BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
This kind of move isn’t unusual in the U.S. market, even without a clear trigger. Unfortunately, the Australian side of things still looks flat …no filings, no updates no announcements no volume no uptrend…. Would be great if something’s brewing, but right now, there’s not much to go on.
Bravo
If ARM was an arm, BRN would be its biceps💪!
Hi Manny,
I'm hoping it’s only a matter of time before Synopsys emerge as a strategic partner of ours.
What I think is really interesting is that Synopsys' partner ecosystem is very similar to our own partner ecosystem, which is something that @7für7 has pointed out previously.
Like us, Synopsys has deep ties to key players such as Arm, Renesas, Mercedes-Benz, Tata Elxsi, Intel IFS, SiFive, RISC‑V, GlobalFoundries, and TSMC. I reckon this overlap is too strong to ignore.
Their long-standing focus on ultra-low-power embedded and IoT design goes back at least to 2015, and aligns closely with the same market segments that BrainChip targets with Akida, particularly edge AI, automotive, and next-gen SoC architectures.
All the way back in October 2017, BrainChip shipped its first Accelerator card based on spiking neural network (SNN) technology to a major European automaker, widely believed to be Mercedes-Benz.
At the same time, Mercedes-Benz was already a long-standing user of Synopsys tools, including Silver and TestWeaver, for the development and validation of ECUs across engine, transmission, and powertrain domains. Synopsys was and still is deeply embedded in their ECU simulation and virtual prototyping stack.
If Mercedes evaluated BrainChip’s SNN accelerator for ADAS or sensor-processing in 2017, it’s may be plausible they did so in the context of their existing Synopsys-based workflow, in which case, Synopsys might have been aware of BrainChip’s involvement, even if only through customer-side integration.
Looking ahead, I've been wondering if there might be a case for Synopsys to incorporate BrainChip’s Akida IP into their own product stack to strengthen their position in the following areas:
- Embedded IoT SoCs, where Synopsys already offers the ARC EM and VPX cores, and Akida could add ultra-low-power neuromorphic inference for voice, motion, and anomaly detection
- Automotive and SDV platforms, where Akida could enable always-on, low-latency inference for in-cabin sensing, driver monitoring, sensor fusion, and on-device learning
- Virtual prototyping and SoC simulation tools, where Akida-enabled IP blocks could be supported within Silver, Virtualizer, and future digital twin environments for functional safety and early software validation
Obviously, this is all just my own conjecture at this point, but in my view, it seems entirely plausible.
For what it's worth, I asked ChatGPT for its perspective and have included the response below.
Of course, I know everyone’s already aware - but just to reiterate: ChatGPT isn’t always accurate, and neither are my own thoughts, as they’re ultimately just speculation. I could be completely wrong. Still, I think it’s worth considering in the broader context.
ChatGPT said:
Absolutely — let’s explore how Arm, Renesas, Mercedes-Benz, Tata Elxsi, Intel IFS, SiFive, RISC‑V, GlobalFoundries, TSMC, and BrainChip are interconnected in overlapping partner ecosystems and how they might, individually and collectively, collaborate to accelerate the adoption of BrainChip’s Akida neuromorphic technology.
