Stable Genius
Regular
Gas Sensors in the Toilet? — Intelligut.ai
Why the Future of Gut Health Is Passive and Personal
www.intelligut.ai
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
www.intelligut.ai
Agree, the engineering is a real positive. It indicates we have 3 likely sizeable clients going through the engagement to reve ue cycle.Good evening,
Having read yesterday the company's 4C & Quarterly Report I felt overall it was positive, the Board appears to have done a
thorough evaluation of their earlier statement about moving our entire listing offshore to the US, yes, that's correct, the USA.
And the decision/recommendation was a solid NO.........in my opinion it was/is way too early and that the Chairperson is
part of a team that never ever revolves around one individual and his fickle ideas, once again, that's my private view.
The revenue appeared to represent a 10-fold increase, now no shareholder should assume anything at this point, what we
would like to see is back-back quarters, showing another increase, say 2 million +.... slowly increasing, but continually, quarter
on quarter, remembering that we are still starting from a very low base.
A concern to me was the failure to raise the 20 million AUD, receiving the 8.2 million AUD at an average of 0.2059, surely this
wasn't the agreement, I must be going mad, I thought the agreement was more like 0.50 a share x 40 million shares issued,
and I thought that Ken Scarince confirmed as such at the AGM?......so clearly, I am wrong.
Never-the-less we have approximately 17.3 million USD to 1 August 2025.......plus revenue (if any).
The grind continues.
Goodnight, All......Tech
How far through??
Wags
Regular
Hi again smooth.
None of it bothers me, actually sounds pretty good if turns out true. Maybe there was another collaboration or details of partnership announced that I haven't seen, but the red flag for me was the GPT comment "given the strategic nature of the partnership announced in late 2023" when we know the actual IP Licence announcement Dec 2020. The other concern is the formal announcement talks about Renesas required to pay for ongoing support after 2 yrs (paraphrasing), and as you know, engineering revenue (or any revenue) hasn't been great, so I'm a 50/50 on Renesas. Not being a downer by any means, just voicing my thoughts. Conversely, there is obviously lots going on behind the curtains, so I am hopeful, we will all see the tide to turn soonish????
I think GPT is great in many ways, but at the moment, I don't completely trust.
Great pic up.
The end date for the Bascom Hunter SBIR program is 18th Aug'25.
It matches the new recruiting drive by BH.
The director of ISR Systems includes Neuromorphic as part of the job scope and required skill.
I'm assuming that it's not usual for a company to hire directors if there isn't any plan for a big expansion or scale up.
smoothsailing18
Regular
The fact that AI is going everywhere and into everything ARM can see the expedential growth in this chiplet market. Neuromorphic compute/ Brn is extremely well placed both within the eco systems,manufacturers ext but also with its latest TENN'S design that can do all the tasks that ARM required of it.ChatGPT said:
Here’s how the recent Arm announcement impacts BrainChip, and why BrainChip’s **Akida™ neuromorphic technology is well-aligned with a future where Arm drives chiplet-based systems:
Arm is pivoting from being a pure IP licensor to also designing and producing its own chips, including modular chiplets, according to its CEO. This represents a significant evolution in its business model Barron's+11EDN+11The Institution of Electronics+11Investing.com+5Reuters+5Barron's+5.
What Arm’s Strategy Shift Means
Meanwhile, Arm has released its first public Chiplet System Architecture (CSA) specification, a framework aimed at standardizing how chiplets communicate and integrate across suppliers—now backed by over 60 companies EDN+10Datacenter Dynamics+10chiplet-marketplace.com+10.
Arm is also deeply involved in ecosystem initiatives like UCIe and AMBA extensions, ensuring seamless interoperability between chiplet modules like NPUs, CPUs, memory, and I/O cores documentation-service.arm.com+15en.wikipedia.org+15EDN+15.
Relevance to BrainChip and Akida
1. Chiplet-Savvy IP Fits Modular Architecture
- Akida, as an NPU IP block, is ideally suited to be a chiplet in multi-die systems.
- With Arm pushing for chiplet-based SoCs, BrainChip’s neuromorphic IP can slot into that ecosystem as a dedicated inference engine.
2. Ecosystem Compatibility
- Arm’s CSA and UCIe standards enable modular integration of IP like Akida into diverse platforms.
- As a partner in the Arm ecosystem, BrainChip can more easily supply Akida as a scalable chiplet accelerator.
