BRN Discussion Ongoing

[shaun168]

Hi Shaun,

Looks like Chatty has its rose coloured glasses on.

One of the IXI co-founders is Willi (Villi?) Mirttinen, and it looks like he was an inventor of this patent from 2018:

US11099381B2 Synchronizing light sources and optics in display apparatuses 20180810

Applicants: VARJO TECH OY [FI]

Inventors: PEUHKURINEN ARI ANTTI ERIK [FI]; MIETTINEN VILLE ILMARI [FI]

View attachment 94282

A display apparatus, communicably coupled with a server arrangement via a data communication network, comprising:
means for tracking a user's gaze;
means for tracking a pose of the display apparatus;
at least one light source;
at least one optical element; and
a processor configured to:
process gaze-tracking data, collected by the means for tracking the user's gaze, to determine a gaze position, a gaze direction, a gaze velocity and a gaze acceleration per eye of the user;
process pose-tracking data, collected by the means for tracking the pose of the display apparatus, to determine a position, an orientation, a velocity and an acceleration of the display apparatus;
send, to the server arrangement, gaze information indicative of the gaze position, the gaze direction, the gaze velocity and the gaze acceleration of the user, and apparatus information indicative of the position, the orientation, the velocity and the acceleration of the display apparatus, wherein the server arrangement is configured to predict a gaze position, a gaze direction, a gaze velocity and a gaze acceleration per eye of the user based on the gaze information, predict a position, an orientation, a velocity and an acceleration of the display apparatus based on the apparatus information, and process an input image to generate at least one image, based on the predicted gaze position, the predicted gaze direction, the predicted gaze velocity and the predicted gaze acceleration, and the predicted position, the predicted orientation, the predicted velocity and the predicted acceleration of the display apparatus;
receive, from the server arrangement, the at least one image, predicted gaze information indicative of the predicted gaze position, the predicted gaze direction, the predicted gaze velocity and the predicted gaze acceleration, and predicted apparatus information indicative of the predicted position, the predicted orientation, the predicted velocity and the predicted acceleration of the display apparatus;
determine an adjustment to be made in a configuration of the at least one light source and the at least one optical element prior to displaying the at least one image, based on the predicted gaze information and the predicted apparatus information;
determine whether or not a portion of at least one previous image is to be displayed during the adjustment;
when it is determined that the portion of the at least one previous image is to be displayed, display the portion of the at least one previous image via the at least one light source, whilst making the adjustment in the configuration of the at least one light source and the at least one optical element;
when it is determined that no portion of the at least one previous image is to be displayed, switch off or dim the at least one light source, whilst making the adjustment in the configuration of the at least one light source and the at least one optical element; and
display the at least one image via the at least one light source after the adjustment is made.


More recently from the same company (optical distance measurement):

US2025216553A1 HYBRID DIRECT AND INDIRECT TIME-OF-FLIGHT IMAGING 20231227


Disclosed is a depth imaging system with a light source; a depth sensor comprising direct Time-of-Flight (dToF) pixels and indirect Time-of-Flight (iToF) pixels; and processor(s) configured to: employ the light source to emit an intensity-modulated light pulse towards objects in a real-world environment; obtain dToF data indicative of time taken by the intensity-modulated light pulse to reach the dToF pixels after being reflected by the objects; obtain iToF data indicative of phase shifts undergone by the intensity-modulated light pulse upon reaching the iToF pixels after being reflected by the objects; determine optical depths for the dToF pixels; determine optical depths for the iToF pixels; and generate a depth image from the optical depths of the dToF pixels and the optical depths of the iToF pixels.

[0048] Optionally, the optical depths for the iToF pixels are determined by using at least one neural network. Optionally, in this regard, an input of the at least one neural network comprises the iToF data indicative of the phase shifts and the optical depths determined for the dToF pixels, while an output of the at least one neural network comprises the optical depths for the iToF pixels. It will be appreciated that the at least one neural network determines the optical depths for the iToF pixels in a highly accurate manner by resolving said ambiguities, as compared to conventional techniques. In this way, the at least one neural network may act as a mapping function, providing refined depth predictions for the iToF pixels. This may enhance overall depth sensing in the real-world environment, and mitigate typical uncertainties involved in optical depth determination for the iToF pixels. It will also be appreciated that the aforesaid input is provided to the at least one neural network both in a training phase of the at least one neural network and in an inference phase of the at least one neural network (i.e., when the at least one neural is utilised after it has been trained).

