Återgå till huvudnavigering Återgå till sök Gå direkt till huvudinnehållet

Beskrivning

Artificial Intelligence (AI) has revolutionized countless domains, but its growing energy footprint poses a critical challenge. The primary bottleneck lies in data movement - shuttling information between memory and processors consumes far more energy than computation itself. In contrast, the human brain achieves remarkable efficiency by computing where the data resides. Neuromorphic technology takes inspiration from this principle, rethinking the computer architecture to suit the heavy data loads of AI. By leveraging materials with memory properties, such as memristors, we can enable analog, in-memory computation that drastically reduces energy costs. This talk explores how neuromorphic hardware can disrupt conventional AI processing and why success will depend on a co-design approach, requiring interdisciplinary teams integrating expertise in materials science, circuits and system architecture, and algorithm development. We will outline our current effort (NeuTec) which will bring together Swedish neuromorphic researchers at all technology levels, bridging disciplines and forming common visions, with the ultimate goal for Sweden to lead in a new era of sustainable, brain-inspired computing.
Period2025 dec. 10
Typ av evenemangSeminarium
PlatsLund, SverigeVisa på karta
OmfattningNationell