Rice University’s Early Bird method for training deep neural networks finds key connectivity patterns early in training, reducing the computations and carbon footprint for the increasingly popular form of artificial intelligence known as deep learning. (Graphic courtesy of Y. Lin/Rice University)
Novel training method could shrink carbon footprint for greener deep learning Rice University’s Early Bird could care less about the worm; it’s looking for megatons of greenhouse gas emissions.
Early Bird is an energy-efficient method for training deep neural networks (DNNs), the form of artificial intelligence (AI) behind self-driving cars, intelligent assistants, facial recognition and dozens more high-tech applications.
Researchers from Rice and Texas A&M University unveiled Early Bird April 29 in a spotlight paper at ICLR 2020, the International Conference on Learning Representations. A study by lead authors Haoran You and Chaojian Li of Rice’s Efficient and Intelligent Computing (EIC) Lab showed Early Bird could use 10.7 times less energy to train a DNN to the same level of accuracy or better than typical training. EIC Lab director Yingyan Lin led the research along with Rice’s Richard Baraniuk and Texas A&M’s Zhangyang Wang.
“A major driving force in recent AI breakthroughs is the introduction of bigger, more expensive DNNs,” Lin said. “But training these DNNs demands considerable energy. For more innovations to be unveiled, it is imperative to find ‘greener’ training methods that both address environmental concerns and reduce financial barriers of AI research.”
Training cutting-edge DNNs is costly and getting costlier. A 2019 study by the Allen Institute for AI in Seattle found the number of computations needed to train a top-flight deep neural network increased 300,000 times between 2012-2018, and a different 2019 study by researchers at the University of Massachusetts Amherst found the carbon footprint for training a single, elite DNN was roughly equivalent to the lifetime carbon dioxide emissions of five U.S. automobiles.
DNNs contain millions or even billions of artificial neurons that learn to perform specialized tasks. Without any explicit programming, deep networks of artificial neurons can learn to make humanlike decisions — and even outperform human experts — by “studying” a large number of previous examples. For instance, if a DNN studies photographs of cats and dogs, it learns to recognize cats and dogs. AlphaGo, a deep network trained to play the board game Go, beat a professional human player in 2015 after studying tens of thousands of previously played games.
“The state-of-art way to perform DNN training is called progressive prune and train,” said Lin, an assistant professor of electrical and computer engineering in Rice’s Brown School of Engineering. “First, you train a dense, giant network, then remove parts that don’t look important — like pruning a tree. Then you retrain the pruned network to restore performance because performance degrades after pruning. And in practice you need to prune and retrain many times to get good performance.”
Pruning is possible because only a fraction of the artificial neurons in the network can potentially do the job for a specialized task. Training strengthens connections between necessary neurons and reveals which ones can be pruned away. Pruning reduces model size and computational cost, making it more affordable to deploy fully trained DNNs, especially on small devices with limited memory and processing capability.
“The first step, training the dense, giant network, is the most expensive,” Lin said. “Our idea in this work is to identify the final, fully functional pruned network, which we call the ‘early-bird ticket,’ in the beginning stage of this costly first step.”
By looking for key network connectivity patterns early in training, Lin and colleagues were able to both discover the existence of early-bird tickets and use them to streamline DNN training. In experiments on various benchmarking data sets and DNN models, Lin and colleagues found Early Bird could emerge as little as one-tenth or less of the way through the initial phase of training.
“Our method can automatically identify early-bird tickets within the first 10% or less of the training of the dense, giant networks,” Lin said. “This means you can train a DNN to achieve the same or even better accuracy for a given task in about 10% or less of the time needed for traditional training, which can lead to more than one order savings in both computation and energy.”
Developing techniques to make AI greener is the main focus of Lin’s group. Environmental concerns are the primary motivation, but Lin said there are multiple benefits.
“Our goal is to make AI both more environmentally friendly and more inclusive,” she said. “The sheer size of complex AI problems has kept out smaller players. Green AI can open the door enabling researchers with a laptop or limited computational resources to explore AI innovations.”
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Training deep neural networks
- The complexity of artificial intelligenceon March 5, 2021 at 8:14 am
SMU Assistant Professor Sun Qianru says highly diverse training data is critical to ensure the machine sees a wide range of examples and counterexamples that cancel out spurious patterns.
- Accurate surface ultraviolet radiation forecasting for clinical applications with deep neural networkon March 2, 2021 at 4:00 pm
Surface UV and weather data acquisition. Surface UV radiation, total ozone column, cloud coverage, and aerosol optical depth at 500 nm (AOD500), were collected at the Faculty of S ...
- Machine learning in spectral domainon February 26, 2021 at 10:08 am
Theoretical aspects of automated learning from data involving deep neural networks have open questions. Here Giambagli et al. show that training the neural networks in the spectral domain of the ...
- STM32 solutions for Artificial Neural Networkson February 17, 2021 at 4:09 pm
Capture a sufficient amount of representative data about the phenomenon that is being modeled. This usually involves placing sensors on or near the object being monitored in order to record its state ...
- Neural Regression Using PyTorch: Defining a Networkon February 12, 2021 at 12:04 am
Next, the demo creates an 8-(10-10)-1 deep neural network. The demo prepares training by setting up a loss function (mean squared error), a training optimizer function (Adam) and parameters for ...
Go deeper with Google Headlines on:
Training deep neural networks
Go deeper with Bing News on:
- Dell Enterprise has a green vision to stop our love for technology killing the planeton March 7, 2021 at 4:24 am
But the coolest thing for me was hearing about how technology like AI, cloud computing and 5G connectivity will be used to further this longevity plan, for example by pushing over-the-air updates to ...
- From AI to green chemistry: how Stockholm University is tackling the climate crisison March 5, 2021 at 4:48 pm
Do AI's 'dark machines' provide more reasons for hope or fear when it comes to tackling climate change? And how can 'green chemistry' and economics play a role in building a sustainable future? The ...
- From new Portuguese home, Ai Weiwei plans tribute to "visionary" Gorbachevon March 4, 2021 at 9:42 am
Ai Weiwei, the Chinese dissident whose activist art has made him Beijing's best-known critic, has swapped life in British exile for Portugal, where, in a countryside estate east of Lisbon, he is ...
- Green Hydrogen Market is Poised to Expand at 13.2% CAGR | Market Research Future (MRFR)on March 4, 2021 at 6:13 am
Green Hydrogen Systems (Denmark), H2X (Australia), Engie (France), Siemens Gas and Power GmbH & Co. KG (Germany), FuelcellWorks (US), Fuelcell Energy (US), Plug Power (US), Hydrogenics (Canada), ...
- With AI-Powered Green Coffee Analysis, Demetria Closes $3 Million Roundon March 2, 2021 at 11:32 pm
Israeli and Colombian agriculture tech startup Demetria has closed a $3 million seed funding round to support its artificial-intelligence-powered green coffee quality analysis system. The ...