A bit more info on the research paper I came across. The research was carried out in Zurich which I also happens to get a mention on Brainchips website.I accidentally came across this research paper whilst looking for something else. There’s no mention of Akida or any other chip. It’s a technical piece and a lot went over my head
( sorry, the bold seems to be stuck onbut very interesting in regards to medical breakthroughs. I’ve copied some relevant paragraphs highlighting the use of SNN
)
A neuromorphic spiking neural network detects epileptic high frequency oscillations in the scalp EEG
Spiking neural networks (SNN) have emerged as optimal architectures for embedding in compact low-power signal processing hardware.
This study is a further step towards non-invasive epilepsy monitoring with a low-power wearable device.
Future implementation in neuromorphic hardware
Our simulated EEG SNN has been motivated by the perspective of future implementation in neuromorphic processors that carry out computation “at the edge''47–49. The EEG SNN can be easily mapped onto the neuromorphic device that we have developed and described previously8. All parameters and architecture elements in this neuromorphic device have been carefully chosen to enable the implementation of the simulated EEG SNN in the neuromorphic hardware with only minor adaptations.
A hardware HFO detector based on neuromorphic technology would benefit from low power consumption since it performs spike-based processing. The raw signal is converted into "events" by an asynchronous delta modulator (ADM) circuit. There is no fixed sampling rate. This feature makes the whole device highly efficient in terms of power consumption. As an output, only the presence of an HFO would be signaled to a data storage device, e.g., a mobile phone.
To estimate power consumption, we envision a real-time HFO analysis “at the edge” that includes signal amplification in the preprocessing stage, HFO detection in the SNN, and wireless transmission of a flag to a storage device at the time of HFO occurrence. As previously reported8, our chip consumes 58.4 μW for preprocessing and 555.6 μW for the SNN.
Neuromorphic chip detects high-frequency oscillations
Neuromorphic engineering is a promising new approach that bridges the gap between artificial and natural intelligence. An interdisciplinary research team at the University of Zurich, the ETH Zurich, and the UniversityHospital Zurich has used this approach to develop a chip based on neuromorphic technology that reliably and accurately recognizes complex biosignals. The scientists were able to use this technology to successfully detect previously recorded high-frequency oscillations (HFOs). These specific waves, measured using an intracranial electroencephalogram (iEEG), have proven to be promising biomarkers for identifying the brain tissue that causes epileptic seizures.
Then there’s this;

Home - HFO Zurich
High frequency oscillations (HFO) in the EEG are considered to be new biomarkers with which we can detect epileptogenic tissue more accurately than is possible with standard methods.…
hfozuri.ch
And this from Brainchip website;
