As anyone with a green thumb knows, pruning can promote thriving vegetation. A snip here, a snip there, and growth can be controlled and directed for a more vigorous plant.
The same principle can be applied to machine learning algorithms. Removing bits and pieces along coding branches in those algorithms can reduce complexity in decision trees and increase predictive performance.
Researchers at the U.S. Department of Energy’s Pacific Northwest National Laboratory (PNNL) have done just that. Exploring with binarized neural networks (BNNs), they used pruning principles to significantly reduce computation complexity and memory demands. BNNs are close cousins to deep neural networks, which require large amounts of computation. But BNNs differ in a significant way: they use single bits to encode each neuron and parameter, using much less energy and power for computation.
Pruning for faster growth
Researchers recognized the potential value of BNNs for machine learning starting in about 2016. If constructed–or pruned–just the right way, they consume less computing energy and are nearly as accurate as deep neural networks. That means BNNs have more potential to benefit resource-constrained environments, such as mobile phones, smart devices, and the entire Internet of Things ecosystem.
This is where pruning comes into play. As neural networks research has grown in recent years, pruning has gained more interest among computing researchers.
“Pruning is currently a hot topic in machine learning,” said PNNL computer scientist Ang Li. “We can add software and architecture coding to push the trimming towards a direction that will have more benefits for the performance of computing devices. These benefits include lower energy needs and lower computing costs.”
Pruning for precision
Li was among a group of PNNL researchers who recently published results in the Institute of Electrical and Electronics Engineers Transactions on Parallel and Distributed Systems showing the benefits of selective pruning. The research demonstrated that pruning redundant bits of the BNN architecture led to a custom-built out-of-order BNN, called O3BNN-R. Their work shows a highly-condensed BNN model–which already could display high-performing supercomputing qualities–can be shrunk signi?cantly further without loss of accuracy.
“Binarized neural networks have the potential of making the processing time of neural networks around microseconds,” said Tong “Tony” Geng, a Boston University doctoral candidate who, as a PNNL intern, assisted Li on the O3BNN-R project.
“BNN research is headed in a promising direction to make neural networks really useful and be readily adopted in the real-world,” said Geng, who will rejoin the PNNL staff in January as a postdoctoral research fellow. “Our finding is an important step to realize this potential.”
Their research shows this out-of-order BNN can prune, on average, 30 percent of operations without any accuracy loss. With even more fine tuning–in a step called “regularization at training”–the performance can be improved an additional 15 percent.
Pruning for power
In addition to this out-of-order BNN’s contributions to the Internet of Things, Li also pointed to potential benefits to the energy grid. Implementation of a modified BNN could also provide a boost to existing software that guards against cyberattacks when deployed in the power grid by helping existing sensors detect and respond to an attack, said Li.
“Basically,” said Li, “we are accelerating the speed of processing in hardware.”
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Binarized neural networks
- Spiking activity propagation in neuronal networks: reconciling different perspectives on neural coding
Yet, signal transmission is a vital functions for a neural code in ensuring communication among highly specialized brain regions. Feedforward networks with convergent or divergent connections ...
- How to build a neural network in Java
Artificial neural networks are a form of deep learning and one of the pillars of modern-day AI. The best way to really get a grip on how these things work is to build one. This article will be a ...
- Neural Imaging Reveals Secret Conversational Cues
Complex signals and subliminal signs underpin all human verbal communication—and a real-time translation is on the horizon.
- Researchers Build Neural Networks With Actual Neurons
Neural networks have become a hot topic over the last decade, put to work on jobs from recognizing image content to generating text and even playing video games. However, these artificial neural ...
- Predicting dementia using neural network characteristics
In a study recently published in Dementia and Geriatric Cognitive Disorders, researchers from the University of Tsukuba have revealed changes in the cerebral neural network that could function as ...
Go deeper with Google Headlines on:
Binarized neural networks
[google_news title=”” keyword=”binarized neural networks” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
BNN research
- 'Made-in-Canada system' keeps egg supply stable. But is it also keeping prices high?
Canada's egg industry appears to be quietly sidestepping widespread shortages and wildly spiking prices affecting other countries, and some say supply management is to thank.
- Research Centers
The Smithsonian is one of the world’s foremost research centers in science, the arts, and the humanities. In addition to research pursued by the museums, the following facilities specialize in areas ...
- Ackman Says Banks Face Too Much Liability Exposure on Adani Deal
Investor Bill Ackman doubled down on his criticism of Adani Group, saying that there’s just too much liability exposure for the banks involved in the Indian company’s equity sale.
- National Narcotics Agency chief says he will never support medical marijuana in Indonesia
He’s supposed to say it, but a statement by the National Narcotics Agency (BNN) chief nevertheless represents a minor setback for medical marijuana in Indonesia.
- Cancer Research UK
Cancer is relentless. But so are we. Whether you fundraise, pledge to leave a gift in your will or donate. Every part supports life-saving research. Play your part and together we will beat cancer. If ...
Go deeper with Google Headlines on:
BNN research
[google_news title=”” keyword=”BNN research” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]