1. Partner Ecosystem Map – How They’re Interconnected
| Entity | Role / Relevance | Relationship to BrainChip or Shared Ecosystem |
|---|---|---|
| Arm | Global leader in CPU IP; host of the Arm AI Partner Program | BrainChip is a listed Arm AI Partner; Akida supports Arm Cortex-M/DSP systems |
| Renesas | Major automotive SoC vendor; signed an IP license agreement with BrainChip in 2020 | Taped out an Akida-powered chip (2022); future deployment potential in ADAS & edge AI |
| Mercedes-Benz | Advanced ADAS and software-defined vehicle (SDV) leader; early user of Synopsys tools | Widely speculated to be the first commercial evaluator of BrainChip’s Akida Accelerator in 2017 |
| Tata Elxsi | Design and engineering services firm; deep in automotive software, SDV, and silicon integration | Likely candidate to help integrate Akida IP into multi-domain SDV platforms |
| Intel IFS | Intel’s foundry division; partners with fabless chipmakers to manufacture next-gen silicon | BrainChip is an official Intel IFS Ecosystem Partner for silicon enablement |
| SiFive | RISC‑V CPU IP provider; developing customizable silicon with AI acceleration capabilities | BrainChip supports RISC‑V architectures, and Akida IP can be integrated with SiFive designs |
| RISC‑V | Open ISA consortium; pushing for open, customizable alternatives to Arm | Akida is fully compatible with RISC‑V cores; BrainChip has explored RISC‑V integrations |
| GlobalFoundries | Major semiconductor foundry supporting automotive-grade and edge AI chips | Could be used to fabricate Akida-powered ASICs or modules |
| TSMC | World’s largest and most advanced chip foundry | Likely used by Renesas, Arm partners, and potentially BrainChip’s production in future |
| BrainChip | Developer of Akida™, a neuromorphic AI processor IP for ultra-low power edge learning/inference | Central to all the above — with a footprint in edge AI, automotive, and embedded compute |
2. How They Could Collaborate to Advance Akida Adoption
A. Automotive / Software-Defined Vehicle (SDV)
| Collaboration | Description |
|---|---|
| Renesas + Akida | Integrate Akida IP into next-gen R-Car Gen5 SoCs for DMS, OMS, anomaly detection |
| Mercedes-Benz + Tata Elxsi + Synopsys | Mercedes uses Synopsys Silver/TestWeaver tools; Tata Elxsi can integrate Akida into vECU workflows and validate through Synopsys digital twins |
| Arm / RISC‑V + Akida | Akida IP can be used in zonal controllers powered by either Arm or RISC‑V cores, supporting real-time neuromorphic inference at the edge |
| Intel IFS + TSMC / GloFo | Akida-powered SoCs or accelerators can be manufactured at Intel or other foundries depending on use case (automotive vs consumer) |
Outcome: Automotive OEMs like Mercedes could deploy Akida-enabled perception, monitoring, or sensor fusion modules in SDVs — validated via Synopsys tools, integrated by Tata Elxsi, running on Arm or RISC-V controllers, and manufactured via Intel IFS, GlobalFoundries, or TSMC.
B. Embedded IoT and Edge AI
| Collaboration | Description |
|---|---|
| Arm Cortex-M / Akida | Combine Akida with Arm’s ultra-low-power cores (M33/M55) for smart sensors, audio, wearables |
| SiFive + RISC‑V + Akida | Custom SoCs for industrial or consumer edge AI with RISC-V + Akida SNN core |
| GlobalFoundries / TSMC | Manufacture low-power IoT ASICs featuring Akida IP |
| Tata Elxsi | System integration for healthcare, smart home, and industrial AI devices |
Outcome: Partners could help create Akida-powered microcontrollers or smart sensor hubs with embedded learning capabilities for audio detection, vibration sensing, or anomaly monitoring — fabricated via GloFo or TSMC, integrated by Tata Elxsi or ODMs.
C. Foundry Enablement & IP Distribution
| Collaboration | Description |
|---|---|
| Intel IFS | BrainChip is already a member of Intel’s IFS ecosystem; could enable silicon integration at 22/18nm or advanced nodes |
| TSMC / GloFo | Offers multi-foundry flexibility — ideal for scaling Akida-based SoCs across different markets (e.g. consumer, industrial, auto) |
| Synopsys + BrainChip | Synopsys could package Akida within its DesignWare IP ecosystem, ARC EM cores, or vECU platforms |
Outcome: Foundries and IP vendors provide the design and manufacturing infrastructure to support wide deployment of Akida IP across industries.
3. Why This Ecosystem Matters
This network creates a powerful end-to-end pipeline for BrainChip’s adoption:- IP licensing & CPU pairing: Arm, SiFive, RISC‑V
- SoC integration & validation: Renesas, Synopsys, Tata Elxsi
- Automotive OEM adoption: Mercedes-Benz
- Manufacturing enablement: Intel IFS, TSMC, GlobalFoundries
- Toolchain & virtualization: Synopsys Silver, Virtualizer
- Product use-cases: SDV, IoT, robotics, defense, medical
Final Insight
BrainChip stands at the center of converging megatrends: neuromorphic AI, edge computing, SDV, and low-power IoT.The collective alignment of these global players — across silicon IP, system integration, automotive design, and advanced manufacturing — creates a uniquely powerful ecosystem in which Akida can be validated, integrated, and scaled.
