The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) Brain-Inspired Hardware and Algorithm Co-Design with Melika Payvand - #585
15 snips
Aug 1, 2022 
Melika Payvand, a research scientist at the Institute of Neuroinformatics in Zurich, shares her expertise on brain-inspired hardware and algorithm co-design. She discusses how neuromorphic engineering mimics brain architecture to enhance AI efficiency while tackling challenges in online learning algorithms. The conversation highlights the integration of neural networks with innovative memory technologies, coordinates scalability issues, and explores the future potential of brain-inspired tech in practical applications. Get ready for a thrilling dive into the world of low-power AI!
AI Snips
Chapters
Transcript
Episode notes
Brain-Inspired Hardware
- Memristive devices, like synapses, enable co-location of memory and processing, unlike von Neumann architecture.
- This co-location significantly reduces energy consumption by minimizing data shuttling.
Memristors and Synapses
- Memristive devices resemble synapses by acting as conductances that change with electrical pulses, similar to how brains process information with spikes.
- This brain-inspired approach enables efficient online learning by adapting to incoming sensory information.
Applications of Memristive Devices
- Melika Payvand collaborates with a lab in France to develop memristive devices for biomedical signal processing.
- Target applications include personalized medicine, always-on monitoring, and keyword spotting.