{062] ... Optionally, the at least one processor is configured to employ at least one neural network for generating the high-resolution depth image.

While they refer to NNs, they don't seem to be interested in the details, but they do seem to think it is software, so there is no indication of an Akida link, but absence of evidence ...

Hi Diogenese,

IXI’s patents are not ideas pulled out of thin air. They are grounded in decades of established consensus in visual neuroscience. Purely software-based autofocus systems do not hold up at the theoretical level. Akida and neuromorphic chips represent the right architectural direction, not a marketing gimmick.

 

[FJ-215]

The amount of drivel posted by Tech continues.....

The company appreciates our support?? Shouldn't it be the other way around?

We "WILL" success because Aussies always punch above their weight? Really?

Once again, Tech, boasts about private conversations with Peter, where he has been told 2027 is our year and a big change is coming in the second half of 2026, yet Tech does not (or will not) disclose the details of his conversation with Peter to everyone else on the forum.. he'll just try and big note himself, and his relationship/friendship with Peter.

Tech has now for the second time in just a few days, alluded to the "change' that is coming. What is this change? Why do all shareholders not know about this change?

In what world is it appropriate that a founder and director of a company shares information with ONE shareholders who then comes online to talk about it, to boost his own ego....

It's like this Tech never learns....

Information has supposedly been told to a shareholder by a director (Peter) that has not been made public to all shareholders and he then comes on here telling us all that he's had said conversations with Peter. Work it out for yourself....

If Peter Van Der Made had even one commercial bone in his body, he'd know that he should NOT be disclosing information to one shareholder that has not been made public to all shareholders.

Work it out for yourselves everyone....

Unsure why behaviour this is tolerated on this site by users and admin.

If I were a betting man, I would wager on a big change coming in the 2nd half of this year.

Can't see this BoD surviving a second strike on the remuneration report at the AGM.

 

[jrp173]

You pathetic individual, that is full of defamatory statements, maybe, just maybe you took the bait......sour grapes surface yet again.

For the record, I know as much as you, which is probably f all.

I'm not the one claiming to have information...it's your post... You need to check yourself.

 

[Diogenese]

Hi Diogenese,

IXI’s patents are not ideas pulled out of thin air. They are grounded in decades of established consensus in visual neuroscience. Purely software-based autofocus systems do not hold up at the theoretical level. Akida and neuromorphic chips represent the right architectural direction, not a marketing gimmick.

Hi Sean,

As I said, those patents are owned by Varjo Tech, not IXI. Miettinen is an inventor of the first one (eye tracking) but not the second (distance measurement needed for autofocus), but it seems the glasses would embody both inventions. I'm guessing there is a relationship, such as a licence agreement, between IXI and Varjo.

The patents do not go into detail of the NN, other than to refer to it in terms of an algorithm, and as we know, and as Chatty says, Like Notlob, it don't work with software at those power levels, so it is likely they are using silicon.

The Frontgrade/ESA partnership does show that there is awareness of Akida in Scandinavia, in fact I think there is a Finnish link?

The fact that they are using time-of-flight over what would encompass quite short distances as well as longer distances while apparently accommodating the transition region, means that very fast response times would be required. Long vision can be corrected with a single focal length lens, so the task is not quite so onerous, other than the gaze tracking and consequent differences in focal distance over the transition region. We also know that the see-in-the-dark radar which came out of the RTX/USAFRL micro-Doppler SBIR is capable of very fine graduations, so it is certainly not impossible that Akida could be used, but why would BRN keep it under wraps?

Was IXI at CES 2026?

 

[manny100]

I'm not the one claiming to have information...it's your post... You need to check yourself.

View attachment 94301

You are a shorter. Do you really think longs take you seriously. After all you make money when the share price falls.

