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
JUL 20, 2020
Neuroscience
Phantom-Limb Pain Reduced by Brain-Computer Interface
JUL 20, 2020
Phantom-Limb Pain Reduced by Brain-Computer Interface
Phantom-limb pain is a condition in which amputees feel like their amputated limb is still attached to their bodies. Whi ...
JUL 01, 2020
Technology
Computerize Your Dog
JUL 01, 2020
Computerize Your Dog
Scientists at CAMERA, a research institute at the University of Bath, can make it possible to computerize your dog using ...
JUL 17, 2020
Technology
How Digital Data Can Determine Your Behavior
JUL 17, 2020
How Digital Data Can Determine Your Behavior
Digital data is the product of our technological uses. Simply opening your smartphone and googling something personal ca ...
JUL 31, 2020
Chemistry & Physics
Advancing Nuclear Fusion by Taming the "Chirping" Plasma
JUL 31, 2020
Advancing Nuclear Fusion by Taming the "Chirping" Plasma
2020 turns out to a year of breakthrough for nuclear fusion. The world's largest fusion project ITER (International ...
AUG 20, 2020
Technology
Smartphones That Can Tell If You Are Intoxicated
AUG 20, 2020
Smartphones That Can Tell If You Are Intoxicated
Smartphones have been under scrutiny for how much data they can capture about someone. Well, now they can apparently not ...
NOV 14, 2020
Cannabis Sciences
New Genetic Test Identifies Cannabis THC Levels from Seeds
NOV 14, 2020
New Genetic Test Identifies Cannabis THC Levels from Seeds
Researchers from the University of Minnesota have developed a genetic test that can predict how much cannabidiol (CBD) o ...
Loading Comments...