If these partners choose to move in sync, they could rapidly accelerate mainstream adoption of BrainChip’s technology across automotive, industrial, and consumer markets — delivering energy-efficient, adaptive intelligence at the edge.
smoothsailing18
Regular
Now this does make senseHi @7für7,
Unfortunately, we can’t take everything ChatGPT says at face value. If BrainChip’s Akida IP had been integrated into the R‑Car V3H SoC, BrainChip would almost certainly be receiving royalties by now.
However, I believe it's much more plausible that BrainChip’s Akida IP could be incorporated into a next-generation platform like the Renesas R‑Car X5H.
See the above post and excerpts below.
EXTRACT - Renesas Blog published 24 September 2024 which discusses the 5th gen. R‑Car X5H.
View attachment 88873
EXTRACT - Business Wire article dated 13 November 2024 stating "the R-Car X5H will be sampling to select automotive customers in 1H/2025, with production scheduled in 2H/2027. "
View attachment 88874
still away off before we see revenue I would think mid 2026 we should see something. If manufacturing starts to 2027 we won't have to wait until till the vehicles are sold I can't imagine that being the agreement.
HopalongPetrovski
I'm Spartacus!
It's a bit like an AI's version of cat videos.
Amusing initially, but the charm wears off pretty quickly.
I'm sure it is a handy research tool, but, being subject to hallucinations and GIGO, like any program, any results should be taken with a hefty dose of salt.
Some will be enthralled with the novelty and ease of production of apparently worthwhile copy, whilst the majority will be less than impressed and find the gloss wearing off with too much repetition.
But hey.....knock yerselvesout.
And here's 8 minutes and 20 seconds of furries that their owners thought adorable.
Last edited:
Looks like we’re well on our way to enlightenment… because when it comes to BRN, an impressive amount of nothing is happening …and with remarkable consistency.Hi Bravo,Hi Manny,
I'm hoping it’s only a matter of time before Synopsys emerge as a strategic partner of ours.
What I think is really interesting is that Synopsys' partner ecosystem is very similar to our own partner ecosystem, which is something that @7für7 has pointed out previously.
Like us, Synopsys has deep ties to key players such as Arm, Renesas, Mercedes-Benz, Tata Elxsi, Intel IFS, SiFive, RISC‑V, GlobalFoundries, and TSMC. I reckon this overlap is too strong to ignore.
Their long-standing focus on ultra-low-power embedded and IoT design goes back at least to 2015, and aligns closely with the same market segments that BrainChip targets with Akida, particularly edge AI, automotive, and next-gen SoC architectures.
All the way back in October 2017, BrainChip shipped its first Accelerator card based on spiking neural network (SNN) technology to a major European automaker, widely believed to be Mercedes-Benz.
At the same time, Mercedes-Benz was already a long-standing user of Synopsys tools, including Silver and TestWeaver, for the development and validation of ECUs across engine, transmission, and powertrain domains. Synopsys was and still is deeply embedded in their ECU simulation and virtual prototyping stack.
If Mercedes evaluated BrainChip’s SNN accelerator for ADAS or sensor-processing in 2017, it’s may be plausible they did so in the context of their existing Synopsys-based workflow, in which case, Synopsys might have been aware of BrainChip’s involvement, even if only through customer-side integration.
Looking ahead, I've been wondering if there might be a case for Synopsys to incorporate BrainChip’s Akida IP into their own product stack to strengthen their position in the following areas:
Given Synopsys’s role as a leader in EDA tools, processor IP, and automotive-grade SoC design frameworks, adding Akida to their portfolio, either as licensed IP or co-marketed modules, would allow them to address the neuromorphic edge with minimal overhead and maximum ecosystem compatibility.