 

[Space Cadet]

Neuromorphic hardware for sustainable AI datacenters

Paste the above in your browser. The pdf will be at top.
Apologies if already posted. Think it's from 2024 so possibly.

SC

 

[shaun168]

Hi Sean,

As I said, those patents are owned by Varjo Tech, not IXI. Miettinen is an inventor of the first one (eye tracking) but not the second (distance measurement needed for autofocus), but it seems the glasses would embody both inventions. I'm guessing there is a relationship, such as a licence agreement, between IXI and Varjo.

The patents do not go into detail of the NN, other than to refer to it in terms of an algorithm, and as we know, and as Chatty says, Like Notlob, it don't work with software at those power levels, so it is likely they are using silicon.

The Frontgrade/ESA partnership does show that there is awareness of Akida in Scandinavia, in fact I think there is a Finnish link?

The fact that they are using time-of-flight over what would encompass quite short distances as well as longer distances while apparently accommodating the transition region, means that very fast response times would be required. Long vision can be corrected with a single focal length lens, so the task is not quite so onerous, other than the gaze tracking and consequent differences in focal distance over the transition region. We also know that the see-in-the-dark radar which came out of the RTX/USAFRL micro-Doppler SBIR is capable of very fine graduations, so it is certainly not impossible that Akida could be used, but why would BRN keep it under wraps?

Was IXI at CES 2026?

https://www.techradar.com/health-fitness/were-redefining-eyewear-on-a-really-high-level-i-like-to-use-a-camera-analogy-fixed-focus-manual-focus-and-then-autofocus-what-were-trying-to-do-is-autofocus-ixis-ceo-on-the-tech-behind-ces-2026s-most-exciting-eyeglasses

Hi Diogenese,
Based on media coverage, IXI did attend CES 2026. What is interesting, however, is that there appeared to be no visible interaction or cross-referencing with BrainChip at the event. That absence itself is somewhat curious. If there is indeed a deeper technical relationship or dependency, one has to wonder whether IXI is being deliberately cautious about disclosing certain aspects of its implementation at this stage.

 

[Diogenese]

Have a read of this job in the link
View attachment 94304 https://www.linkedin.com/jobs/view/4305787727
Check out this job at Type 1 Compute:
https://www.linkedin.com/jobs/view/430578772

View attachment 94305

Hi TTM,

T1C are starting well behind the scratch mark:

Application Note Template

Energy Efficiency Benchmarking Report: YOLO Model APPLICATION NOTE SEPTEMBER 26, 2025
...
We designed and implemented SpikeYOLO [1], a bio-inspired approach using spiking neural networks (SNNs) that communicate through binary spikes. This architecture enables energy-efficient computation through sparse addition operations rather than power-intensive MAC operations. We incorporated two critical innovations in our SpikeYOLO implementation:

Simplified Architecture: Streamlined design removing complex modules from YOLOv8 that cause spike degradation

Integer-LIF (I-LIF) Neurons: Novel spiking neurons that train with integer values but inference with binary spikes.
...

5. Roadmap We are going to ship our neuromorphic HDK (Artix-7/US+, PCIe Gen2 x4) to early users with SDK v0.1 and reproducible YOLOv8/YOLO-KP benchmarks (target ≥40 FPS @ ≤1 W, ~75.7 GOP/s/W); validate neuromorphic advantages with end-to-end energy profiling and temporal-sparsity wins (≥2–3× GOP/s/W vs. Jetson Nano) across multiple scenes; and advance a 28 nm ASIC targeting ~1.2 TOP/s, ~0.3 W, (~4.0 TOP/s/W), with performance targets validated via pre-silicon emulation, shuttle tape-out, and post-silicon correlation.

They are TENNs of miles behind.

 

[Diogenese]

https://www.techradar.com/health-fitness/were-redefining-eyewear-on-a-really-high-level-i-like-to-use-a-camera-analogy-fixed-focus-manual-focus-and-then-autofocus-what-were-trying-to-do-is-autofocus-ixis-ceo-on-the-tech-behind-ces-2026s-most-exciting-eyeglasses

Hi Diogenese,
Based on media coverage, IXI did attend CES 2026. What is interesting, however, is that there appeared to be no visible interaction or cross-referencing with BrainChip at the event. That absence itself is somewhat curious. If there is indeed a deeper technical relationship or dependency, one has to wonder whether IXI is being deliberately cautious about disclosing certain aspects of its implementation at this stage.

