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.
Learn more: New Technique Cuts AI Training Time By More Than 60 Percent
The Latest on: Artificial intelligence training
[google_news title=”” keyword=”artificial intelligence training” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Artificial intelligence training
- Billionaire Bill Ackman Owns 8 Stocks -- and This Hypergrowth Artificial Intelligence (AI) Stock Isn't One of Themon April 27, 2024 at 4:15 am
Some investors might cringe at his portfolio's lack of diversification, but Ackman's strategy has worked out over the long term. Additionally, some might question its lack of artificial intelligence ...
- How Artificial Intelligence Is Changing The Way You Buy Travel Insuranceon April 27, 2024 at 3:52 am
Artificial intelligence is transforming the way you buy travel insurance. Here are the surprising ways it could affect your next vacation.
- Artificial Intelligence and the Future of Singapore’s Foreign Workforceon April 26, 2024 at 2:20 pm
Without careful regulations, AI will widen the already significant divide between Singaporean workers and the country’s large population of migrant laborers.
- Artificial Intelligence: Major Cyber Threats for Law Firms in 2024on April 26, 2024 at 6:18 am
Because trust is crucial in a lawyer-client relationship, it is of the utmost importance that law firms maintain the highest standards in data security.
- A Once-in-a-Decade Investment Opportunity: 2 Artificial Intelligence (AI) Stocks to Buy Now and Hold Long Termon April 26, 2024 at 2:00 am
These stocks could help investors turn a profit as artificial intelligence takes root across business processes and consumer products.
- 1 Monster Artificial Intelligence (AI) Growth Stock Up 45,900% in 20 Years to Buy Now, According to Wall Streeton April 26, 2024 at 1:44 am
Nvidia stock produced life-changing returns over the past two decades, but Wall Street analysts still see upside for shareholders.
- Meta introduces new artificial intelligence training chipon April 25, 2024 at 11:01 am
Meta introduced its new artificial intelligence (AI) training chip Wednesday that supports new generative AI products and services. The US-based global tech firm said its next generation Meta ...
- The Impact of Artificial Intelligence on Job Market Trendson April 25, 2024 at 3:49 am
Are robots taking over our jobs? Will artificial intelligence make human labor obsolete? These questions have been wandering over the job market for years, sparking debates and fears about the future ...
- Artificial intelligence helps scientists engineer plants to fight climate changeon April 24, 2024 at 1:42 pm
The Intergovernmental Panel on Climate Change (IPCC) has declared that removing carbon from the atmosphere is now essential to fighting climate change and limiting global temperature rise. To support ...
- The AI Conscience: Leading Ethical Decision-Making In The Artificial Intelligence Ageon April 24, 2024 at 4:00 am
The march of artificial intelligence (AI) is transforming businesses worldwide. As AI becomes more influential, leaders face the challenge of making ethical decisions in uncharted territories. As ...
via Bing News