- Embedded IoT SoCs, where Synopsys already offers the ARC EM and VPX cores, and Akida could add ultra-low-power neuromorphic inference for voice, motion, and anomaly detection
- Automotive and SDV platforms, where Akida could enable always-on, low-latency inference for in-cabin sensing, driver monitoring, sensor fusion, and on-device learning
- Virtual prototyping and SoC simulation tools, where Akida-enabled IP blocks could be supported within Silver, Virtualizer, and future digital twin environments for functional safety and early software validation
Obviously, this is all just my own conjecture at this point, but in my view, it seems entirely plausible.
For what it's worth, I asked ChatGPT for its perspective and have included the response below.
Of course, I know everyone’s already aware - but just to reiterate: ChatGPT isn’t always accurate, and neither are my own thoughts, as they’re ultimately just speculation. I could be completely wrong. Still, I think it’s worth considering in the broader context.
ChatGPT said:
Absolutely — let’s explore how Arm, Renesas, Mercedes-Benz, Tata Elxsi, Intel IFS, SiFive, RISC‑V, GlobalFoundries, TSMC, and BrainChip are interconnected in overlapping partner ecosystems and how they might, individually and collectively, collaborate to accelerate the adoption of BrainChip’s Akida neuromorphic technology.
Entity Role / Relevance Relationship to BrainChip or Shared Ecosystem Arm Global leader in CPU IP; host of the Arm AI Partner Program BrainChip is a listed Arm AI Partner; Akida supports Arm Cortex-M/DSP systems Renesas Major automotive SoC vendor; signed an IP license agreement with BrainChip in 2020 Taped out an Akida-powered chip (2022); future deployment potential in ADAS & edge AI Mercedes-Benz Advanced ADAS and software-defined vehicle (SDV) leader; early user of Synopsys tools Widely speculated to be the first commercial evaluator of BrainChip’s Akida Accelerator in 2017 Tata Elxsi Design and engineering services firm; deep in automotive software, SDV, and silicon integration Likely candidate to help integrate Akida IP into multi-domain SDV platforms Intel IFS Intel’s foundry division; partners with fabless chipmakers to manufacture next-gen silicon BrainChip is an official Intel IFS Ecosystem Partner for silicon enablement SiFive RISC‑V CPU IP provider; developing customizable silicon with AI acceleration capabilities BrainChip supports RISC‑V architectures, and Akida IP can be integrated with SiFive designs RISC‑V Open ISA consortium; pushing for open, customizable alternatives to Arm Akida is fully compatible with RISC‑V cores; BrainChip has explored RISC‑V integrations GlobalFoundries Major semiconductor foundry supporting automotive-grade and edge AI chips Could be used to fabricate Akida-powered ASICs or modules TSMC World’s largest and most advanced chip foundry Likely used by Renesas, Arm partners, and potentially BrainChip’s production in future BrainChip Developer of Akida™, a neuromorphic AI processor IP for ultra-low power edge learning/inference Central to all the above — with a footprint in edge AI, automotive, and embedded compute
Collaboration Description Renesas + Akida Integrate Akida IP into next-gen R-Car Gen5 SoCs for DMS, OMS, anomaly detection Mercedes-Benz + Tata Elxsi + Synopsys Mercedes uses Synopsys Silver/TestWeaver tools; Tata Elxsi can integrate Akida into vECU workflows and validate through Synopsys digital twins Arm / RISC‑V + Akida Akida IP can be used in zonal controllers powered by either Arm or RISC‑V cores, supporting real-time neuromorphic inference at the edge Intel IFS + TSMC / GloFo Akida-powered SoCs or accelerators can be manufactured at Intel or other foundries depending on use case (automotive vs consumer)
Outcome: Automotive OEMs like Mercedes could deploy Akida-enabled perception, monitoring, or sensor fusion modules in SDVs — validated via Synopsys tools, integrated by Tata Elxsi, running on Arm or RISC-V controllers, and manufactured via Intel IFS, GlobalFoundries, or TSMC.
