AI applications like ChatGPT are energy-intensive due to their reliance on standard artificial neural networks. A recent study suggests that spiking neurons, which mimic the way biological neurons communicate, could offer a more energy-efficient alternative. While training spiking neurons has been challenging in the past, this new research indicates that standard training methods may be adaptable to these networks, paving the way for more sustainable AI development.
AI applications like ChatGPT are based on artificial neural networks that, in many respects, imitate the nerve cells in our brains. They are trained with vast quantities of data on high-performance computers, gobbling up massive amounts of energy in the process. Spiking neurons, which are much less energy-intensive, could be one solution to this problem. In the past, however, the normal techniques used to train them only worked with significant limitations.
"Biological neurons do things differently," explains Professor Raoul-Martin Memmesheimer from the Institute of Genetics at the University of Bonn."They communicate with the help of short voltage pulses, known as action potentials or spikes." These occur fairly rarely, so the networks get by on much less energy." Developing artificial neural networks that also"spike" in this way is thus an important field in AI research.
Whereas it was previously assumed that the usual training method would prove highly problematic for spiking networks, the latest study has now shown this not to be the case."We found that, in some standard neuron models, the spikes can't simply appear or disappear just like that. Instead, all they can essentially do is be brought forward or pushed back in time," Klos explains.
AI Artificial Intelligence Spiking Neurons Energy Efficiency Neural Networks
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Researchers discover new neurons that suppress food intakeResearchers have discovered a new population of neurons that is responsive to the hormone leptin. Leptin responsive neurons are important in obesity since leptin is sent to the brain from the body's fat stores to suppress hunger.
Read more »
Ariana Madix Advises New Vanderpump Rules Cast to 'Forge Their Own Path'Ariana Madix encourages the new cast of Vanderpump Rules to be themselves and create their own unique storylines, rather than trying to emulate the original cast.
Read more »
Vanderpump Rules New Cast Encouraged to Forge Their Own PathAriana Madix advises the new Vanderpump Rules cast to differentiate themselves from the originals. Lisa Vanderpump anticipates a fresh energy for season 12, acknowledging the need for a change after the long run of the original cast.
Read more »
New Orleans Attack Suspect's Path to RadicalizationShamsud-Din Jabbar, the suspect in the New Orleans attack, had a successful life in Texas before the tragedy. He faced pressures like a third divorce and struggling businesses. Authorities believe the attack, which killed 14 and injured 30, was inspired by ISIS. Jabbar posted videos aligning himself with the group before the attack.
Read more »
Path of Exile: New Update Focuses on Bug FixesGrinding Gear Games releases a new update for Path of Exile, primarily addressing gameplay, monster, and ability-related bugs.
Read more »
Chainsaw Man: The New Power Trio Offers a Darker Path ForwardWhile Denji's relationships with Pochita and Makima were central in Chainsaw Man Part 1, his bond with Power and Aki Hayakawa provided a crucial sense of family. Part 2 introduces a new trio: Asa Mitaka and Hirofumi Yoshida, who mirror the roles of Power and Aki respectively, but with added complexities and hidden agendas. This new dynamic offers a more nuanced and potentially dangerous path for Denji's development.
Read more »