3. Strategic Opportunity Ahead
- If Arm builds CPUs or AI modules using its own chiplets, they may still license third-party accelerators like Akida for edge inference tasks.
- For BrainChip, this presents both co-design opportunities and licensing pathways within future modular AI SoCs.
What Needs to Happen for BrainChip
- Akida Adaptation for Chiplet Interface
- Support UCIe and AMBA protocols.
- Package Akida as a physical die compliant with CSA guidelines.
- Software & Toolchain Bridge
- API/SDK compatibility with Arm-based SoCs.
- Ensuring model portability in heterogeneous chiplet setups.
- Collaboration with Arm or Arm Licensees
- Joint development prototyping for chiplet reference designs.
- Certification and validation within Arm’s modular ecosystem.
Arm’s ambition to build its own chips—and more importantly, to lay the groundwork for a chiplet-first future—is very good news for BrainChip:
- It validates the modular architecture model in which Akida could play a central role.
- It provides a strategic alignment path into new SoCs without forging custom heavy-lift silicon deals.
- It opens a sizable avenue for BrainChip to position Akida as the go-to neuromorphic accelerator in Arm-powered chiplet platforms.
Reuters
Chip tech provider Arm looks to design own processors in major shift
Yesterday
Reuters
Arm considers developing own chips; stock falls as outlook disappoints
Yesterday
ChatGPT said:
Yes, AKIDA 2.0 + TENNs (The Event-based Neural Network) could absolutely be incorporated into a chiplet, and doing so could offer substantial advantages.
- Modular Architecture:
Akida is designed as a modular IP block, making it inherently suitable for chiplet integration. Its small footprint and event-driven nature align well with heterogeneous system design.- RISC-V & Interoperability:
BrainChip has shown compatibility with RISC-V and can interface through standard protocols (e.g. AXI4), making it easier to integrate as a chiplet alongside CPUs, NPUs, GPUs, or other IP.- Low Power & Locality:
TENNs (Temporal/Event-based processing) is ideal for edge inference, making Akida a great fit for edge AI chiplets in multi-die systems where power and bandwidth are constrained.- AI Workload Specialization:
As systems adopt task-specific chiplets, Akida could serve as a dedicated neuromorphic co-processor, handling real-time, sparse, low-latency inference — particularly valuable in:
- Vision (event-based cameras)
- Audio (low-power wake word, anomaly detection)
- Predictive control (motor, robotics)
Practical Pathways for Chiplet Integration:
- Interposer-based SoC: Akida could sit on an interposer beside ARM/Synopsys CPU, LPDDR, and sensor interface chiplets.
- Heterogeneous 3D stack: Placing Akida on a logic die below a sensor/compute array.
- Multi-chip module (MCM) with secure, shared memory access.
Strategic Implication for BrainChip:
- Opens the door to tier-1 partnerships where large OEMs build custom SoCs with pluggable IP.
- Aligns with trends in chiplet ecosystems like those being promoted by AMD, Intel, and ARM.
- Allows Akida to ride the AI chiplet wave without needing to fab monolithic chips.
If Arm is exploring chiplet-based designs (as per your Reuters link), and BrainChip is already partnered with them — this makes integration via chiplets a realistic and strategic route for Akida to enter new platforms (phones, automotive, industrial AI, etc.).
It may well be closer than we all think now this explosive growth.
Go brainchip.
Pom down under
Top 20
Well another week passes without any real news and the silence coming from the company has gone beyond deafening. Have a great weekend everyone and maybe this time next year we will all be millionaires
smoothsailing18
Regular
FF.
