In this episode Sunny talks to Prof Shih-Chii Liu, co-director of the Sensors Group at the Institute of Neuroinformatics (INI)—part of both the ETH and the University of Zurich, Switzerland. Shih-Chii is a researcher with more than three decades in neuromorphic engineering. She has helped build the field through her direct research and teaching, but also through helping to lead community-building projects like the Telluride and Capo Caccia workshops. You’ll hear her talk about neuromorphic cochlea, sparsity and deep networks, and what it will take for the technology to solve real problems in industry. Discussion follows with Giulia and Ralph.
Articles and Papers
- Winner of the 2020 Misha Mahowald Prize for Neuromorphic Engineering
- Robustness of spiking deep belief networks to noise and reduced bit precision of neuro-inspired hardware platforms
- Conversion of continuous-valued deep networks to efficient event-driven networks for image classification
- Delta Networks for Optimized Recurrent Network Computation
From the Discussion
- Object-based analog VLSI vision circuits
- The neurophysiology of figure-ground segregation in primary visual cortex
- Figure-ground organization in natural scenes: performance of a recurrent neural model compared with neurons of area V2
- A model of saliency-based visual attention for rapid scene analysis
- A model of proto-object based saliency
- Focal-plane analog VLSI cellular implementation of the boundary contour system
- On bottlenecks, Helmholtz and hearing
- Improved implementation of the silicon cochlea
- A 126-μW cochlear chip for a totally implantable system
- A silicon model of amplitude modulation detection in the auditory brainstem
- Micropower gradient flow acoustic localizer
- Blind separation of auditory event-related brain responses into independent components
- Learning the higher-order structure of a natural sound
- Modelling auditory attention
- Real-time decomposition and recognition of acoustical patterns with an analog neural computer
- Real time feature extraction of acoustic signals with an analog neural computer
- Multiplicative gain modulation arises through unsupervised learning in a predictive coding model of cortical function
Episode Credits
Producer/Writer: Sunny Bains
Co-hosts: Sunny Bains and Giulia D’Angelo
Commentator: Ralph Etienne-Cummings
Editor: Rose Gotto
Audio Production: Taylor Marvin, Coupe Studios Music and Sound Design
Music: 3 of Diamonds by Matt Harris
For EETimes.com
This episode is produced in conjunction with EETimes. Podcast reproduced with permission.