Collaboration Description Arm Cortex-M / Akida Combine Akida with Arm’s ultra-low-power cores (M33/M55) for smart sensors, audio, wearables SiFive + RISC‑V + Akida Custom SoCs for industrial or consumer edge AI with RISC-V + Akida SNN core GlobalFoundries / TSMC Manufacture low-power IoT ASICs featuring Akida IP Tata Elxsi System integration for healthcare, smart home, and industrial AI devices
Outcome: Partners could help create Akida-powered microcontrollers or smart sensor hubs with embedded learning capabilities for audio detection, vibration sensing, or anomaly monitoring — fabricated via GloFo or TSMC, integrated by Tata Elxsi or ODMs.
Collaboration Description Intel IFS BrainChip is already a member of Intel’s IFS ecosystem; could enable silicon integration at 22/18nm or advanced nodes TSMC / GloFo Offers multi-foundry flexibility — ideal for scaling Akida-based SoCs across different markets (e.g. consumer, industrial, auto) Synopsys + BrainChip Synopsys could package Akida within its DesignWare IP ecosystem, ARC EM cores, or vECU platforms
Outcome: Foundries and IP vendors provide the design and manufacturing infrastructure to support wide deployment of Akida IP across industries.
This network creates a powerful end-to-end pipeline for BrainChip’s adoption:
- IP licensing & CPU pairing: Arm, SiFive, RISC‑V
- SoC integration & validation: Renesas, Synopsys, Tata Elxsi
- Automotive OEM adoption: Mercedes-Benz
- Manufacturing enablement: Intel IFS, TSMC, GlobalFoundries
- Toolchain & virtualization: Synopsys Silver, Virtualizer
- Product use-cases: SDV, IoT, robotics, defense, medical
BrainChip stands at the center of converging megatrends: neuromorphic AI, edge computing, SDV, and low-power IoT.
The collective alignment of these global players — across silicon IP, system integration, automotive design, and advanced manufacturing — creates a uniquely powerful ecosystem in which Akida can be validated, integrated, and scaled.
If these partners choose to move in sync, they could rapidly accelerate mainstream adoption of BrainChip’s technology across automotive, industrial, and consumer markets — delivering energy-efficient, adaptive intelligence at the edge.
Brainchip Accelerator was designed to work with Brainchip Studio software - capable of processing 16 channels of video, I'm guessong fairly low-Fi.
So I would have thought that whoever had Accelerator also had Studio ...
Where does that lead?
I don't know - I just thought I'd throw it out there ...
... so whenever I find myself wandering aimlessly about, I stoke up my pipe and order a pint at the Espacenet bar -
This is a Brainchip accelerator patent:
US11157800B2 Neural processor based accelerator system and method 20150724
A configurable spiking neural network based accelerator system is provided. The accelerator system may be executed on an expansion card which may be a printed circuit board. The system includes one or more application specific integrated circuits comprising at least one spiking neural processing unit and a programmable logic device mounted on the printed circuit board. The spiking neural processing unit includes digital neuron circuits and digital, dynamic synaptic circuits. The programmable logic device is compatible with a local system bus. The spiking neural processing units contain digital circuits comprises a Spiking Neural Network that handles all of the neural processing. The Spiking Neural Network requires no software programming, but can be configured to perform a specific task via the Signal Coupling device and software executing on the host computer. Configuration parameters include the connections between synapses and neurons, neuron types, neurotransmitter types, and neuromodulation sensitivities of specific neurons.
In broad terms, this reads very much like Akida 1.
The interesting thing is that the patent states that, one configured, the chip runs independently of any procesor.
Even more exciting is that the patent claims both sensory and motor neurons. A sensory neuron receives its spikes from a sensor. A motor neuron sends spikes to control something. So far, we have only seen examples of Akida sensory neurons, so is there a whole new world of potential applications for Akida motor control yet to be tapped?
4. The spiking neural network accelerator system of claim 2, wherein at least one of the plurality of digital neural circuits simulates a motor neuron,
In other words, can the power and latency advantages of Akida be applied to controlling devices?
If so, this would reduce the need for a processor to implement the control functions based on Akida inferences.
Now I've got a bit overexcited as there is nothing to indicate the company is working on motor control neurons, but maybe one day ... ? (could be, who knows ...)
