
A novel proof that certain quantum convolutional networks can be guaranteed to be trained clears the way for quantum artificial intelligence to aid in materials discovery and many other applications
CREDIT: Los Alamos National Laboratory
Novel theorem demonstrates convolutional neural networks can always be trained on quantum computers, overcoming threat of ‘barren plateaus’ in optimization problems
Convolutional neural networks running on quantum computers have generated significant buzz for their potential to analyze quantum data better than classical computers can. While a fundamental solvability problem known as “barren plateaus” has limited the application of these neural networks for large data sets, new research overcomes that Achilles heel with a rigorous proof that guarantees scalability.
“The way you construct a quantum neural network can lead to a barren plateau—or not,” said Marco Cerezo, coauthor of the paper titled “Absence of Barren Plateaus in Quantum Convolutional Neural Networks,” published today by a Los Alamos National Laboratory team in Physical Review X. Cerezo is a physicist specializing in quantum computing, quantum machine learning, and quantum information at Los Alamos. “We proved the absence of barren plateaus for a special type of quantum neural network. Our work provides trainability guarantees for this architecture, meaning that one can generically train its parameters.”
As an artificial intelligence (AI) methodology, quantum convolutional neural networks are inspired by the visual cortex. As such, they involve a series of convolutional layers, or filters, interleaved with pooling layers that reduce the dimension of the data while keeping important features of a data set.
These neural networks can be used to solve a range of problems, from image recognition to materials discovery. Overcoming barren plateaus is key to extracting the full potential of quantum computers in AI applications and demonstrating their superiority over classical computers.
Until now, Cerezo said, researchers in quantum machine learning analyzed how to mitigate the effects of barren plateaus, but they lacked a theoretical basis for avoiding it altogether. The Los Alamos work shows how some quantum neural networks are, in fact, immune to barren plateaus.
“With this guarantee in hand, researchers will now be able to sift through quantum-computer data about quantum systems and use that information for studying material properties or discovering new materials, among other applications,” said Patrick Coles, a quantum physicist at Los Alamos and a coauthor of the paper.
Many more applications for quantum AI algorithms will emerge, Coles thinks, as researchers use near-term quantum computers more frequently and generate more and more data—all machine learning programs are data-hungry.
Avoiding the Vanishing Gradient
“All hope of quantum speedup or advantage is lost if you have a barren plateau,” Cerezo said.
The crux of the problem is a “vanishing gradient” in the optimization landscape. The landscape is composed of hills and valleys, and the goal is to train the model’s parameters to find the solution by exploring the geography of the landscape. The solution usually lies at the bottom of the lowest valley, so to speak. But in a flat landscape one cannot train the parameters because it’s difficult to determine which direction to take.
That problem becomes particularly relevant when the number of data features increases. In fact, the landscape becomes exponentially flat with the feature size. Hence, in the presence of a barren plateau, the quantum neural network cannot be scaled up.
The Los Alamos team developed a novel graphical approach for analyzing the scaling within a quantum neural network and proving its trainability.
For more than 40 years, physicists have thought quantum computers would prove useful in simulating and understanding quantum systems of particles, which choke conventional classical computers. The type of quantum convolutional neural network that the Los Alamos research has proved robust is expected to have useful applications in analyzing data from quantum simulations.
“The field of quantum machine learning is still young,” Coles said. “There’s a famous quote about lasers, when they were first discovered, that said they were a solution in search of a problem. Now lasers are used everywhere. Similarly, a number of us suspect that quantum data will become highly available, and then quantum machine learning will take off.”
For instance, research is focusing on ceramic materials as high-temperature superconductors, Coles said, which could improve frictionless transportation, such as magnetic levitation trains. But analyzing data about the material’s large number of phases, which are influenced by temperature, pressure, and impurities in these materials, and classifying the phases is a huge task that goes beyond the capabilities of classical computers.
Using a scalable quantum neural network, a quantum computer could sift through a vast data set about the various states of a given material and correlate those states with phases to identify the optimal state for high-temperature superconducting.
Original Article: Breakthrough proof clears path for quantum AI
More from: Los Alamos National Laboratory
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Convolutional neural networks
- Deep learning-designed diffractive processor computes hundreds of transformations in parallel
In today's digital age, computational tasks have become increasingly complex. This, in turn, has led to an exponential growth in the power consumed by digital computers. Thus, it is necessary to ...
- How hybrid cybersecurity is strengthened by AI, machine learning and human intelligence
Human intelligence combined with AI and ML models enable hybrid cybersecurity to better predict, identify and stop security breaches.
- What Is a Convolutional Neural Network (CNN) and How Does It Work?
Here's everything you need to know about convolutional neural networks, from how they work to their various applications.
- AI Beats Humans in Predicting Cancer Treatment Outcomes
A new study published in IEEE Journal of Translational Engineering in Health and Medicine demonstrates how an AI method can predict therapy outcomes in patients with brain metastases—cancer that has ...
- New AI Listens to Toilet Sounds to Detect Diarrhea
Georgia Tech engineers have developed AI that can identify diarrhea with up to 98% accuracy and could help us catch disease outbreaks early.
Go deeper with Google Headlines on:
Convolutional neural networks
[google_news title=”” keyword=”convolutional neural networks” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Quantum neural networks
- Challenging questions, practical benefits and financial rewards: why medical physics has it all
Latest Explore all the latest news and information on Physics World; Research updates Keep track of the most exciting research breakthroughs and technology innov ...
- New quantum computing architecture could be used to connect large-scale devices
Researchers have demonstrated an architecture that can enable high fidelity and scalable communication between superconducting quantum processors. Their technique can generate and route photons, which ...
- Researchers Present New Analysis of On-Chip Lasers
Internet traffic by global consumers increased four-fold between 2017 and 2022 with a 31% compound annual growth rate. It will attain 4.8 ZB yearly by 2022, or 396 Exabytes (EB) every month.
- Physicists discover completely new type of quantum entanglement
Physicists at Brookhaven National Laboratory (BNL) have discovered a completely new type of quantum entanglement, the spooky phenomenon that binds particles across any distance. In particle collider ...
- New quantum computing architecture could be used to connect large-scale devices
Their method ensures quantum information flows in the correct direction more than 96 percent of the time. Linking several of these modules enables a larger network of quantum processors that are ...
Go deeper with Google Headlines on:
Quantum neural networks
[google_news title=”” keyword=”quantum neural networks” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]