Looking a little further into Deniz Cakan, PhD, (Principal Transformational Physicist at Northrop Grumman). Deniz was one of the people who liked Rudy Pei's PLEIADES post.
Obviously Deniz has an interest in neuromorphic computing, given he co-authored the paper below, which discusses neuromorphic computing.
At Northrop, Deniz leads the quantum R&D at the intersection of AIML, materials science, and device physics. His team’s work focuses on designing intelligent systems that accelerate quantum R&D.
In short, his work at the intersection of quantum + AI looks like it lines up very neatly with what BrainChip’s PLEIADES aims to deliver: intelligent, low-latency systems that can sense, decide, and adapt at the edge.
I asked ChatGPT if BrainChip's PLEIADES could help move quantum computing closer to commercialization. See the answer below if interested or scroll past it if you're not.
I said:
Could BrainChip's PLEIADES help bring quantum computing closer to commercialisation?
ChatGPT said:
That’s a really sharp question — and yes, in a meaningful way,
it could help move quantum computing closer to commercialization, though not by “solving” quantum computing outright.
Here’s the nuance:
The bottleneck today
The hardest part of scaling quantum systems isn’t just building qubits — it’s
stabilising and controlling them in real time.
- Qubits drift, decohere, or get noisy in unpredictable ways.
- Each quantum chip, material, or cryostat behaves slightly differently.
- The tuning and calibration process is slow, data-heavy, and often manual — scientists spend hours just “babysitting” devices to keep them coherent.
Where PLEIADES-style neuromorphic AI fits
A system like
BrainChip’s PLEIADES (event-driven, polynomial-based temporal processing) could serve as an
intelligent control layer that:
- Detects state changes or drifts as events, in microseconds.
- Adjusts voltages, fields, or bias currents autonomously, without waiting for batch analysis.
- Learns the behaviour of each individual device locally, using on-chip adaptation.
- Runs at low power and deterministic latency, which is vital for cryogenic or shielded setups.
Essentially, it brings
real-time intelligence to the hardware level, closing the loop between sensing and actuation — something cloud-scale AI can’t do because of latency and bandwidth limits.
The commercial implication
If labs can stabilise and tune qubits faster and keep them stable longer, they can:
- Improve yield (more usable qubits per wafer),
- Shorten test and calibration time, and
- Reduce operational cost and complexity.
That’s the difference between a research-only system and a manufacturable, scalable product line.
In short
PLEIADES-type neuromorphic controllers won’t build the qubits — but they could make quantum systems
smarter, more autonomous, and commercially viable by solving the
control and reliability problem that’s holding the industry back.
www.executivebiz.com
(Aside from that “Rudy” topic) fun fact at its best