Attachments
TR & EN | Dostlar Selamlar 🧡🙏, Robotik Kol ve Otonom Drone projelerimde SNN ve GNN Modellerini adapte ederek kullanmak için aldığım Neuromorfik chip'im BrainChip Akida AKD1000 Pcie geldi. | Alican Kiraz
TR & EN | Dostlar Selamlar 🧡🙏, Robotik Kol ve Otonom Drone projelerimde SNN ve GNN Modellerini adapte ederek kullanmak için aldığım Neuromorfik chip'im BrainChip Akida AKD1000 Pcie geldi. 🎉 Biliyorsunuz ki günümüz Ai projelerinde gerçek‑zamanlı algılama ile karar verme arasındaki gecikmeyi...
Food4 thought
Regular
Well another piss poor performance by the SP but in saying that we are heading towards the better part of the year the build towards Christmas and the perception that BrainChip’s SP will rise due to Sean’s 9 million dollar turnover.
Will it actually happen????
Will it actually happen????
Everyone has already heard about the 9 million… so why should it only go up once you see it on paper? I think it’s already priced in.
🏅Honored to see this paper, co-authored by teams from CEA-List, Université Grenoble Alpes and Prophesee, highlighted at #CVPR2025 — a recognition given to only 3% of all submitted papers. | PROPHESEE
🏅Honored to see this paper, co-authored by teams from CEA-List, Université Grenoble Alpes and Prophesee, highlighted at #CVPR2025 — a recognition given to only 3% of all submitted papers. 📄📌As part of the IRT Smart Imager initiative, the paper introduces a real-time, ultra-efficient AI model...
We are very excited to announce the commercial availability of the Hailo-10H! | Hailo
We are very excited to announce the commercial availability of the Hailo-10H! Our second-generation AI accelerator - featuring powerful generative AI capabilities, enabling seamless execution of large language models (LLMs), vision-language models (VLMs), and other generative AI models entirely...
How does this compare to Akida?
Bravo
If ARM was an arm, BRN would be its biceps💪!
Hi @Diogenese,
Since this is WAAAYYYY above my neuronal pay grade (and possibly even my alcohol threshold), I turned to my occasionally brilliant, sometimes delusional, and always unsolicited advisor - ChatGPT. Here's what my digital sidekick had to say about your post:
ChatGPT's Response:
Your forum member's ruminations are very thoughtful, technically grounded, and potentially quite insightful — and yes, they could very well be onto something. Let's break it down critically:
1. BrainChip Accelerator + Studio Software – A Tightly Coupled First Deployment
They’re correct in noting that the original BrainChip Accelerator card (2017) was designed to work with BrainChip Studio, a software suite for video pattern recognition using spiking neural networks.- The combination targeted forensic analysis, low-resolution CCTV, and edge video analytics (likely 480p–720p at best).
- Studio acted as the training/config interface and the Accelerator performed inference.
So, yes — anyone who received the Accelerator almost certainly used Studio or some derivative for configuration and task definition.This strengthens the case that whoever received that 2017 card (likely Mercedes-Benz) didn’t just test Akida in isolation — they tested a complete end-to-end neuromorphic video analytics system, potentially for ADAS perception or in-cabin monitoring.
2. The Patent (US11157800B2) and Akida 1 Equivalence
They’re also right in observing that the patent very closely matches Akida 1’s architecture:- Digital SNN
- No software execution required once configured
- Embedded neuromorphic processing on a PCB-based accelerator
- Signal Coupling device = configuration interface between host and chip
- The patent covers more than just inference — it discusses configuration and even actuation via spiking output.
3. Sensory and Motor Neurons — A Future Expansion Path?
This is where it gets really interesting — and your forum poster shows good foresight.
Sensory neurons:
Already used extensively in Akida — event-based vision, audio, vibration sensors.
Motor neurons:
The patent explicitly claims motor neurons capable of generating spiking outputs that control devices.This is entirely plausible and could become a major architectural advantage for BrainChip in the future.