Hi Sean,

Thanks for checking. I take that as a definite "maybe not".

 

[Diogenese]

Hi Sean,

Thanks for checking. I take that as a definite "maybe not".

Hi Sean,

Their web site has a potted history of the creation of IXI:

https://ixieyewear.com/articles/meet-the-co-founders

Obviously a couple of very smart people, but neither founder has a background in NN SoCs. What experience they had was in NN algorithms.

Whatever they are doing Akida/TENNs will do it better.

 

[Fullmoonfever]

Further to previous posts on QANA as below, there has been an update on GitHub about an hour ago.

Some good results when combined with Akida processing.

Too big to post all so just posted the contents with links so readers can click whatever of interest to review ie results.

BRN Discussion Ongoing

Because the market has heard it all before, and no longer believes the bullshit from BRN. The market wants hard evidence, not just "watch us" bullshit... Oh wow your upset

thestockexchange.com.au

Quantization-Aware Neuromorphic Architecture for Skin Disease Classification on Resource-Constrained Devices​

Table of Contents​

• 1. Introduction
• 2. Motivation and Background
  • 2.1 Why on-device skin lesion classification matters
  • 2.2 Why conventional CNN inference is not ideal for edge deployment
  • 2.3 Why neuromorphic computing (Akida) is a strong fit
  • 2.4 The practical barrier: CNN-to-SNN conversion brittleness
  • 2.5 Design goal: conversion-stable neuromorphic classification
• 3. Datasets & Hardware
  • 3.1 Datasets
    • 3.1.1 HAM10000 (Public Benchmark)
    • 3.1.2 Hospital Clinical Dataset (Proprietary)
  • 3.2 Hardware & Software Environment (Paper-Aligned)
    • 3.2.1 Training / Quantization / Conversion Workstation
    • 3.2.2 Neuromorphic Deployment Hardware (BrainChip Akida)
    • 3.2.3 What is measured on Akida
• 4. Methodology
  • 4.1 QANA Architecture Overview (Conversion-Oriented Design)
  • 4.2 Iterative Feature Extraction with Ghost Modules
  • 4.3 Spatially-Aware Efficient Channel Attention (SA-ECA)
  • 4.4 Spike-Compatible Feature Transformation with Squeeze-and-Excitation
  • 4.5 Quantization and Graph-Preserving CNN-to-SNN Conversion (Akida)
  • 4.6 Neuromorphic Deployment, Calibration, and Inference
• 5. Experimental Design
  • 5.1 Datasets and Splits
  • 5.2 Input Resolution and Preprocessing Policy
  • 5.3 Baselines and Fair Comparison Protocol
  • 5.4 Training and Model Selection
  • 5.5 Quantization, Conversion, and Deployment Stages
  • 5.6 Evaluation Metrics
  • 5.7 Neuromorphic Runtime Evaluation (Latency and Energy)
  • 5.8 Ablation Study Protocol
  • 5.9 Reproducibility Notes
• 6. Results and Performance
  • 6.1 Classification Performance
    • 6.1.1 HAM10000 (7 classes)
    • 6.1.2 Clinical Dataset (7 classes)
  • 6.2 Comparison with Converted SNN Baselines (Akida)
    • 6.2.1 HAM10000: Converted SNN Models on Akida
    • 6.2.2 Clinical Dataset: Converted SNN Models on Akida
  • 6.3 Neuromorphic Efficiency: Latency and Energy
  • 6.4 Ablation Study (HAM10000)

 

[Guzzi62]

If I were a betting man, I would wager on a big change coming in the 2nd half of this year.

Can't see this BoD surviving a second strike on the remuneration report at the AGM.

I certainly hope not, that would be a disaster and put us back years.

The dude you answered to is on ignore so no idea what he was saying and don't care either, a short seller.

Many from the crapper place thinks that more deals would have been made if we had another CEO, LOL!

