Connect with us
We’re experimenting with AI-generated content to help deliver information faster and more efficiently.
While we try to keep things accurate, this content is part of an ongoing experiment and may not always be reliable.
Please double-check important details — we’re not responsible for how the information is used.

Computer Modeling

“From Kindergarten to Complex Tasks: How ‘Basic Skills’ Enhance AI Learning”

We need to learn our letters before we can learn to read and our numbers before we can learn how to add and subtract. The same principles are true with AI, a team of scientists has shown through laboratory experiments and computational modeling. In their work, researchers found that when recurrent neural networks (RNNs) are first trained on simple cognitive tasks, they are better equipped to handle more difficult and complex ones later on.

Avatar photo

Published

on

The content:

From Kindergarten to Complex Tasks: How ‘Basic Skills’ Enhance AI Learning

Imagine you’re trying to learn a new language or how to play a musical instrument. You wouldn’t start with the intricacies of grammar rules or complicated melodies, would you? Instead, you’d begin with the basics – learning your alphabet, simple sentences, and basic chords. The same principles are true for artificial intelligence (AI), as a team of researchers from New York University has demonstrated through laboratory experiments and computational modeling.

In their work, published in the journal Nature Machine Intelligence, the scientists found that when recurrent neural networks (RNNs) are first trained on simple cognitive tasks, they are better equipped to handle more difficult and complex ones later on. They labeled this form of training ‘kindergarten curriculum learning’ as it centers on first instilling an understanding of basic tasks and then combining knowledge of these tasks in carrying out more challenging ones.

“From very early on in life, we develop a set of basic skills like maintaining balance or playing with a ball,” explains Cristina Savin, an associate professor in NYU’s Center for Neural Science and Center for Data Science. “With experience, these basic skills can be combined to support complex behavior – for instance, juggling several balls while riding a bicycle.”

The researchers took these principles to enhance the capabilities of RNNs, which first learn a series of easy tasks, store this knowledge, and then apply a combination of these learned tasks to successfully complete more sophisticated ones. This approach proved to be effective in improving the performance of RNNs in complex cognitive tasks.

To test their theory, the scientists conducted a series of experiments with laboratory rats. The animals were trained to seek out a water source in a box with several compartmentalized ports. However, in order to know when and where the water would be available, the rats needed to learn that delivery of the water was associated with certain sounds and the illumination of the port’s lights – and that the water was not delivered immediately after these cues.

In order to reach the water, then, the animals needed to develop basic knowledge of multiple phenomena (e.g., sounds precede water delivery, waiting after the visual and audio cues before trying to access the water) and then learn to combine these simple tasks in order to complete a goal (water retrieval). These results pointed to principles of how the animals applied knowledge of simple tasks in undertaking more complex ones.

The scientists took these findings to train RNNs in a similar fashion – but, instead of water retrieval, the RNNs managed a wagering task that required these networks to build upon basic decision making in order to maximize the payoff over time. They then compared this kindergarten curriculum learning approach to existing RNN-training methods.

Overall, the team’s results showed that the RNNs trained on the kindergarten model learned faster than those trained on current methods. “AI agents first need to go through kindergarten to later be able to better learn complex tasks,” observes Savin. “Overall, these results point to ways to improve learning in AI systems and call for developing a more holistic understanding of how past experiences influence learning of new skills.”

This research was funded by grants from the National Institute of Mental Health (1R01MH125571-01, 1K01MH132043-01A1) and conducted using research computing resources of the Empire AI consortium, with support from the State of New York, the Simons Foundation, and the Secunda Family Foundation.

Computational Biology

A Quantum Leap Forward – New Amplifier Boosts Efficiency of Quantum Computers 10x

Chalmers engineers built a pulse-driven qubit amplifier that’s ten times more efficient, stays cool, and safeguards quantum states—key for bigger, better quantum machines.

Avatar photo

Published

on

By

Quantum computers have long been touted as revolutionary machines capable of solving complex problems that stymie conventional supercomputers. However, their full potential has been hindered by the limitations of qubit amplifiers – essential components required to read and interpret quantum information. Researchers at Chalmers University of Technology in Sweden have taken a significant step forward with the development of an ultra-efficient amplifier that reduces power consumption by 90%, paving the way for more powerful quantum computers with enhanced performance.

The new amplifier is pulse-operated, meaning it’s activated only when needed to amplify qubit signals, minimizing heat generation and decoherence. This innovation has far-reaching implications for scaling up quantum computers, as larger systems require more amplifiers, leading to increased power consumption and decreased accuracy. The Chalmers team’s breakthrough offers a solution to this challenge, enabling the development of more accurate readout systems for future generations of quantum computers.

One of the key challenges in developing pulse-operated amplifiers is ensuring they respond quickly enough to keep pace with qubit readout. To address this, the researchers employed genetic programming to develop a smart control system that enables rapid response times – just 35 nanoseconds. This achievement has significant implications for the future of quantum computing, as it paves the way for more accurate and powerful calculations.

The new amplifier was developed in collaboration with industry partners Low Noise Factory AB and utilizes the expertise of researchers at Chalmers’ Terahertz and Millimeter Wave Technology Laboratory. The study, published in IEEE Transactions on Microwave Theory and Techniques, demonstrates a novel approach to developing ultra-efficient amplifiers for qubit readout and offers promising prospects for future research.

