North Carolina State University researchers have developed a technique that reduces training time for deep learning networks by more than 60 percent without sacrificing accuracy, accelerating the development of new artificial intelligence (AI) applications.
“Deep learning networks are at the heart of AI applications used in everything from self-driving cars to computer vision technologies,” says Xipeng Shen, a professor of computer science at NC State and co-author of a paper on the work.
“One of the biggest challenges facing the development of new AI tools is the amount of time and computing power it takes to train deep learning networks to identify and respond to the data patterns that are relevant to their applications. We’ve come up with a way to expedite that process, which we call Adaptive Deep Reuse. We have demonstrated that it can reduce training times by up to 69 percent without accuracy loss.”
Training a deep learning network involves breaking a data sample into chunks of consecutive data points. Think of a network designed to determine whether there is a pedestrian in a given image. The process starts by dividing a digital image into blocks of pixels that are adjacent to each other. Each chunk of data is run through a set of computational filters. The results are then run through a second set of filters. This continues iteratively until all of the data have been run through all of the filters, allowing the network to reach a conclusion about the data sample.
When this process has been done for every data sample in a data set, that is called an epoch. In order to fine-tune a deep learning network, the network will likely run through the same data set for hundreds of epochs. And many data sets consist of between tens of thousands and millions of data samples. Lots of iterations of lots of filters being applied to lots of data means that training a deep learning network takes a lot of computing power.
The breakthrough moment for Shen’s research team came when it realized that many of the data chunks in a data set are similar to each other. For example, a patch of blue sky in one image may be similar to a patch of blue sky elsewhere in the same image or to a patch of sky in another image in the same data set.
By recognizing these similar data chunks, a deep learning network could apply filters to one chunk of data and apply the results to all of the similar chunks of data in the same set, saving a lot of computing power.
“We were not only able to demonstrate that these similarities exist, but that we can find these similarities for intermediate results at every step of the process,” says Lin Ning, a Ph.D. student at NC State and lead author of the paper. “And we were able to maximize this efficiency by applying a method called locality sensitive hashing.”
But this raises two additional questions. How large should each chunk of data be? And what threshold do data chunks need to meet in order to be deemed “similar”?
The researchers found that the most efficient approach was to begin by looking at relatively large chunks of data using a relatively low threshold for determining similarity. In subsequent epochs, the data chunks get smaller and the similarity threshold more stringent, improving the deep learning network’s accuracy. The researchers designed an adaptive algorithm that automatically implements these incremental changes during the training process.
To evaluate their new technique, the researchers tested it using three deep learning networks and data sets that are widely used as testbeds by deep learning researchers: CifarNet using Cifar10; AlexNet using ImageNet; and VGG-19 using ImageNet.
Adaptive Deep Reuse cut training time for AlexNet by 69 percent; for VGG-19 by 68 percent; and for CifarNet by 63 percent – all without accuracy loss.
“This demonstrates that the technique drastically reduces training times,” says Hui Guan, a Ph.D. student at NC State and co-author of the paper. “It also indicates that the larger the network, the more Adaptive Deep Reuse is able to reduce training times – since AlexNet and VGG-19 are both substantially larger than CifarNet.”
“We think Adaptive Deep Reuse is a valuable tool, and look forward to working with industry and research partners to demonstrate how it can be used to advance AI,” Shen says.
The Latest on: Artificial intelligence training
via Google News
The Latest on: Artificial intelligence training
- Hybrid Legal Document Review: Where Human and Artificial Intelligence Meeton February 27, 2020 at 12:19 pm
We hear a lot about the potential of artificial intelligence and machine learning to make the e-discovery process faster ... and it’s important to realize that platforms utilizing this technology are ...
- Gravyty and Accordant Announce Strategic Partnership to Transform Health Care Philanthropy with Artificial Intelligenceon February 27, 2020 at 5:41 am
/PRNewswire/ -- Gravyty, the market-defining provider of fundraiser enablement solutions powered by artificial intelligence (AI), and Accordant announced ...
- 12 Things Pop Culture Gets Wrong About Artificial Intelligenceon February 27, 2020 at 5:20 am
When non-tech people glean much of their tech knowledge from pop culture, it can lead to a lot of misinformation.
- Boosting AI’s smarts in the absence of training dataon February 27, 2020 at 3:02 am
AI (artificial intelligence) is the most perfect field of dreams in modern culture. If you ask the average person on the street what AI runs on, they probably won’t mention training data. Instead, ...
- Training the built environment to withstand, recover, adapt: An AI-driven decision-making paradigmon February 26, 2020 at 3:09 pm
Bridging autonomous training of AI agents and engineering decision-making ... as these emerge at the interface of structural engineering and data science. Inspired by novel advances in artificial ...
- The Business Use of Artificial Intelligence Course (Dubai, United Arab Emirates - April 8-9, 2020) - ResearchAndMarkets.comon February 25, 2020 at 8:54 pm
The "The Business Use of Artificial Intelligence" training has been added to ResearchAndMarkets.com's offering. Leveraging AI for Business Value Your competitors are using AI to analyze sales, what do ...
- Will Artificial Intelligence Make Psychiatry Better?on February 25, 2020 at 2:59 pm
Artificial intelligence (AI) is garnering increasing attention and popularity across medicine ... it is important to know whether a given model can be generalized, so we have to think about the ...
- Explore the uses of artificial intelligence in science March 18 at College of DuPageon February 25, 2020 at 1:43 pm
His research interests include artificial intelligence, machine learning, optimization ... COD offers a broad range of academic programs designed to provide students with the educational background ...
- Center for Artificial Intelligence in Health Sciences to be established at University of Karachion February 25, 2020 at 10:25 am
A state-of-the-art Center for Artificial Intelligence in Health Sciences will be established ... and industries of Pakistan as well as young Pakistanis by giving training to them.
- The Pentagon now has 5 principles for artificial intelligenceon February 24, 2020 at 9:46 pm
Jack Shanahan, the director of the Joint Artificial Intelligence Center, said the decision to adopt the principles separates ... organizational controls, risk mitigation strategies and training ...
via Bing News