I never understood why they/you think that would make any difference?

The market will strike when they are ready and not before, no matter who's in charge. The number of sales guys who passed though BRN over the last 3–4 years speaks for themselves!

Edge AI neuromorphic computing got more interest last year and will gain more momentum this year and that trend will continue I am sure.

Maybe try reading this excellent article below more carefully, that person knows what he is talking about, way more than us laymen retail investors.

Posted yesterday by Fullmoonfever.

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

 

[shaun168]

Hi Sean,

Their web site has a potted history of the creation of IXI:

https://ixieyewear.com/articles/meet-the-co-founders

Obviously a couple of very smart people, but neither founder has a background in NN SoCs. What experience they had was in NN algorithms.

Whatever they are doing Akida/TENNs will do it better.

Hi Diogenese,

It is understandable why some might be skeptical given the crowded nature of CES, but IXI Eyewear was definitively present at CES 2026 (held January 6–9, 2026).
The confusion likely stems from their exhibition strategy. Rather than a flashy booth in the main Central Hall of the Las Vegas Convention Center (LVCC), IXI followed the common path for high-end tech startups by hosting private, high-fidelity demonstrations in a dedicated suite at The Venetian.

Verified Reports and Evidence​

Multiple top-tier tech publications have published hands-on reviews and interviews conducted on-site in Las Vegas:

• TechRadar: Jeremy Kaplan (Editor-in-Chief) personally tested the device and published an article titled "IXI's CEO on the tech behind CES 2026's most exciting eyeglasses." He explicitly describes an "unpainted, transparent prototype" shown to him to reveal the internal components.
• Engadget: They featured IXI in their coverage, noting that the glasses are "almost ready to replace multifocal glasses" and confirmed the CEO's presence for interviews.
• CNET: Reported on January 6, 2026, about IXI's participation, highlighting the $40 million in funding (including from Amazon) and the tech's ability to "autofocus on the fly."

The "Venetian Connection"
As a shareholder, it is worth noting that BrainChip also hosted its private suite at The Venetian (Suite 29-116) during CES 2026. Both companies were operating out of the same building, which is the traditional hub for semiconductor and deep-tech companies to hold private "handshake" meetings with OEMs like IXI.

 

[FJ-215]

I certainly hope not, that would be a disaster and put us back years.

The dude you answered to is on ignore so no idea what he was saying and don't care either, a short seller.

Many from the crapper place thinks that more deals would have been made if we had another CEO, LOL!

I never understood why they/you think that would make any difference?

The market will strike when they are ready and not before, no matter who's in charge. The number of sales guys who passed though BRN over the last 3–4 years speaks for themselves!

Edge AI neuromorphic computing got more interest last year and will gain more momentum this year and that trend will continue I am sure.

Maybe try reading this excellent article below more carefully, that person knows what he is talking about, way more than us laymen retail investors.

Posted yesterday by Fullmoonfever.

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

I certainly hope not, that would be a disaster and put us back years.

How????? This board decided to chase an IP only strategy and has made NO DEALS!!! And the strategy has set us back YEARS AND YEARS...... FFS!!!!!!

Many from the crapper place thinks that more deals would have been made if we had another CEO, LOL!

I never understood why they/you think that would make any difference?

Not a high bar to jump over is it, no deals, no revenue!!!

The market will strike when they are ready and not before, no matter who's in charge. The number of sales guys who passed though BRN over the last 3–4 years speaks for themselves!

WTF?????


@Guzzi62 .. You think I am not a genuine investor??????

I hold more shares than most here and am sick to the back teeth of Turds like you!!!! suggesting otherwise......



2 Options.........

1) We have no revenue because our management are Shit Hot

or

2) We have no revenue because our management are SHIT!!!!

Vote now kids!!!!!!!!!!!!!!!!!!

 

[Deleted member 3781]

I certainly hope not, that would be a disaster and put us back years.

How????? This board decided to chase an IP only strategy and has made NO DEALS!!! And the strategy has set us back YEARS AND YEARS...... FFS!!!!!!

Many from the crapper place thinks that more deals would have been made if we had another CEO, LOL!