In conclusion, the development of this highly efficient amplifier represents a significant leap forward for quantum computing. By reducing power consumption by 90%, researchers have opened doors to more powerful and accurate calculations, unlocking new possibilities in fields such as drug development, encryption, AI, and logistics. As the field continues to evolve, it will be exciting to see how this innovation shapes the future of quantum computing.

Continue Reading

Artificial Intelligence

AI Uncovers Hidden Heart Risks in CT Scans: A Game-Changer for Cardiovascular Care

What if your old chest scans—taken years ago for something unrelated—held a secret warning about your heart? A new AI tool called AI-CAC, developed by Mass General Brigham and the VA, can now comb through routine CT scans to detect hidden signs of heart disease before symptoms strike.

Avatar photo

Published

on

The Massachusetts General Brigham researchers have developed an innovative artificial intelligence (AI) tool called AI-CAC to analyze previously collected CT scans and identify individuals with high coronary artery calcium (CAC) levels, indicating a greater risk for cardiovascular events. Their research, published in NEJM AI, demonstrated the high accuracy and predictive value of AI-CAC for future heart attacks and 10-year mortality.

Millions of chest CT scans are taken each year, often in healthy people, to screen for lung cancer or other conditions. However, this study reveals that these scans can also provide valuable information about cardiovascular risk, which has been going unnoticed. The researchers found that AI-CAC had a high accuracy rate (89.4%) at determining whether a scan contained CAC or not.

The gold standard for quantifying CAC uses “gated” CT scans, synchronized to the heartbeat to reduce motion during the scan. However, most chest CT scans obtained for routine clinical purposes are “nongated.” The researchers developed AI-CAC, a deep learning algorithm, to probe through these nongated scans and quantify CAC.

The AI-CAC model was 87.3% accurate at determining whether the score was higher or lower than 100, indicating a moderate cardiovascular risk. Importantly, AI-CAC was also predictive of 10-year all-cause mortality, with those having a CAC score over 400 having a 3.49 times higher risk of death over a 10-year period.

The researchers hope to conduct future studies in the general population and test whether the tool can assess the impact of lipid-lowering medications on CAC scores. This could lead to the implementation of AI-CAC in clinical practice, enabling physicians to engage with patients earlier, before their heart disease advances to a cardiac event.

As Dr. Raffi Hagopian, first author and cardiologist at the VA Long Beach Healthcare System, emphasized, “Using AI for tasks like CAC detection can help shift medicine from a reactive approach to the proactive prevention of disease, reducing long-term morbidity, mortality, and healthcare costs.”

Continue Reading

Computer Modeling

Harnessing True Randomness from Entangled Photons: The Colorado University Randomness Beacon (CURBy)

Scientists at NIST and the University of Colorado Boulder have created CURBy, a cutting-edge quantum randomness beacon that draws on the intrinsic unpredictability of quantum entanglement to produce true random numbers. Unlike traditional methods, CURBy is traceable, transparent, and verifiable thanks to quantum physics and blockchain-like protocols. This breakthrough has real-world applications ranging from cybersecurity to public lotteries—and it’s open source, inviting the world to use and build upon it.

Avatar photo

Published

on

By

The Colorado University Randomness Beacon (CURBy) is a pioneering service that harnesses the true randomness of entangled photons to produce unguessable strings of numbers. This breakthrough was made possible by the work of scientists at the National Institute of Standards and Technology (NIST) and their colleagues at the University of Colorado Boulder.

“True randomness is something that nothing in the universe can predict in advance,” said Krister Shalm, a physicist at NIST. “If God does play dice with the universe, then you can turn that into the best random number generator that the universe allows.”

The CURBy system uses a Bell test to measure pairs of entangled photons whose properties are correlated even when separated by vast distances. When researchers measure an individual particle, the outcome is random, but the properties of the pair are more correlated than classical physics allows, enabling researchers to verify the randomness.

This is the first random number generator service to use quantum nonlocality as a source of its numbers, and the most transparent source of random numbers to date. The results are certifiable and traceable to a greater extent than ever before.

The CURBy system consists of a nonlinear crystal that generates entangled photons, which travel via optical fiber to separate labs at opposite ends of the hall. Once the photons reach the labs, their polarizations are measured. The outcomes of these measurements are truly random.

NIST passes millions of these quantum coin flips to a computer program at the University of Colorado Boulder, where special processing steps and strict protocols are used to turn the outcomes into 512 random bits of binary code (0s and 1s). The result is a set of random bits that no one, not even Einstein, could have predicted.

The CURBy system has been operational for several months now, with an impressive success rate of over 99.7%. The ability to verify the data behind each random number was made possible by the Twine protocol, a novel set of quantum-compatible blockchain technologies developed by NIST and its collaborators.

“The Twine protocol lets us weave together all these other beacons into a tapestry of trust,” said Jasper Palfree, a research assistant on the project at the University of Colorado Boulder. This allows any user to verify the data behind each random number, providing security and traceability.

The CURBy system can be used anywhere an independent, public source of random numbers would be useful, such as selecting jury candidates, making a random selection for an audit, or assigning resources through a public lottery.

“I wanted to build something that is useful. It’s this cool thing that is the cutting edge of fundamental science,” said Gautam Kavuri, a graduate student on the project. The whole process is open source and available to the public, allowing anyone to not only check their work but even build on the beacon to create their own random number generator.

The CURBy system has the potential to revolutionize fields such as cryptography, gaming, and finance, where true randomness is essential. By harnessing the power of entangled photons, scientists have created a truly independent source of random numbers that can be trusted.

Continue Reading

Trending