I have updated my list of Brainchip Engagements as at 1 August, 2025. I use this list for the purpose of ongoing research to keep track of existing projects or to pick up any new projects. Needless to say the list is now quite long so if anyone wants use it for their research activities they are quite welcome:
1. FORD
2. VALEO
3. RENESAS
4. NASA
5. TATA Consulting Services
6.MEGACHIPS
7. MOSCHIP
8.SOCIONEXT
9.PROPHESEE
10. VVDN
11. TEKSUN
12. Ai LABS
13. NVISO now BeEMOTION
14. EMOTION3D
15. ARM
16. EDGE IMPULSE
17. INTEL
18. GLOBALFOUNDRIES
19. BLUERIDGE ENVISIONEERING
20. MERCEDES BENZ
21. ANT 61
22. QUANTUM VENTURA
23.INFORMATION SYSTEM LABORATORIES
24.INTELLISENSE SYSTEMS
25. CVEDIA
26. LORSER INDUSTRIES
27. SiFIVE
28. IPROSILICONE
29.SALESLINK
30. NUMEM
31. VORAGO
32. NANOSE
33. BIOTOME
34. OCULI
35. CIRCLE8 CLEAN TECHNOLOGIES
36. AVID GROUP
37. TATA ELXSI
38. NEUROBUS
39. EDGX
40. EUROPEAN SPACE AGENCY
41 UNIGEN
42. iniVation
43. SAHOMA CONTROLWARE
44. MAGIKEYE
45. MYWAI
46. INFINEON
47. ERICSSON
48. MICROCHIP
49. ONSEMI
50. IPSOLON RESEARCH
51. UBH - HELLAS
52. ACCENTURE
53. FRONTGRADE GAISLER
54. DELL Technologies
55. BOSTON DYNAMICS
56. AIRBUS
57. PARSONS CORPORATION
58. BASCOM HUNTER
59. ExeLANCE IT
60. US AIRFORCE RESEARCH LABORATORY
61. ONSOR
62. ANDES TECHNOLOGY
63. DEGIRUM
64. VEDYA
65. MULTICOREWARE
66. ARQUIMEA
67. LOCKHEED MARTIN
68. RTX - RAYTHEON & COLLINS
69. Nurjana Technologies
70. Chelpis Quantum GROUP
71. MiRLE GROUP
72. BOSCH
73. RENAULT
74. ST MICROELECTRONICS
75. University of Virginia
76. University of Oklahoma
77. Arizona State University
78. Carnegie Mellon University
79. Rochester Institute of Technology
80. Drexel University
81. Cornell Tech - founded by Cornell University & Technion - (Israel Institute of Technology and sponsor of Nanose)
82. University of Western Australia
83. Penn State University
My opinion only DYOR
Fact Finder
I have updated my list of Brainchip Engagements as at 1 August, 2025. I use this list for the purpose of ongoing research to keep track of existing projects or to pick up any new projects. Needless to say the list is now quite long so if anyone wants use it for their research activities they are quite welcome:
1. FORD
2. VALEO
3. RENESAS
4. NASA
5. TATA Consulting Services
6.MEGACHIPS
7. MOSCHIP
8.SOCIONEXT
9.PROPHESEE
10. VVDN
11. TEKSUN
12. Ai LABS
13. NVISO now BeEMOTION
14. EMOTION3D
15. ARM
16. EDGE IMPULSE
17. INTEL
18. GLOBALFOUNDRIES
19. BLUERIDGE ENVISIONEERING
20. MERCEDES BENZ
21. ANT 61
22. QUANTUM VENTURA
23.INFORMATION SYSTEM LABORATORIES
24.INTELLISENSE SYSTEMS
25. CVEDIA
26. LORSER INDUSTRIES
27. SiFIVE
28. IPROSILICONE
29.SALESLINK
30. NUMEM
31. VORAGO
32. NANOSE
33. BIOTOME
34. OCULI
35. CIRCLE8 CLEAN TECHNOLOGIES
36. AVID GROUP
37. TATA ELXSI
38. NEUROBUS
39. EDGX
40. EUROPEAN SPACE AGENCY
41 UNIGEN
42. iniVation
43. SAHOMA CONTROLWARE
44. MAGIKEYE
45. MYWAI
46. INFINEON
47. ERICSSON
48. MICROCHIP
49. ONSEMI
50. IPSOLON RESEARCH
51. UBH - HELLAS
52. ACCENTURE
53. FRONTGRADE GAISLER
54. DELL Technologies
55. BOSTON DYNAMICS
56. AIRBUS
57. PARSONS CORPORATION
58. BASCOM HUNTER
59. ExeLANCE IT
60. US AIRFORCE RESEARCH LABORATORY
61. ONSOR
62. ANDES TECHNOLOGY
63. DEGIRUM
64. VEDYA
65. MULTICOREWARE
66. ARQUIMEA
67. LOCKHEED MARTIN
68. RTX - RAYTHEON & COLLINS
69. Nurjana Technologies
70. Chelpis Quantum GROUP
71. MiRLE GROUP
72. BOSCH
73. RENAULT
74. ST MICROELECTRONICS
75. University of Virginia
76. University of Oklahoma
77. Arizona State University
78. Carnegie Mellon University
79. Rochester Institute of Technology
80. Drexel University
81. Cornell Tech - founded by Cornell University & Technion - (Israel Institute of Technology and sponsor of Nanose)
82. University of Western Australia
83. Penn State University
My opinion only DYOR
Fact Finder
Rskiff
Regular
Impressive. Now SUT$
Fullmoonfever
Top 20
We know MB instigated a MOU or whatever with Uni of Waterloo and I was just reading an article about Ontario and how it's a bit of a Tech, AI & neuromorphic hub.
