The team, led by Hava Siegelmann, Provost Professor at the Manning College of Information and Computer Sciences, confronts a paradox that has long hampered the expansion of AI capabilities: the insatiable energy demands of ever-growing, highly synchronized neural networks. While contemporary AI models such as ChatGPT and Claude exhibit astounding computational feats, they do so by relying on synchronous updates coordinated through a global clock, inevitably resulting in energy consumption on the order of millions of watts. This complexity and energy cost have become a drastic bottleneck for deploying autonomous and embedded AI systems at scale.

One of the fundamental insights driving Siegelmann’s research is the striking contrast between artificial neural networks and the biological brain. The human brain, with its nearly 86 billion neurons firing asynchronously and selectively, manages to perform immensely complex cognitive tasks while consuming only about 20 watts of power—comparable to the energy usage of a small LED bulb. This ability arises from neurons updating independently, activating only as needed for the task at hand, thus avoiding the global synchronization overhead that plagues standard AI architectures. Emulating this asynchronous dynamism has been a longstanding but elusive goal within computational neuroscience and machine learning.

Existing attempts to harness asynchronous spiking neural networks have stumbled over significant practical hurdles, primarily because these biologically inspired models have not supported efficient training methods. Traditional backpropagation and other gradient-based techniques, which enable modern deep neural networks’ remarkable learning capabilities, are ill-suited to the irregular timing and event-driven nature of spiking neurons. As a result, the AI community has wrestled with a tradeoff, forced to choose between energy-efficient but less adaptable spiking models and computationally powerful but energy-intensive synchronized networks.

Siegelmann’s team broke new ground by introducing Asynchronous Neural Turing networks, or ANT—a novel neural architecture that integrates the adaptive power of differentiable deep networks with the energy efficiency of asynchronous processing. ANT dispenses with the central coordinating clock, allowing neural units to update independently in response to pertinent stimuli, much like biological neurons, while maintaining compatibility with gradient-based training methods. This approach requires revolutionary design principles to ensure that asynchronous updating does not disrupt information flow or learning capacity—challenges that Siegelmann’s group has impressively overcome.

The benefits of this architecture are both theoretical and practical. By restricting computation to only those neurons essential to the immediate cognitive function, ANT systems can dramatically reduce power consumption by orders of magnitude. In theory, this efficiency does not compromise computational capability—in fact, ANT potentially matches the prowess of conventional digital systems and state-of-the-art deep learning frameworks, all while enabling real-time, continuous learning. This breakthrough directly addresses the escalating environmental footprint of AI research and deployment, especially as models scale to trillions of parameters.

The conceptual underpinnings of ANT are anchored in Siegelmann’s foundational work from the mid-1990s, when she demonstrated that recurrent neural networks could attain the computational equivalence of Turing machines, a seminal finding linking machine learning architectures to classical computation theory. Building on decades of expertise in neural computation, the Siegelmann lab’s innovation marries theoretical rigor with practical applicability, fostering a new class of energy-aware neural networks primed for next-generation AI applications.

The implications extend far beyond academic curiosity. With energy efficiency at a premium for autonomous robotics, edge computing devices, and self-driving vehicles, ANT architectures could enable these machines to operate sustainably in environments where power resources are limited or costly. Moreover, by facilitating continuous online learning free from rigid training phases, this approach promises smarter, more adaptable systems capable of learning and evolving within their operational contexts without prohibitive energy costs.

Siegelmann’s team is actively advancing the ANT framework, focusing on enhancing real-time learning capabilities and pushing the boundaries of energy efficiency even further. Their work is poised to inspire a paradigm shift across AI research, promoting systems that not only mitigate environmental impact but also improve adaptability and autonomy in ways previously constrained by synchronous computation.

As AI’s role broadens in society and industry, the urgency of developing sustainable, scalable, and capable architectures cannot be overstated. ANT represents a crucial step toward reconciling AI’s extraordinary promise with the practical realities of power consumption and environmental stewardship. The research, supported by the U.S. National Science Foundation and the Air Force Office of Scientific Research, invites the global scientific community to rethink core assumptions about AI design and operation.

In summary, the ANT framework embodies a transformative vision for AI: one where intelligence is not sacrificed at the altar of energy efficiency, and where learning is continuous, dynamic, and more brain-like than ever before. By realigning artificial intelligence with the principles that make biological computation so efficient, Siegelmann and her collaborators herald an era of smarter, greener AI poised to meet the challenges of tomorrow.