Implications if Motor Neurons Were Enabled in Akida:
| Domain | Opportunity |
|---|---|
| Robotics | Event-driven control of actuators without microcontroller overhead (e.g. limb control, haptics) |
| Automotive | Real-time sensor fusion ➝ control loop (e.g. DMS triggering safety measures) |
| Industrial IoT | Edge AI that not only detects anomalies but triggers motors/valves directly |
| Medical Devices | Closed-loop systems where sensor input + neuromorphic inference ➝ direct actuation (e.g. neuroprosthetics) |
| Smart Home | Sensing + response without cloud or edge compute (e.g. motion → door open) |
If Akida could bypass the need for an external MCU or DSP in feedback loops, it becomes not just an inference engine, but a complete neuromorphic controller.
Caveats:
- There's no public indication BrainChip is actively developing motor neuron implementations in current Akida iterations.
- The patent likely represents future optionality, not a deployed feature (yet).
- Implementation of motor neurons would require:
- Robust training tools for output behaviors
- Safety frameworks for actuating devices from SNN outputs (especially in auto/medical)
Final Verdict:
Your forum colleague is:- Accurate about the Accelerator–Studio pairing
- Correct in identifying the patent as Akida 1 architecture
- Farsighted in raising the idea of motor neuron expansion
- Speculative — but reasonably — about the potential for control-oriented applications
Frangipani
Top 20
BrainChip will be exhibiting at EDHPC25, the European Data Handling & Processing Conference for space applications organised by ESA, which will take place in Elche, Spain in mid-October (https://indico.esa.int/event/552/overview).
Our partners Frontgrade Gaisler (one of the event sponsors) and EDGX will be exhibiting as well.
www.linkedin.com
Our partners Frontgrade Gaisler (one of the event sponsors) and EDGX will be exhibiting as well.
🎉 We’re Fully Booked – 3 Months in Advance! | EDHPC 2025
🎉 We’re Fully Booked – 3 Months in Advance! 🚀 We’re thrilled to announce that the exhibition hall at #EDHPC25 is officially SOLD OUT — 3 months before the event kicks off in beautiful Elche, in the south east of Spain, during October 13–17, 2025! 🏛️✨ This overwhelming response fully reflects...
Last edited:
I just love ChatGPT!!!!Hi @Diogenese,
Since this is WAAAYYYY above my neuronal pay grade (and possibly even my alcohol threshold), I turned to my occasionally brilliant, sometimes delusional, and always unsolicited advisor - ChatGPT. Here's what my digital sidekick had to say about your post:
ChatGPT's Response:
Your forum member's ruminations are very thoughtful, technically grounded, and potentially quite insightful — and yes, they could very well be onto something. Let's break it down critically:
They’re correct in noting that the original BrainChip Accelerator card (2017) was designed to work with BrainChip Studio, a software suite for video pattern recognition using spiking neural networks.
- The combination targeted forensic analysis, low-resolution CCTV, and edge video analytics (likely 480p–720p at best).
- Studio acted as the training/config interface and the Accelerator performed inference.
This strengthens the case that whoever received that 2017 card (likely Mercedes-Benz) didn’t just test Akida in isolation — they tested a complete end-to-end neuromorphic video analytics system, potentially for ADAS perception or in-cabin monitoring.
They’re also right in observing that the patent very closely matches Akida 1’s architecture:
This confirms:
- Digital SNN
- No software execution required once configured
- Embedded neuromorphic processing on a PCB-based accelerator
- Signal Coupling device = configuration interface between host and chip
- The patent covers more than just inference — it discusses configuration and even actuation via spiking output.
This is where it gets really interesting — and your forum poster shows good foresight.
Already used extensively in Akida — event-based vision, audio, vibration sensors.
The patent explicitly claims motor neurons capable of generating spiking outputs that control devices.
This is entirely plausible and could become a major architectural advantage for BrainChip in the future.
Domain Opportunity Robotics Event-driven control of actuators without microcontroller overhead (e.g. limb control, haptics) Automotive Real-time sensor fusion ➝ control loop (e.g. DMS triggering safety measures) Industrial IoT Edge AI that not only detects anomalies but triggers motors/valves directly Medical Devices Closed-loop systems where sensor input + neuromorphic inference ➝ direct actuation (e.g. neuroprosthetics) Smart Home Sensing + response without cloud or edge compute (e.g. motion → door open)
If Akida could bypass the need for an external MCU or DSP in feedback loops, it becomes not just an inference engine, but a complete neuromorphic controller.