Something I found interesting about The Uni and their Applied Brain Spin off is how a lot of their focus is on SNN models, algos etc to apply to neuromorphic processors, not as much the processors themselves it seems. That could change(d), don't know.
But it got me thinking that maybe, just maybe, MB does def like Akida (still listed as a partner or customer or whatever) but they don't have the requisite experience in the SNN side to really achieve what they want Akida to do and hence the engagement with Waterloo.
Just a thought.
Couple of excerpts below from the article which I presume is part / all AI Gen overseen by this guy. Either way, the info on Waterloo I found interesting.
autogpt.net
Updated:July 31, 2025
Applied Brain Research collaborates extensively with academic institutions and industrial partners to implement adaptive control and edge inference systems that benefit from brain-inspired computing. Their work transforms theory into deployed reality across sectors like robotics, automotive, and industrial automation.
Recent pilot programs have shown promise in domains such as traffic analysis and industrial automation, where real-time learning and micro-power consumption are game changers. The cross-pollination between academia and industry in Ontario accelerates the transition from research prototype to deployed solution.
Something I found interesting about The Uni and their Applied Brain Spin off is how a lot of their focus is on SNN models, algos etc to apply to neuromorphic processors, not as much the processors themselves it seems. That could change(d), don't know.
But it got me thinking that maybe, just maybe, MB does def like Akida (still listed as a partner or customer or whatever) but they don't have the requisite experience in the SNN side to really achieve what they want Akida to do and hence the engagement with Waterloo.
Just a thought.
Couple of excerpts below from the article which I presume is part / all AI Gen overseen by this guy. Either way, the info on Waterloo I found interesting.
Joey Mazars
Contributor & AI Expert
How Neuromorphic Chips Are Reimagining AI by Thinking Like the Brain
Neuromorphic chips—hardware designed to mimic the structure and function of the human brain—are quietly engineering a seismic shift in how AI systems perceive, learn, and react.
autogpt.net
How Neuromorphic Chips Are Reimagining AI by Thinking Like the Brain
Updated:July 31, 2025
Ontario’s Global Position in Neuromorphic AI
Globally, neuromorphic hardware has reached notable milestones—Intel’s Loihi chips offer programmable SNNs, IBM’s TrueNorth pioneered the use of 1 million digital neurons, and BrainChip’s Akida platform integrates spiking intelligence into commercial edge devices. What makes Ontario stand out isn’t just research, but readiness. With the Vector Institute, University of Waterloo, silicon innovators like Untether AI and Tenstorrent, and real-world testing grounds like iGaming and robotics, Ontario offers a unique blend of capability and application. It could become North America’s leading launchpad for neuromorphic AI—where theory meets ROI across both factory floors and digital casinos.Applied Brain Research (Waterloo)
Applied Brain Research, based in Waterloo, stands as a pillar in the neuromorphic ecosystem. The company is best known for Nengo, a widely adopted software tool for building and simulating spiking neural networks. Nengo supports both research and commercial deployments, enabling models that run efficiently on neuromorphic substrates and low-power accelerators.Applied Brain Research collaborates extensively with academic institutions and industrial partners to implement adaptive control and edge inference systems that benefit from brain-inspired computing. Their work transforms theory into deployed reality across sectors like robotics, automotive, and industrial automation.