Subject of Research: Energy-efficient Artificial Intelligence inspired by asynchronous neural computation

Article Title: “Energy-Efficient Asynchronous Neural Turing Networks for Continuous Real-Time AI Learning”

News Publication Date: June 5, 2026

Web References:
https://doi.org/10.1038/s41467-026-73830-6
https://www.cics.umass.edu/about/directory/hava-siegelmann

Image Credits: UMass Amherst

Keywords

Artificial Intelligence, Energy Efficiency, Asynchronous Neural Networks, Continuous Learning, Neural Computation, ANT Architecture, Sustainable AI, Gradient-Based Learning, Autonomous Systems, Neural Turing Machines, Brain-Inspired Computing, Real-Time Adaptation

A groundbreaking study recently published in the prestigious journal Nature has unveiled significant progress in this field, showcasing collaborative efforts from leading global institutions including Politecnico di Milano, École Polytechnique Fédérale de Lausanne, Stanford University, University of Cambridge, and the Max Planck Institute. This research delves into the core challenge of training physical neural networks—an area that until now had largely been conceptual, hindered by the difficulty of adapting learning algorithms to operate within analogue physical substrates rather than traditional digital simulations.

At the heart of this innovation is the photonic microchip developed by the research team at Politecnico di Milano, which stands as a testament to the power of integrated photonic technologies. Unlike conventional electronic chips that rely on voltage and current states to represent and manipulate data, these photonic chips utilize the interference patterns of light waves to perform fundamental mathematical operations such as summations and multiplications. Remarkably, these operations occur on silicon microchips mere square millimeters in size, highlighting the extraordinary miniaturization and integration capabilities that photonics enables in hardware design.

This approach fundamentally transforms how data is processed. By bypassing the digital conversion steps that are traditionally necessary in electronic neural networks, photonic chips execute computational tasks natively in the analogue domain. According to Francesco Morichetti, the head of the Photonic Devices Lab at Politecnico di Milano, this leads to a profound reduction in both energy consumption and processing time. Such an advancement is pivotal, considering that modern AI data centers are notorious for their massive energy footprints. The capacity to perform AI computations in a more sustainable and efficient manner could redefine the environmental and economic landscape of machine learning.

Crucially, the study addresses one of the most vital aspects of neural network functionality: training. Training involves iteratively adjusting the network’s parameters until it successfully performs specific tasks or recognizes patterns in data. Traditionally, this process is computationally intensive and carried out within digital or software-based frameworks before deploying trained models onto hardware. The collaborative research introduces an innovative “in-situ” training methodology for photonic neural networks, whereby learning is conducted entirely within the physical system using light signals, without recourse to digital simulations.

This photonics-based in-situ training method embodies a paradigm shift by treating the physical network as the training medium itself. It leverages the intrinsic physics of light interference to update network weights and parameters directly on the photonic chip. Morichetti explains that this eliminates layers of data conversion and transfer between physical and digital domains, resulting in accelerated training speeds with enhanced robustness and efficiency. The potential to execute training faster, with lower latency, unlocks new possibilities for adaptive AI systems that can learn and evolve in real-time.

The implications of these advancements stretch far beyond laboratory prototypes. Photonic chips with optical neural network architectures could enable the creation of more sophisticated AI models capable of handling complex computations at the edge—on devices such as autonomous vehicles, drones, and portable sensors—without relying on centralized cloud processing. This decentralization of AI computation means systems can process real-time data locally, reducing communication lag, enhancing privacy, and improving resilience against network disruptions.

Moreover, photonic neural networks embody a confluence of multiple cutting-edge scientific disciplines, spanning applied physics, nanophotonics, optical materials, and computer science. The ability to engineer nanophotonic structures that manipulate photons with extreme precision enables the design of highly customizable neural architectures adapted for specific application domains. As research advances, this technology could birth new classes of AI hardware that operate fundamentally differently from silicon-based electronic processors, potentially surpassing them in speed, energy efficiency, and scalability.

One of the technical marvels enabling these developments is the exploitation of light interference—a phenomenon where multiple light waves overlap, amplifying or diminishing each other to yield precise mathematical outcomes on-chip. These analogue computations, inherently parallel and swift, contrast starkly with sequential electronic logic operations in conventional processors, offering significant advantages in throughput and power efficiency.

The collaborative nature of this research is also notable, bringing together experts from diverse institutions across Europe and the United States, each contributing unique expertise in photonics, AI, and applied sciences. Such interdisciplinary efforts underscore the complexity of transitioning physical neural networks from theoretical constructs to viable practical technologies. The paper, titled “Training of Physical Neural Networks,” provides a detailed commentary on the state of research in this domain and charts future pathways for overcoming remaining challenges.

In conclusion, the advent of physical neural networks powered by integrated photonic chips heralds a transformative step toward the next generation of intelligent machines. By leveraging the laws of physics to perform computational operations natively and efficiently, these systems promise to transcend the limitations of traditional digital computing architectures. Beyond merely accelerating AI workloads, they lay the groundwork for sustainable, adaptive, and decentralized intelligence embedded directly within everyday devices. The prospect of AI computations unfolding at the speed of light within miniature silicon photonic circuits marks a thrilling confluence of physics, engineering, and machine learning, poised to redefine how we conceive and deploy intelligent systems in the near future.

