are about 1 million English words, for example, but there are easily more than 100 million products online,” commented Tharun Medini, a Ph.D. student at Rice University regarding the challenges with product search.

Not just Amazon but other Tech companies like Google and Microsoft have immense data on successful and unsuccessful product searches. So, researchers have utilized their stored data by combing it with deep learning—which is a potentially effective way to get the best result to searchers.

Deep learning systems, sometimes known as neural network models, are collections of math equations that take in certain numbers called input vectors and transform them into a different numbers called output vectors.

“A neural network that takes search input and predicts from 100 million outputs, or products, will typically end up with about 2,000 parameters per product,” Medini said. “So you multiply those, and the final layer of the neural network is now 200 billion parameters. And I have not done anything sophisticated. I’m talking about a very, very dead simple neural network model.”

Watch this video below to learn more:

“It would take about 500 gigabytes of memory to store those 200 billion parameters,” Medini said. “But if you look at current training algorithms, there’s a famous one called Adam that takes two more parameters for every parameter in the model, because it needs statistics from those parameters to monitor the training process. So, now we are at 200 billion times three, and I will need 1.5 terabytes of working memory just to store the model. I haven’t even gotten to the training data. The best GPUs out there have only 32 gigabytes of memory, so training such a model is prohibitive due to massive inter-GPU communication.”

Source: Rice University

About the Author
  • Nouran earned her BS and MS in Biology at IUPUI and currently shares her love of science by teaching. She enjoys writing on various topics as well including science & medicine, global health, and conservation biology. She hopes through her writing she can make science more engaging and communicable to the general public.
You May Also Like
DEC 20, 2019
Cannabis Sciences
DEC 20, 2019
Beware Twitter Bots Spreading False Cannabis Claims
Twitter bots (accounts controlled by software instead of people) are spreading false claims about the medical uses of cannabis, a new study in the American...
JAN 05, 2020
Space & Astronomy
JAN 05, 2020
It's Finally the Year of the Mars 2020 Mission
It’s officially 2020, and with that in mind, anyone paying attention to NASA’s launch schedule should know already that the Mars 2020 rover is...
JAN 09, 2020
Technology
JAN 09, 2020
Advancing Wearable Technology
Scientists have developed a sensor that works to record the complex sensations of human skin. The development is dubbed as the ‘artificial ionic skin...
JAN 28, 2020
Technology
JAN 28, 2020
Portable device analyzes microbes in the environment
Aquatic microbes often serve as challenge to study, after all, they are too tiny to detect. But, what if there was a device that can swiftly analyze aquati...
FEB 09, 2020
Space & Astronomy
FEB 09, 2020
Here's Why NASA Needs Another Space Station Orbiting the Moon
NASA already has the International Space Station at its disposal, and with that in mind, many have come to question why the American space agency plans to...
FEB 21, 2020
Drug Discovery & Development
FEB 21, 2020
New Antibiotics Found Using AI Technology
Using AI, researchers at MIT have found a powerful new antibiotic capable of killing some of the most dangerous drug-resistant bacteria known to man. ...
Loading Comments...