Vector Institute and University of Waterloo
Two of Ontario’s premier research hubs—Toronto’s Vector Institute and the University of Waterloo—are deeply involved in neuromorphic AI exploration. Vector researchers are advancing algorithms that make spiking networks trainable and efficient, particularly in on-chip learning scenarios. Meanwhile, University of Waterloo labs are publishing on adaptive spiking inference and energy-aware ML models.Recent pilot programs have shown promise in domains such as traffic analysis and industrial automation, where real-time learning and micro-power consumption are game changers. The cross-pollination between academia and industry in Ontario accelerates the transition from research prototype to deployed solution.
smoothsailing18
Regular
Parsons acquired Blacksignal last year:
https://www.parsons.com/2024/07/parsons-to-acquire-blacksignal-technologies/
Blaclsignal lists Blue Ridge as one of its companies:
https://www.blacksignal.tech/our-companies
Parsons lists a lot of AI applications:
https://www.parsons.com/ai/
Explore All Of Our AI Capabilities
- Idea Conception
- Requirements Analysis
- AI Cloud/Edge Architectures
- AI HW/SW Design and Dev
- R&D Prototyping
- Large Scale Data Collection
- Data Preprocessing/Preparation
- Model Verification and Validation
- Model Security
- AI Solution Field Testing
- AI Solution Deployment
- Runtime Environment O&M
- AI Solution Risk Mitigation
- AI Ethics/Privacy/Anti-Bias
- AI Recruiting
- AI Staff Training
- AI Technology Surveillance
- AI Technology T&E (Paladin)
- Data Decommissioning
- AI System Decommissioning
- Synthetic Data Generation
The 2023 Blue Ridge/Brainchip announcement makes reference to Akida 2 technology:
https://www.edgeir.com/brainchip-bl...am-up-to-build-tactical-edge-devices-20230416
BrainChip, a provider of neuromorphic processors for edge AI on-chip processing, has teamed up with Blue Ridge Envisioneering. Blue Ridge Envisioneering will integrate BrainChip Akida processors into Blue Ridge’s designs for tactical edge devices used by defense and intelligence agencies.
The co-developed tactical edge devices will deploy in harsh, resource-constrained environments with limited power access and strict thermal requirements. The BrainChip Akida platform’s proficiency in functioning effectively in extreme situations and its ability to offer advanced artificial intelligence capabilities at the edge makes it suitable for military applications.
...
BrainChip recently announced the development of its latest Akida platform, which is designed for embedded edge AI applications and features 8-bit processing. The new system utilizes vision transformers and Temporal Event Based Neural Nets (TENN) spatial-temporal convolutions to improve performance and power efficiency.
The Brainchip/Blue Ridge partnership should be a neat fit, or rather a significant technical advancement, for Parsons.
JDelekto
Regular
Wow. What a small world. As a high school student during the late 1980s, I worked as a student programmer for Parsons Engineering Science in Atlanta (they had acquired the small civil engineering firm in 1981).
Those were some of the most enjoyable projects I've worked on in my professional career, including hardware and software solutions for remote monitoring and control of tank pumps, remote calibration and measurement of rainwater levels, or simplifying calculations for treatment plant operations. Most of what they did was very innovative, integrating off-the-shelf components to create very unique automated solutions for their customers.
I can see how Parsons' subsidiaries and companies would benefit from using BrainChip's technology in their solutions, specifically for smart infrastructure projects. While they were a team that focused on Civil Engineering, they would usually contract out to Electrical Engineers for solutions that would make MacGyver proud.
While things are probably very different from what they were in the 80s, back then, I could envision someone using Akida (if it were available at that time) and cobbling together a custom solution for a client. By the way, most of their clients were large corporations and sometimes involved multi-year contracts regulated by government entities.
Thanks for that trip down memory lane!
Stable Genius
Regular
Vedya talking NPU’s:
www.linkedin.com
Do you like to have a control on your data and ensure AI models run instantly at the EDGE? | Vedya Labs
Do you like to have a control on your data and ensure AI models run instantly at the EDGE? 𝐓𝐡𝐚𝐭’𝐬 𝐰𝐡𝐞𝐫𝐞 𝐍𝐏𝐔𝐬 𝐜𝐨𝐦𝐞 𝐢𝐧. We talk a lot about GPUs when it comes to AI — and rightly so. But as AI shifts to the edge — phones, cameras, sensors — the game changes. NPUs (Neural Processing Units) are...
GazDix
Regular
100%.
Experiment with other LLMs and they all cater and adjust to your biases. OpenAi have revealed they keep all your data.
For those who use ChatGPT often, try using the same question about BRN with a family member's account, maybe in a different house or different ISP address with a VPN on. See if you get the same results...
Under 16s good too for now. But don't dare look up history videos in Youtube.
Getupthere
Regular
CEO Tim Cook says Apple ready to open its wallet to catch up in AI — Reuters
Apple (AAPL.O) CEO Tim Cook signaled on Thursday the iPhone maker was ready to spend more to catch up to rivals in artificial intelligence by building more data centers or buying a larger player in the segment, a departure from a long practice of fiscal frugality.
Yes. I've worked on satellite comms, radio navigation, optical fibre projects, ... . This is the most exciting time in the electronics/computing field ever. Having been retired for several years, I'm more than a little envious, so I get my vicarious kicks from following Brainchip.
Maybe one of the new era jobs will be in model development and SNN configuration?
BrainShit
Regular
When googling for “Brainchip Akida” the other day, I stumbled across an Interesting Engineering article titled “Can an AI chip that mimics the brain beat the data deluge?”, but couldn’t access it at the time, because it was behind a paywall. (IMO it makes far more sense to spend the equivalent of that 1 US$ on half a dozen BRN shares right now…)
View attachment 89044
Today I discovered a link on the BrainChip website under Investor Relations that will take you to a PDF document created by Sarah Marker from Bospar (our new PR & Marketing Agency), which contains screenshots of that same article:
BrainChip’s neuromorphic approach to energy-efficient computing – BrainChip Investor Portal
investor.brainchip.com
“Brain-inspired chips slash AI power to micro-joules, but 8-bit limits and tooling gaps keep neuromorphic tech niche, for now.”
Learn more
…which links to…
She (or whoever else took those screenshots) unfortunately cut off some lines of text on each page, so in case we have any IE subscribers here on TSE, they may want to double-check whether we missed out on anything important.
View attachment 89045
View attachment 89027
View attachment 89028 View attachment 89029 View attachment 89030
View attachment 89031 View attachment 89032
View attachment 89034
This article - based on an interview with our CMO Steve Brightfield - should serve as a reality check to those shareholders who see virtually everything about BRN through rose-coloured glasses.
One challenge relating to the adoption of neuromorphic technology is that certain applications benefit more than others:
“It is important to note that the power savings are dramatic only in high sparsity scenarios such as static security cameras, sparse sensor data, and anomaly detection. ‘If the scene is a very active video feed with significant motion, resulting in low sparsity, you can expect considerably less savings,’ Brightfield cautioned.”
The last paragraph, where Steve Brightfield is quoted as saying “We’re still in the early stages of understanding how to best leverage neuromorphic architectures”,
might also be rather sobering for quite a few (especially long-term) shareholders. Our CMO then added: “The real test will be whether these efficiency gains can translate into broader applications as the technology matures.”
Now does that sound like our Chief Marketing Officer were talking about our company as being entirely de-risked and about imminent “generational wealth” for shareholders? Or is it rather an honest and realistic assessment of BrainChip’s current market position?
Here's a link to a "readable" version. This page also allows you to "save and display" websites that are behind a paywall / proxy ;-)
Source: https://archive.ph/89ax6
Last edited:
gilti
Regular
Hi Chippers,
This is just a big thank you to all the amazing sleuths out there continuing the ever expanding research into the Brainchip world.
As a technically illiterate man in the street it is such a bonus having these continuous streams of valuable information being presented.
So thanks again for your efforts. It is very much appreciated.
Gilti
This is just a big thank you to all the amazing sleuths out there continuing the ever expanding research into the Brainchip world.
As a technically illiterate man in the street it is such a bonus having these continuous streams of valuable information being presented.
So thanks again for your efforts. It is very much appreciated.
Gilti
Fullmoonfever
Top 20
Was googling some search words as I do and this person's CV came up. No longer with BRN but was, back in mid 2023, for 3 mths as a ML Intern working on MB EQXX.
What I found interesting is that it appears MB maybe weren't just testing or playing with Akida for "Hey Mercedes" KWS but also driver distraction via sensors if I read correctly?
AND...over a year after the EQXX demo in early 2022 if this person's dates are correct.
Nice to see pretty damn good anomaly detection performace against a high end, though slightly older, GTX 1080 GPU.
HERE
What I found interesting is that it appears MB maybe weren't just testing or playing with Akida for "Hey Mercedes" KWS but also driver distraction via sensors if I read correctly?
AND...over a year after the EQXX demo in early 2022 if this person's dates are correct.
Nice to see pretty damn good anomaly detection performace against a high end, though slightly older, GTX 1080 GPU.
HERE
Similar threads