I never understood why they/you think that would make any difference?

Not a high bar to jump over is it, no deals, no revenue!!!

The market will strike when they are ready and not before, no matter who's in charge. The number of sales guys who passed though BRN over the last 3–4 years speaks for themselves!

WTF?????


@Guzzi62 .. You think I am not a genuine investor??????

I hold more shares than most here and am sick to the back teeth of Turds like you!!!! suggesting otherwise......



2 Options.........

1) We have no revenue because our management are Shit Hot

or

2) We have no revenue because our management are SHIT!!!!

Vote now kids!!!!!!!!!!!!!!!!!!

 

[Guzzi62]

I certainly hope not, that would be a disaster and put us back years.

How????? This board decided to chase an IP only strategy and has made NO DEALS!!! And the strategy has set us back YEARS AND YEARS...... FFS!!!!!!

Many from the crapper place thinks that more deals would have been made if we had another CEO, LOL!

I never understood why they/you think that would make any difference?

Not a high bar to jump over is it, no deals, no revenue!!!

The market will strike when they are ready and not before, no matter who's in charge. The number of sales guys who passed though BRN over the last 3–4 years speaks for themselves!

WTF?????


@Guzzi62 .. You think I am not a genuine investor??????

I hold more shares than most here and am sick to the back teeth of Turds like you!!!! suggesting otherwise......



2 Options.........

1) We have no revenue because our management are Shit Hot

or

2) We have no revenue because our management are SHIT!!!!

Vote now kids!!!!!!!!!!!!!!!!!!

I said: the poster you answered to is a short seller, why don't you read carefully before commenting!

AKD 1000 have been available on the market as smart boxes/M2 card and so on as per the link below. AKD2 was first finished tapping out not so long ago, and they might do some fab of that one as well, but what size should they choose? 7 nm, 5 nm, 4 nm, or 3 nm? no wait, the good ol nm22 maybe? The lower the no, the higher the cost.
You can have 1/2 million nm22 chips made up for around 5-10 million $US according to Goggle.
IP is way better, AKD IP will be integrated into the chip design, not so much work for BRN to do, way fewer man-hours needed, but physical chips will be better for testing of the customers prototype(s) as Steven B. said in an interview.

Welcome to BrainChip

Power innovation with BrainChip's first-to-market neuromorphic AI. Advance solutions to the Edge. Explore now!

shop.brainchipinc.com

Calling me a turd, eh!

Calling our management, highly educated people with many many years in the industry, sxxx are pretty low.

I will therefore not be reading any further posts from you, bye-bye on ignore you go, clown!!!!

 

[Diogenese]

Hi Shaun,

Looks like Chatty has its rose coloured glasses on.

One of the IXI co-founders is Willi (Villi?) Mirttinen, and it looks like he was an inventor of this patent from 2018:

US11099381B2 Synchronizing light sources and optics in display apparatuses 20180810

Applicants: VARJO TECH OY [FI]

Inventors: PEUHKURINEN ARI ANTTI ERIK [FI]; MIETTINEN VILLE ILMARI [FI]

