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

2 months ago

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.

Source:New York University
Original Link:https://www.sciencedaily.com/releases/2025/05/250519131553.htm
Related Topics:
Continue Reading

Artificial Intelligence

Scientists Uncover the Secret to AI’s Language Understanding: A Phase Transition in Neural Networks

Neural networks first treat sentences like puzzles solved by word order, but once they read enough, a tipping point sends them diving into word meaning instead—an abrupt “phase transition” reminiscent of water flashing into steam. By revealing this hidden switch, researchers open a window into how transformer models such as ChatGPT grow smarter and hint at new ways to make them leaner, safer, and more predictable.
Avatar photo

Published

4 days ago

on

July 10, 2025

By

The ability of artificial intelligence systems to engage in natural conversations is a remarkable feat. However, despite this progress, the internal processes that lead to such results remain largely unknown. A recent study published in the Journal of Statistical Mechanics: Theory and Experiment (JSTAT) has shed light on this mystery. The research reveals that when small amounts of data are used for training, neural networks initially rely on the position of words in a sentence. However, as the system is exposed to enough data, it transitions to a new strategy based on the meaning of the words.

This transition occurs abruptly, once a critical data threshold is crossed – much like a phase transition in physical systems. The findings offer valuable insights into understanding the workings of these models. Just as a child learning to read starts by understanding sentences based on the positions of words, a neural network begins its journey by relying on word positions. However, as it continues to learn and train, the network “keeps going to school” and develops a deeper understanding of word meanings.

This shift is a critical discovery in the field of artificial intelligence. The researchers used a simplified model of self-attention mechanism – a core building block of transformer language models. These models are designed to process sequences of data, such as text, and form the backbone of many modern language systems.

The study’s lead author, Hugo Cui, explains that the network can use two strategies: one based on word positions and another on word meanings. Initially, the network relies on word positions, but once a certain threshold is crossed, it abruptly shifts to relying on meaning-based strategies. This transition is likened to a phase transition in physical systems, where the system undergoes a sudden, drastic change.

Understanding this phenomenon from a theoretical viewpoint is essential. The researchers emphasize that their findings can provide valuable insights into making neural networks more efficient and safer to use. The study’s results are published in JSTAT as part of the Machine Learning 2025 special issue and included in the proceedings of the NeurIPS 2024 conference.

The research by Cui, Behrens, Krzakala, and Zdeborová, titled “A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention,” offers new knowledge that can be used to improve the performance and safety of artificial intelligence systems. The study’s findings have significant implications for the development of more efficient and effective language models, ultimately leading to advancements in natural language processing and understanding.

Continue Reading

Artificial Intelligence

The Quantum Drumhead Revolution: A Breakthrough in Signal Transmission with Near-Perfect Efficiency

Researchers have developed an ultra-thin drumhead-like membrane that lets sound signals, or phonons, travel through it with astonishingly low loss, better than even electronic circuits. These near-lossless vibrations open the door to new ways of transferring information in systems like quantum computers or ultra-sensitive biological sensors.
Avatar photo

Published

6 days ago

on

July 8, 2025

By

The Niels Bohr Institute at the University of Copenhagen has made a groundbreaking discovery that could revolutionize the way we transmit information. Researchers, in collaboration with the University of Konstanz and ETH Zurich, have successfully sent vibrations through an ultra-thin drumhead, measuring only 10 mm wide, with astonishingly low loss – just one phonon out of a million. This achievement is even more impressive than electronic circuit signal handling.

The drumhead, perforated with many triangular holes, utilizes the concept of phonons to transmit signals. Phonons are essentially sound waves that travel through solid materials by vibrating atoms and pushing each other. This phenomenon is not unlike encoding a message and sending it through a material, where signal loss can occur due to various factors like heat or incorrect vibrations.

The researchers’ success lies in achieving almost lossless transmission of signals through the membrane. The reliability of this platform for sending information is incredibly high, making it a promising candidate for future applications. To measure the loss, researchers directed the signal through the material and around the holes, observing that the amplitude decreased by only about one phonon out of a million.

This achievement has significant implications for quantum research. Building a quantum computer requires super-precise transfer of signals between its different parts. The development of sensors capable of measuring the smallest biological fluctuations in our own body also relies heavily on signal transfer. As Assistant Professor Xiang Xi and Professor Albert Schliesser explain, their current focus is on exploring further possibilities with this method.

“We want to experiment with more complex structures and see how phonons move around them or collide like cars at an intersection,” says Albert Schliesser. “This will give us a better understanding of what’s ultimately possible and what new applications there are.” The pursuit of basic research is about producing new knowledge, and this discovery is a testament to the power of scientific inquiry.

In conclusion, the quantum drumhead revolution has brought us one step closer to achieving near-perfect signal transmission. As researchers continue to explore the possibilities of this method, we can expect exciting breakthroughs in various fields, ultimately leading to innovative applications that will transform our understanding of the world.

Continue Reading

Computer Modeling

Scientists Crack Code to Simulate Quantum Computations, Paving Way for Robust Quantum Computers

A multinational team has cracked a long-standing barrier to reliable quantum computing by inventing an algorithm that lets ordinary computers faithfully mimic a fault-tolerant quantum circuit built on the notoriously tricky GKP bosonic code, promising a crucial test-bed for future quantum hardware.
Avatar photo

Published

1 week ago

on

July 3, 2025

By

The researchers have successfully simulated quantum computations with an error correction code known as the Gottesman-Kitaev-Preskill (GKP) code. This code is commonly used in leading implementations of quantum computers and allows for the correction of errors without destroying the quantum information.

The method developed by the researchers consists of an algorithm capable of simulating quantum computations using a bosonic code, specifically the GKP code. This achievement has been deemed impossible until now due to the immense complexity of quantum computations.

“We have discovered a way to simulate a specific type of quantum computation where previous methods have not been effective,” says Cameron Calcluth, PhD in Applied Quantum Physics at Chalmers and first author of the study published in Physical Review Letters. “This means that we can now simulate quantum computations with an error correction code used for fault tolerance, which is crucial for being able to build better and more robust quantum computers in the future.”

The researchers’ breakthrough has far-reaching implications for the development of stable and scalable quantum computers, which are essential for solving complex problems in various fields. The new method will enable researchers to test and validate a quantum computer’s calculations more reliably, paving the way for the creation of truly reliable quantum computers.

The article Classical simulation of circuits with realistic odd-dimensional Gottesman-Kitaev-Preskill states has been published in Physical Review Letters. The authors are Cameron Calcluth, Giulia Ferrini, Oliver Hahn, Juani Bermejo-Vega, and Alessandro Ferraro.

Continue Reading

Trending