Researchers at the University of Surrey have developed a groundbreaking brain-inspired artificial intelligence (AI) model that could drastically cut energy use while improving performance. The study, published in Neurocomputing, introduces a new method called Topographical Sparse Mapping (TSM), which mimics how neurons in the human brain connect efficiently.
🇨🇳China unveils world’s first brain-like AI Model SpikingBrain1.0
Upto 100X faster while being trained on less than 2% of the data typically required.
Designed to mimic human brain functionality, uses much less energy. A new paradigm in efficiency and hardware independence.… https://t.co/X6j8IV6EAK pic.twitter.com/8NA1PE4fkU
— Rohan Paul (@rohanpaul_ai) September 11, 2025
Unlike traditional deep-learning models that link every neuron to all others, wasting huge amounts of energy, TSM connects neurons only to nearby or related ones, mirroring how the brain’s visual system processes information. An advanced version, Enhanced TSM (ETSM), also imitates the brain’s pruning process, refining neural links as learning progresses.
The new model achieved up to 99% sparsity, meaning it removed nearly all redundant connections while maintaining or even improving accuracy. According to Dr. Roman Bauer, the system uses less than 1% of the energy consumed by conventional AI models, offering a major step toward sustainable, efficient artificial intelligence.
You May Like To Read: UK Anti-Islamophobia Chief Shares Personal Experience of Discrimination Amid Rising Hate Incidents
Check out our latest video:
