BRN Discussion Ongoing

[Dijon101]

Brain inspired machines are better at math than expected | ScienceDaily https://share.google/wG1D8I8d7q4gxeZgi

"Brain inspired machines are better at math than expected
Brain-inspired computers just proved they can tackle supercomputer-level math — using a fraction of the energy.
Date:
February 14, 2026
Source:
DOE/Sandia National Laboratories
Summary:
Neuromorphic computers modeled after the human brain can now solve the complex equations behind physics simulations — something once thought possible only with energy-hungry supercomputers. The breakthrough could lead to powerful, low-energy supercomputers while revealing new secrets about how our brains process information."

Not specifically about brainchip, however just further evidence we are invested in the right space.

 

[smoothsailing18]

curlednoodles

To add to this, I found this paper “Robust iterative value conversion: Deep reinforcement learning for neurochip-driven edge robots” (2024).

One author is from MegaChips (Shinya Nishimura, MegaChips Corporation) and others are NAIST-affiliated.
They explicitly use Akida 1000, but call it a neurochip.

MegaChips × NAIST Paper Summary:

It’s a direct MegaChips ↔ NAIST link in print.The author list includes NAIST researchers and a MegaChips Corporation co-author, so this isn’t just corporate website wording — it’s a real joint technical output.
It’s explicitly about SNN robot control on edge hardware. The whole paper is focused on training and running spiking neural network (SNN) policies for battery-limited edge robots using deep reinforcement learning (DRL).
The “neurochip” is named as Akida 1000.In their evaluation, they state the SNN is run on “neurochip (Akida 1000),” which is the key hardware pin that ties this NAIST/MegaChips robotics work to BrainChip/Akida.
They report the exact kind of edge-robot benefit MegaChips would care about.The paper reports ~15× lower power and ~5× faster calculation versus an ARM Cortex-A72 edge CPU baseline — i.e., practical real-time control advantages under tight power constraints.

Conclusion: this paper is strong evidence that MegaChips + NAIST have already implemented SNN-based robot control on Akida 1000, with measured power/speed benefits — which makes MegaChips’ broader NAIST/SNN robotics messaging far more credible.

@manny100@Fact Finder

 

[FuzM]

curlednoodles

To add to this, I found this paper “Robust iterative value conversion: Deep reinforcement learning for neurochip-driven edge robots” (2024).

One author is from MegaChips (Shinya Nishimura, MegaChips Corporation) and others are NAIST-affiliated.
They explicitly use Akida 1000, but call it a neurochip.

MegaChips × NAIST Paper Summary:

It’s a direct MegaChips ↔ NAIST link in print.The author list includes NAIST researchers and a MegaChips Corporation co-author, so this isn’t just corporate website wording — it’s a real joint technical output.
It’s explicitly about SNN robot control on edge hardware. The whole paper is focused on training and running spiking neural network (SNN) policies for battery-limited edge robots using deep reinforcement learning (DRL).
The “neurochip” is named as Akida 1000.In their evaluation, they state the SNN is run on “neurochip (Akida 1000),” which is the key hardware pin that ties this NAIST/MegaChips robotics work to BrainChip/Akida.
They report the exact kind of edge-robot benefit MegaChips would care about.The paper reports ~15× lower power and ~5× faster calculation versus an ARM Cortex-A72 edge CPU baseline — i.e., practical real-time control advantages under tight power constraints.

Conclusion: this paper is strong evidence that MegaChips + NAIST have already implemented SNN-based robot control on Akida 1000, with measured power/speed benefits — which makes MegaChips’ broader NAIST/SNN robotics messaging far more credible.

@manny100@Fact Finder

Video

Paper

 

[suss]

Video

Paper

There are a number of videos on this channel.

 

[FuzM]

There are a number of videos on this channel.

Naist find especially with video as recent as a week ago

 

[Deleted member 3781]

Hmmm

CES 2026: MIDI Gear to Watch—and the Accessibility Tech That Can Change How We Make Music

CES 2026 ran January 6–9, 2026 in Las Vegas, and once again the show floor was full of ideas that matter to music creators: new ways to control software, new [...]

midi.org

BRAIN INTERFACES AND ON-DEVICE AI (BRAINEULINK + BRAINCHIP)​

BraineuLink describes work on non-invasive EEG brain-computer interfaces for decoding user intentions and interfacing with digital devices, while BrainChip describes its Akida neuromorphic processor platform for low-power, real-time edge AI.

MIDI relevance: these are enabling technologies: lower-power on-device perception and alternate input methods are exactly what’s needed for future accessible instruments, adaptive controllers, and context-aware performance rigs.

BraineuLink

Apart from they are from Taiwan and started in 2021 there ain’t much online about the company


View attachment 95126
View attachment 95127

Portfolio | Maxpro Ventures

www.maxproventures.com

At BraineuLink Technology Inc, they are pioneering the development of non-invasive EEG brain-computer interfaces (BCI).



Their advanced systems include cutting-edge algorithms for decoding user intentions and innovative BCI chips.



They are focused on creating intelligent solutions that allow seamless brain interaction with digital devices such as mobile applications and AR glasses, as well as translating EEG signals into text.



Their mission is to make neural interfacing technology accessible and transformative for everyday use.

Why the hat ?

 

[Stable Genius]

Video

Paper

Awesome @FuzM

Thanks for sharing.

@manny100 Based on that video very happy to say I’m wrong about Megachips still testing Akida.

Great to see!

 

[Baron Von Ricta]

Hmmm

CES 2026: MIDI Gear to Watch—and the Accessibility Tech That Can Change How We Make Music

CES 2026 ran January 6–9, 2026 in Las Vegas, and once again the show floor was full of ideas that matter to music creators: new ways to control software, new [...]

midi.org

BRAIN INTERFACES AND ON-DEVICE AI (BRAINEULINK + BRAINCHIP)​

BraineuLink describes work on non-invasive EEG brain-computer interfaces for decoding user intentions and interfacing with digital devices, while BrainChip describes its Akida neuromorphic processor platform for low-power, real-time edge AI.

MIDI relevance: these are enabling technologies: lower-power on-device perception and alternate input methods are exactly what’s needed for future accessible instruments, adaptive controllers, and context-aware performance rigs.

BraineuLink

Apart from they are from Taiwan and started in 2021 there ain’t much online about the company


View attachment 95126
View attachment 95127

Portfolio | Maxpro Ventures

www.maxproventures.com

At BraineuLink Technology Inc, they are pioneering the development of non-invasive EEG brain-computer interfaces (BCI).



Their advanced systems include cutting-edge algorithms for decoding user intentions and innovative BCI chips.



They are focused on creating intelligent solutions that allow seamless brain interaction with digital devices such as mobile applications and AR glasses, as well as translating EEG signals into text.



Their mission is to make neural interfacing technology accessible and transformative for everyday use.

I've been waiting for these for many years. Reckon they are now becoming a reality

 

[LongTermInvestor]

curlednoodles

To add to this, I found this paper “Robust iterative value conversion: Deep reinforcement learning for neurochip-driven edge robots” (2024).

One author is from MegaChips (Shinya Nishimura, MegaChips Corporation) and others are NAIST-affiliated.
They explicitly use Akida 1000, but call it a neurochip.

MegaChips × NAIST Paper Summary:

It’s a direct MegaChips ↔ NAIST link in print.The author list includes NAIST researchers and a MegaChips Corporation co-author, so this isn’t just corporate website wording — it’s a real joint technical output.
It’s explicitly about SNN robot control on edge hardware. The whole paper is focused on training and running spiking neural network (SNN) policies for battery-limited edge robots using deep reinforcement learning (DRL).
The “neurochip” is named as Akida 1000.In their evaluation, they state the SNN is run on “neurochip (Akida 1000),” which is the key hardware pin that ties this NAIST/MegaChips robotics work to BrainChip/Akida.
They report the exact kind of edge-robot benefit MegaChips would care about.The paper reports ~15× lower power and ~5× faster calculation versus an ARM Cortex-A72 edge CPU baseline — i.e., practical real-time control advantages under tight power constraints.

Conclusion: this paper is strong evidence that MegaChips + NAIST have already implemented SNN-based robot control on Akida 1000, with measured power/speed benefits — which makes MegaChips’ broader NAIST/SNN robotics messaging far more credible.

@manny100@Fact Finder

The flow of positive developments lately hasn’t just been steady - it’s been accelerating. And with the AGM approaching, momentum feels like it’s building, not fading.

Now look at the latest Shortman data, ASIC Short Report & ASX Short Data - a noticeable surge in fresh short positions. Seriously… what are they chasing here? A 1-2 cent dip from $0.135? That’s the grand prize?

Because if a single major announcement drops out of nowhere, this doesn’t move 1-2 cents… it reprices. Fast. And violently.

Cast your mind back to January 2022. The share price exploded to an ATH of $2.34 largely on the back of the Mercedes-Benz hype alone.

Today? The foundation is on a completely different level.

We’re talking involvement with the United States Air Force, NASA, Ant61, Onsor - and endorsement from IBM’s Field CTO, who is publicly demonstrating real-world Akida applications. That is not speculation. That is validation. When someone in IBM’s leadership ranks showcases your tech live, the market eventually pays attention.

And let’s not forget - the AKD1500 and AKD2500 physical chips are expected in Q3 2026 (possibly earlier). Physical silicon changes perception. It shifts the narrative from potential to deployment.

So ask yourself: if the market pushed this to $2.34 on hype in 2022… what happens now, with materially stronger fundamentals and real-world validation, if meaningful news lands between now and the AGM?

Shorts are playing for pennies. But they’re exposed to dollars.

Risk absolutely cuts both ways - and right now, the asymmetry looks far more dangerous for anyone betting against it.

Sometimes the biggest moves happen when the crowd least expects them.

 

[Baron Von Ricta]

Today on the ASX it's battle of the Botts for BRN once again. Every time one Bot raises the share price by .25 the other Bot at the exact same time pushes it back down. It's great to be part of a fair system

 

[gilti]

Today on the ASX it's battle of the Botts for BRN once again. Every time one Bot raises the share price by .25 the other Bot at the exact same time pushes it back down. It's great to be part of a fair system

View attachment 95142

Horrorfing but thus crap has been going on for years. It is called "promoting liquidity" according to the ASX.

 

[Bravo]

Since yesterday's post I've been doing a bit more research into Loihi 3 and discovered a very long and detailed blog on Loihi 3 from someone called Dr Shayan Erfanian (see link below).

The profile material I found presents Dr Erfanian as a technology strategist and software/cybersecurity entrepreneur, not obviously a primary neuromorphic researcher ,which I think pushes the blog more toward forecasting rather than authoritative disclosure.

For what it's worth, Dr Erfanian says that we can expect to hear more about Loihi 3 at the Intel Developer Conference in Q2/3 2026.

In another expert he states "the 2-3 year horizon following Loihi 3's launch (2028-2029) will witness substantial industry restructuring as the energy efficiency benefits of neuromorphic computing become widely acknowledged and integrated."

Dr Shayan Erfanian - Technology Mentor & Strategist

University professor and technology strategist. Teaching thousands of students and mentoring startup founders in AI, digital transformation, and business innovation.

shayanerfanian.com

Excerpt 1

Excerpt 2

All of these ruminations about the emergence of Loihi 3 would seem to align with Intel's job advertising published 16 days ago for an AI Software Architect Neuromorhpic Computing.

The job ad says "Now, we're entering an exciting new chapter: transforming these breakthroughs into real-world products that will power the coming era of physical AI systems beyond the reach of GPUs and mainstream AI accelerators." It also states a key responsibility is to "Integrate neuromorphic software into leading robotics, IoT, and sensing frameworks to enable broad ecosystem adoption."



Intel's Job Ad

AI Software Architect – Neuromorphic Computing

Job Details: Job Description: For nearly a decade, Intel's Neuromorphic Computing Lab-together with a global ecosystem of 250+ research groups-has explored architectures, algorithms, and software inspired by the brain's extraordinary efficiency, scalability, and adaptability. Our Loihi series of...

intel.wd1.myworkdayjobs.com

​

The other thing that struck me yesterday about Mike Davies LinkedIn Post 8 months ago on Loihi 3 was how similar it sounded to Akida 2 with regard to features such as LLM's (see below).

I realise that the addressable market is big enough for more than 1 player, but Intel is a behemoth of a player and therefore a pretty significant threat.

I can’t deny feeling quite disappointed that what once looked like a meaningful lead has now narrowed.

In hindsight, relying solely on an IP-only strategy appears to have seriously limited commercial traction. The pivot to physical chips AKD1500 (and now AKD2500) feels, at least to me, like an acknowledgment that licensing alone wasn’t able to convert at the pace required.

Having said that, I can understand the appeal of the IP-only idea because it's capital-light (no wafer commitments, inventory risk, or hardware support burden). But in practice, IP-only seems to work best when there’s already a mature ecosystem, strong reference implementations and customers ready to integrate with confidence. Neuromorphic as a new and disruptive technology would make pure IP much harder to monetise.

The key question now isn’t whether the pivot was necessary but whether it was too late. The risk is that competitors with much deeper resources and broader ecosystems may be able to close the window further.

In the coming months I'll be keeping a very close eye on any primary sources from Intel announcing Loihi 3 specs.

​

 

[Guzzi62]

Since yesterday's post I've been doing a bit more research into Loihi 3 and discovered a very long and detailed blog on Loihi 3 from someone called Dr Shayan Erfanian (see link below).

The profile material I found presents Dr Erfanian as a technology strategist and software/cybersecurity entrepreneur, not obviously a primary neuromorphic researcher ,which I think pushes the blog more toward forecasting rather than authoritative disclosure.

For what it's worth, Dr Erfanian says that we can expect to hear more about Loihi 3 at the Intel Developer Conference in Q2/3 2026.

In another expert he states "the 2-3 year horizon following Loihi 3's launch (2028-2029) will witness substantial industry restructuring as the energy efficiency benefits of neuromorphic computing become widely acknowledged and integrated."

Dr Shayan Erfanian - Technology Mentor & Strategist

University professor and technology strategist. Teaching thousands of students and mentoring startup founders in AI, digital transformation, and business innovation.

shayanerfanian.com

Excerpt 1

View attachment 95145



Excerpt 2

View attachment 95146



All of these ruminations about the emergence of Loihi 3 would seem to align with Intel's job advertising published 16 days ago for an AI Software Architect Neuromorhpic Computing.

The job ad says "Now, we're entering an exciting new chapter: transforming these breakthroughs into real-world products that will power the coming era of physical AI systems beyond the reach of GPUs and mainstream AI accelerators." It also states a key responsibility is to "Integrate software into leading robotics, IoT, and sensing frameworks to enable broad ecosystem adoption."



Intel's Job Ad

AI Software Architect – Neuromorphic Computing

Job Details: Job Description: For nearly a decade, Intel's Neuromorphic Computing Lab-together with a global ecosystem of 250+ research groups-has explored architectures, algorithms, and software inspired by the brain's extraordinary efficiency, scalability, and adaptability. Our Loihi series of...

intel.wd1.myworkdayjobs.com

​

The other thing that struck me yesterday about Mike Davies LinkedIn Post 8 months ago on Loihi 3 was how similar it sounded to Akida 2 with regard to features such as LLM's (see below).



View attachment 95147



I realise that the addressable market is big enough for more than 1 player, but Intel is a behemoth of a player and therefore a pretty significant threat.

I can’t deny feeling quite disappointed that what once looked like a meaningful lead has now narrowed.

In hindsight, relying solely on an IP-only strategy appears to have seriously limited commercial traction. The pivot to AKD1500 feels, at least to me, like an acknowledgment that licensing alone wasn’t able to convert at the pace required.

Having said that, I can understand the appeal of the IP-only idea because it's capital-light (no wafer commitments, inventory risk, or hardware support burden). But in practice, IP-only seems to work best when there’s already a mature ecosystem, strong reference implementations and customers ready to integrate with confidence. Neuromorphic as a new and disruptive technology would make pure IP much harder to monetise.

The key question now isn’t whether the pivot was necessary but whether it was too late. The risk is that competitors with much deeper resources and broader ecosystems may be able to close the window further.

In the coming months I'll be keeping a very close eye on any primary sources from Intel announcing Loihi 3 specs.

​

Very nice DD Bravo.

Competition is unavoidable but if they first launch in 2028-29, BRN should have ample time to have secured its place on the market.

Further Akida comes in different editions as we know, 1000-1500-2500 physical chips and IP AKD2/Pico/TENNS as the flagship model but AKD3 being developed which means BRN can offer quite a large range of neuromorphic edge coverage.
We don't know anything about Loihi3 yet, so I will not try to speculate of how good/bad and narrow/wide ranged it will be?

Sean said that quite a few small players don't have resources to develop their own chips and tap them out hence the 1500 will be mass-produced for smaller companies only needing maybe 10k chips or less.

As you mentioned, producing your own chip is expensive and man power heavy. You're also risking a customer wanting chips in 5nm, and you just made 1 million in 22nm! The company simply don't have the resources doing their own chips right now, but they have done what they could: 1500 in 22nm and 2500 as a research chip for prototypes/testing.

Slade said it's good Loihi3 is coming because it's a sign that the transition to edge AI is accelerating, and he got a point.

If Akida is good enough, I don't think we have anything to worry about.
It's telling that a fairly high ranking IBM person are very positive about AKD1000 on M2 card!

 

[Deleted member 3781]

Since yesterday's post I've been doing a bit more research into Loihi 3 and discovered a very long and detailed blog on Loihi 3 from someone called Dr Shayan Erfanian (see link below).

The profile material I found presents Dr Erfanian as a technology strategist and software/cybersecurity entrepreneur, not obviously a primary neuromorphic researcher ,which I think pushes the blog more toward forecasting rather than authoritative disclosure.

For what it's worth, Dr Erfanian says that we can expect to hear more about Loihi 3 at the Intel Developer Conference in Q2/3 2026.

In another expert he states "the 2-3 year horizon following Loihi 3's launch (2028-2029) will witness substantial industry restructuring as the energy efficiency benefits of neuromorphic computing become widely acknowledged and integrated."

Dr Shayan Erfanian - Technology Mentor & Strategist

University professor and technology strategist. Teaching thousands of students and mentoring startup founders in AI, digital transformation, and business innovation.

shayanerfanian.com

Excerpt 1

View attachment 95145



Excerpt 2

View attachment 95146



All of these ruminations about the emergence of Loihi 3 would seem to align with Intel's job advertising published 16 days ago for an AI Software Architect Neuromorhpic Computing.

The job ad says "Now, we're entering an exciting new chapter: transforming these breakthroughs into real-world products that will power the coming era of physical AI systems beyond the reach of GPUs and mainstream AI accelerators." It also states a key responsibility is to "Integrate neuromorphic software into leading robotics, IoT, and sensing frameworks to enable broad ecosystem adoption."



Intel's Job Ad

AI Software Architect – Neuromorphic Computing

Job Details: Job Description: For nearly a decade, Intel's Neuromorphic Computing Lab-together with a global ecosystem of 250+ research groups-has explored architectures, algorithms, and software inspired by the brain's extraordinary efficiency, scalability, and adaptability. Our Loihi series of...

intel.wd1.myworkdayjobs.com

​

The other thing that struck me yesterday about Mike Davies LinkedIn Post 8 months ago on Loihi 3 was how similar it sounded to Akida 2 with regard to features such as LLM's (see below).



View attachment 95147



I realise that the addressable market is big enough for more than 1 player, but Intel is a behemoth of a player and therefore a pretty significant threat.

I can’t deny feeling quite disappointed that what once looked like a meaningful lead has now narrowed.

In hindsight, relying solely on an IP-only strategy appears to have seriously limited commercial traction. The pivot to physical chips AKD1500 (and now AKD2500) feels, at least to me, like an acknowledgment that licensing alone wasn’t able to convert at the pace required.

Having said that, I can understand the appeal of the IP-only idea because it's capital-light (no wafer commitments, inventory risk, or hardware support burden). But in practice, IP-only seems to work best when there’s already a mature ecosystem, strong reference implementations and customers ready to integrate with confidence. Neuromorphic as a new and disruptive technology would make pure IP much harder to monetise.

The key question now isn’t whether the pivot was necessary but whether it was too late. The risk is that competitors with much deeper resources and broader ecosystems may be able to close the window further.

In the coming months I'll be keeping a very close eye on any primary sources from Intel announcing Loihi 3 specs.

​

Just a thought ….could this have been tactical? BrainChip is too small to move the market alone, so maybe the timing depended on a larger player being ready.
I’m not convinced it was a “big mistake.” Leadership (incl. PvdM etc) isn’t naïve …they typically don’t act without a plan.

Maybe we simply can’t see the full picture yet. Time will tell. DYOR.

 

[jrp173]

We have actual real-world testing involving Akida running in an IBM setup, hooked into IBM Symphony workflows.

I’m sure most people would consider this as a positive.

Surely one would expect (as an absolute minimum) that BrainChip would repost this information on their own LinkedIn page and other social media channels?

Happy to be corrected, but I have not seen anything from BrainChip itself on official channels, except a couple of replies inside Kevin’s LinkedIn posts.

I don’t understand why BrainChip do nothing to champion their own technology, on the back of what Kevin Johnson is posting.

It’s not ramping, for BrainChip to share Kevin’s post on their LinkedIn page.

Why are they not doing this?

 

[LongTermInvestor]

We have actual real-world testing involving Akida running in an IBM setup, hooked into IBM Symphony workflows.

I’m sure most people would consider this as a positive.

Surely one would expect (as an absolute minimum) that BrainChip would repost this information on their own LinkedIn page and other social media channels?

Happy to be corrected, but I have not seen anything from BrainChip itself on official channels, except a couple of replies inside Kevin’s LinkedIn posts.

I don’t understand why BrainChip do nothing to champion their own technology, on the back of what Kevin Johnson is posting.

It’s not ramping, for BrainChip to share Kevin’s post on their LinkedIn page.

Why are they not doing this?

Perhaps it's a one-way NDA agreement, meaning the supplier (BrainChip) cannot initiate any post-discussion communications with the media, while the user is allowed to do so???

 

[Deleted member 3781]

Perhaps it's a one-way NDA agreement, meaning the supplier (BrainChip) cannot initiate any post-discussion communications with the media, while the user is allowed to do so???

No, I don’t think so. They posted on his post kind of..it would be great to work together,…but so far this looks like a tryout without any formal agreement. If they reposted it officially on BrainChip’s account now, it could be misleading and create the impression that there’s an official engagement. And given how closely anything around BrainChip is watched (especially on the ASX side), they can’t realistically repost and promote every single project where Akida is being tested.

 

[LongTermInvestor]

No, I don’t think so. They posted on his post kind of..it would be great to work together,…but so far this looks like a tryout without any formal agreement. If they reposted it officially on BrainChip’s account now, it could be misleading and create the impression that there’s an official engagement. And given how closely anything around BrainChip is watched (especially on the ASX side), they can’t realistically repost and promote every single project where Akida is being tested.

Thanks! That's a reasonable explanation.

 

[Newk R]

This is excellent news. I bought 3 more shares today.
Not advice

With all the good news around, and the confidence I have, I'm saving up to buy another share.

 

[Diogenese]

Since yesterday's post I've been doing a bit more research into Loihi 3 and discovered a very long and detailed blog on Loihi 3 from someone called Dr Shayan Erfanian (see link below).