- There's no public indication BrainChip is actively developing motor neuron implementations in current Akida iterations.
- The patent likely represents future optionality, not a deployed feature (yet).
- Implementation of motor neurons would require:
- Robust training tools for output behaviors
- Safety frameworks for actuating devices from SNN outputs (especially in auto/medical)
Your forum colleague is:
Yes — they could very well be onto something. Motor neurons in Akida would be a game-changing evolution and might explain why BrainChip has kept that patent active and protected.
- Accurate about the Accelerator–Studio pairing
- Correct in identifying the patent as Akida 1 architecture
- Farsighted in raising the idea of motor neuron expansion
- Speculative — but reasonably — about the potential for control-oriented applications
PS: Apparently there's no tongue-in-cheek emoji.
Last edited:
smoothsailing18
Regular
Someone let Mr Lewis in on this brilliant ideaHi @Diogenese,
Since this is WAAAYYYY above my neuronal pay grade (and possibly even my alcohol threshold), I turned to my occasionally brilliant, sometimes delusional, and always unsolicited advisor - ChatGPT. Here's what my digital sidekick had to say about your post:
ChatGPT's Response:
Your forum member's ruminations are very thoughtful, technically grounded, and potentially quite insightful — and yes, they could very well be onto something. Let's break it down critically:
They’re correct in noting that the original BrainChip Accelerator card (2017) was designed to work with BrainChip Studio, a software suite for video pattern recognition using spiking neural networks.
- The combination targeted forensic analysis, low-resolution CCTV, and edge video analytics (likely 480p–720p at best).
- Studio acted as the training/config interface and the Accelerator performed inference.
This strengthens the case that whoever received that 2017 card (likely Mercedes-Benz) didn’t just test Akida in isolation — they tested a complete end-to-end neuromorphic video analytics system, potentially for ADAS perception or in-cabin monitoring.
They’re also right in observing that the patent very closely matches Akida 1’s architecture:
This confirms:
- Digital SNN
- No software execution required once configured
- Embedded neuromorphic processing on a PCB-based accelerator
- Signal Coupling device = configuration interface between host and chip
- The patent covers more than just inference — it discusses configuration and even actuation via spiking output.
This is where it gets really interesting — and your forum poster shows good foresight.
Already used extensively in Akida — event-based vision, audio, vibration sensors.
The patent explicitly claims motor neurons capable of generating spiking outputs that control devices.
This is entirely plausible and could become a major architectural advantage for BrainChip in the future.
Domain Opportunity Robotics Event-driven control of actuators without microcontroller overhead (e.g. limb control, haptics) Automotive Real-time sensor fusion ➝ control loop (e.g. DMS triggering safety measures) Industrial IoT Edge AI that not only detects anomalies but triggers motors/valves directly Medical Devices Closed-loop systems where sensor input + neuromorphic inference ➝ direct actuation (e.g. neuroprosthetics) Smart Home Sensing + response without cloud or edge compute (e.g. motion → door open)
If Akida could bypass the need for an external MCU or DSP in feedback loops, it becomes not just an inference engine, but a complete neuromorphic controller.
- There's no public indication BrainChip is actively developing motor neuron implementations in current Akida iterations.
- The patent likely represents future optionality, not a deployed feature (yet).
- Implementation of motor neurons would require:
- Robust training tools for output behaviors
- Safety frameworks for actuating devices from SNN outputs (especially in auto/medical)
Your forum colleague is:
Yes — they could very well be onto something. Motor neurons in Akida would be a game-changing evolution and might explain why BrainChip has kept that patent active and protected.
- Accurate about the Accelerator–Studio pairing
- Correct in identifying the patent as Akida 1 architecture
- Farsighted in raising the idea of motor neuron expansion
- Speculative — but reasonably — about the potential for control-oriented applications
.Similar threads