Subject of Research: Not applicable

Article Title: Training of physical neural networks

News Publication Date: 3-Sep-2025

Web References: DOI: 10.1038/s41586-025-09384-2

Image Credits: Politecnico di Milano, DEIB – Department of Electronics, Information and Bioengineering

Keywords

Artificial neural networks, Applied sciences and engineering, Physical sciences, Physics, Optical materials, Nanophotonics, Photonics, Applied optics, Neural net processing, Computer science, Computer processing, Generative AI, Machine learning

Neurosymbolic AI merges the strengths of traditional symbolic reasoning with the robust capabilities of data-driven neural networks. This hybrid model draws inspiration from the human brain, whose efficient operations require only about 20 watts of power while demonstrating rapid and reflective thinking. The brain’s ability to process information efficiently stands in stark contrast to the energy-hungry operations of current AI systems, which often necessitate extensive computational resources. By examining the underlying principles of cognitive functioning, researchers envision a more sustainable AI landscape where smaller entities can compete with larger corporations that currently dominate the scene.

At the core of neurosymbolic AI is the utilization of semantically meaningful symbols to structure and manipulate knowledge. These symbolic approaches—grounded in logic and mathematical principles, such as differential equations—can streamline the cognitive processes of AI systems. Rather than relying solely on vast datasets to uncover correlations, neurosymbolic models can learn foundational axioms or facts from smaller data samples. This empowers AI systems to infer related truths through the application of symbolic logic, thereby drastically reducing the volume of data and computational demands typically required for generating insights.

Consider the process in which traditional LLMs learn complex relations from considerable data inputs. The range of training necessary often leads to the consumption of resources on a monumental scale. Conversely, neurosymbolic AI offers a more efficient pathway, where AI systems can derive straightforward and profound truths—much like humans do. For instance, from an axiom such as “All men are mortal” and the fact that “Socrates is a man,” the system can ascertain the derived conclusion that “Socrates is mortal.” Such capabilities illustrate the potential of integrating symbolic reasoning with machine learning, presenting a compelling case for reducing the size and energy consumption of AI models.

Analyses conducted by Velasquez and his team suggest that neurosymbolic models could be up to 100 times smaller than contemporary leading LLMs, heralding a significant shift in the AI landscape. This qualitative change not only has the potential to democratize AI technology—allowing smaller companies and research institutions to participate—but also promotes an arena where resource allocation is far more equitable. The implications of such a shift extend beyond corporate competition; they embody a vision of technology that aligns with environmental stewardship and responsibility.

As AI researchers continue to explore the full potential of neurosymbolic AI, the prospects for enhancing trust and reliability in AI systems grow increasingly optimistic. Trust in AI technologies is paramount, especially as these systems become more integrated into everyday life. The principles underlying neurosymbolic AI support the creation of transparent and interpretable models that mirror human reasoning processes. This transparency is essential for establishing confidence in AI outputs, which can often appear opaque or enigmatic, particularly within traditional neural network frameworks.

Moreover, given the mounting concerns regarding the environmental impact of extensive computing operations, the time has come to rethink how society approaches the development and deployment of AI technologies. Neurosymbolic AI embodies a critical step toward a more sustainable model, enabling the delivery of advanced capabilities while minimizing energy consumption. As stakeholders across various sectors assess their tech-related responsibilities, the emergence of neurosymbolic AI fosters a long overdue dialogue about the ethical ramifications of artificial intelligence and its role in society.

Improvements in efficiency and sustainability are especially crucial given the rapid pace of technological advancement. As businesses rush to harness AI capabilities, harnessing the potential of neurosymbolic principles could offer a crucial lifeline in somewhat turbulent waters. Strategic advancements in this field hold the promise of creating AI systems that do not merely reflect the status quo but redefine how technology interacts with human needs and environmental concerns.

Furthermore, operationalizing neurosymbolic methodologies also beckons a reexamination of data governance and accessibility. By requiring less data to train effective models, neurosymbolic AI makes strides not only in performance but also in the ethical dimensions of data usage. This less resource-intensive approach reduces the risk of pervasive surveillance and the monopolization of data, issues that have emerged alongside the rise of AI technologies driven by large datasets.

In conclusion, as the AI industry grapples with its energy demands and ecological footprint, innovations like neurosymbolic AI present an empowering vision for the future. By championing a hybrid approach, researchers pave the way for more democratized access to AI technology that does not sacrifice environmental sustainability or ethical rigor. Embracing the principles of neurosymbolic AI could very well revolutionize the ecological narrative surrounding AI development, empowering a diverse range of contributors to engage in this transformative journey.

The implications of these advancements are boundless, marking a potential turning point in the relationship between technology and nature. It is not only a promise of sustainable AI but also a call to action for society to foster responsible innovation. As we strive to develop technology that aligns with the needs of the planet and its inhabitants, neurosymbolic AI may well become the hallmark of a new era in artificial intelligence.

Subject of Research: Neurosymbolic AI
Article Title: Neurosymbolic AI as an antithesis to scaling laws
News Publication Date: 20-May-2025
Web References:
References:
Image Credits:

Keywords

Artificial intelligence