The profile material I found presents Dr Erfanian as a technology strategist and software/cybersecurity entrepreneur, not obviously a primary neuromorphic researcher ,which I think pushes the blog more toward forecasting rather than authoritative disclosure.

For what it's worth, Dr Erfanian says that we can expect to hear more about Loihi 3 at the Intel Developer Conference in Q2/3 2026.

In another expert he states "the 2-3 year horizon following Loihi 3's launch (2028-2029) will witness substantial industry restructuring as the energy efficiency benefits of neuromorphic computing become widely acknowledged and integrated."

Dr Shayan Erfanian - Technology Mentor & Strategist

University professor and technology strategist. Teaching thousands of students and mentoring startup founders in AI, digital transformation, and business innovation.

shayanerfanian.com

Excerpt 1

View attachment 95145



Excerpt 2

View attachment 95146



All of these ruminations about the emergence of Loihi 3 would seem to align with Intel's job advertising published 16 days ago for an AI Software Architect Neuromorhpic Computing.

The job ad says "Now, we're entering an exciting new chapter: transforming these breakthroughs into real-world products that will power the coming era of physical AI systems beyond the reach of GPUs and mainstream AI accelerators." It also states a key responsibility is to "Integrate neuromorphic software into leading robotics, IoT, and sensing frameworks to enable broad ecosystem adoption."



Intel's Job Ad

AI Software Architect – Neuromorphic Computing

Job Details: Job Description: For nearly a decade, Intel's Neuromorphic Computing Lab-together with a global ecosystem of 250+ research groups-has explored architectures, algorithms, and software inspired by the brain's extraordinary efficiency, scalability, and adaptability. Our Loihi series of...

intel.wd1.myworkdayjobs.com

​

The other thing that struck me yesterday about Mike Davies LinkedIn Post 8 months ago on Loihi 3 was how similar it sounded to Akida 2 with regard to features such as LLM's (see below).



View attachment 95147



I realise that the addressable market is big enough for more than 1 player, but Intel is a behemoth of a player and therefore a pretty significant threat.

I can’t deny feeling quite disappointed that what once looked like a meaningful lead has now narrowed.

In hindsight, relying solely on an IP-only strategy appears to have seriously limited commercial traction. The pivot to physical chips AKD1500 (and now AKD2500) feels, at least to me, like an acknowledgment that licensing alone wasn’t able to convert at the pace required.

Having said that, I can understand the appeal of the IP-only idea because it's capital-light (no wafer commitments, inventory risk, or hardware support burden). But in practice, IP-only seems to work best when there’s already a mature ecosystem, strong reference implementations and customers ready to integrate with confidence. Neuromorphic as a new and disruptive technology would make pure IP much harder to monetise.

The key question now isn’t whether the pivot was necessary but whether it was too late. The risk is that competitors with much deeper resources and broader ecosystems may be able to close the window further.

In the coming months I'll be keeping a very close eye on any primary sources from Intel announcing Loihi 3 specs.

​

Well it looks like Grasshopper Mike is prepared to learn from the master:

https://www.bing.com/videos/rivervi...om/channel/UC4BPiFQh-5JbyVpjZ68aXOg&FORM=VIRE


US2025371331A1 IMPLEMENTING N:M SPARSITY IN A DIGITAL COMPUTE-IN-MEMORY ACCELERATOR 20241114

To support flexible N:M sparsity pattern in a DCiM macro, the DCiM macro is subdivided into multiple sub-macros according to a partitioning factor P. Each sub-macro can support 1:2 sparsity ratio. Leveraging the partitioned design, the sub-macros can be grouped together to support different N:M sparsity patterns. To determine optimal N:N sparsity pattern for each layer of a neural network, an algorithm can determine the value A of a sparsity ratio A/B is based on the number of outliers in a layer, and the value B of the sparsity ratio A/B is based on the locality measure of the outliers representing the spatial distribution of the outliers. Moreover, the optimal N:M sparsity pattern that is aligned with the determined sparsity ratio A/B can be selected based on whether to prioritize latency or accuracy, or to balance both latency and accuracy.