View attachment 94282

A display apparatus, communicably coupled with a server arrangement via a data communication network, comprising:
means for tracking a user's gaze;
means for tracking a pose of the display apparatus;
at least one light source;
at least one optical element; and
a processor configured to:
process gaze-tracking data, collected by the means for tracking the user's gaze, to determine a gaze position, a gaze direction, a gaze velocity and a gaze acceleration per eye of the user;
process pose-tracking data, collected by the means for tracking the pose of the display apparatus, to determine a position, an orientation, a velocity and an acceleration of the display apparatus;
send, to the server arrangement, gaze information indicative of the gaze position, the gaze direction, the gaze velocity and the gaze acceleration of the user, and apparatus information indicative of the position, the orientation, the velocity and the acceleration of the display apparatus, wherein the server arrangement is configured to predict a gaze position, a gaze direction, a gaze velocity and a gaze acceleration per eye of the user based on the gaze information, predict a position, an orientation, a velocity and an acceleration of the display apparatus based on the apparatus information, and process an input image to generate at least one image, based on the predicted gaze position, the predicted gaze direction, the predicted gaze velocity and the predicted gaze acceleration, and the predicted position, the predicted orientation, the predicted velocity and the predicted acceleration of the display apparatus;
receive, from the server arrangement, the at least one image, predicted gaze information indicative of the predicted gaze position, the predicted gaze direction, the predicted gaze velocity and the predicted gaze acceleration, and predicted apparatus information indicative of the predicted position, the predicted orientation, the predicted velocity and the predicted acceleration of the display apparatus;
determine an adjustment to be made in a configuration of the at least one light source and the at least one optical element prior to displaying the at least one image, based on the predicted gaze information and the predicted apparatus information;
determine whether or not a portion of at least one previous image is to be displayed during the adjustment;
when it is determined that the portion of the at least one previous image is to be displayed, display the portion of the at least one previous image via the at least one light source, whilst making the adjustment in the configuration of the at least one light source and the at least one optical element;
when it is determined that no portion of the at least one previous image is to be displayed, switch off or dim the at least one light source, whilst making the adjustment in the configuration of the at least one light source and the at least one optical element; and
display the at least one image via the at least one light source after the adjustment is made.


More recently from the same company (optical distance measurement):

US2025216553A1 HYBRID DIRECT AND INDIRECT TIME-OF-FLIGHT IMAGING 20231227


Disclosed is a depth imaging system with a light source; a depth sensor comprising direct Time-of-Flight (dToF) pixels and indirect Time-of-Flight (iToF) pixels; and processor(s) configured to: employ the light source to emit an intensity-modulated light pulse towards objects in a real-world environment; obtain dToF data indicative of time taken by the intensity-modulated light pulse to reach the dToF pixels after being reflected by the objects; obtain iToF data indicative of phase shifts undergone by the intensity-modulated light pulse upon reaching the iToF pixels after being reflected by the objects; determine optical depths for the dToF pixels; determine optical depths for the iToF pixels; and generate a depth image from the optical depths of the dToF pixels and the optical depths of the iToF pixels.

[0048] Optionally, the optical depths for the iToF pixels are determined by using at least one neural network. Optionally, in this regard, an input of the at least one neural network comprises the iToF data indicative of the phase shifts and the optical depths determined for the dToF pixels, while an output of the at least one neural network comprises the optical depths for the iToF pixels. It will be appreciated that the at least one neural network determines the optical depths for the iToF pixels in a highly accurate manner by resolving said ambiguities, as compared to conventional techniques. In this way, the at least one neural network may act as a mapping function, providing refined depth predictions for the iToF pixels. This may enhance overall depth sensing in the real-world environment, and mitigate typical uncertainties involved in optical depth determination for the iToF pixels. It will also be appreciated that the aforesaid input is provided to the at least one neural network both in a training phase of the at least one neural network and in an inference phase of the at least one neural network (i.e., when the at least one neural is utilised after it has been trained).

{062] ... Optionally, the at least one processor is configured to employ at least one neural network for generating the high-resolution depth image.

While they refer to NNs, they don't seem to be interested in the details, but they do seem to think it is software, so there is no indication of an Akida link, but absence of evidence ...

Well it seems they are not using the time-of-flight to determine the focal length:

https://tech.eu/2025/04/29/ixi-raises-365m/

"We've developed an eye-tracking technology that fits into the frames and operates at low power, allowing it to run continuously. It measures the vectors of both eyeballs. When you focus on something close, your eyes naturally converge slightly.

Based on this convergence, we can determine the distance you're looking at and adjust the optical power accordingly."

So it all depends on the bifocal eyeball tracking. That idea's got to be worth a fortune. It could be used with a foveated camera/lidar to pick up fine detail at a point of interest.

 

[FJ-215]

I said: the poster you answered to is a short seller, why don't you read carefully before commenting!

AKD 1000 have been available on the market as smart boxes/M2 card and so on as per the link below. AKD2 was first finished tapping out not so long ago, and they might do some fab of that one as well, but what size should they choose? 7 nm, 5 nm, 4 nm, or 3 nm? no wait, the good ol nm22 maybe?
Maybe even nm2, well no I guess: The initial cost to design a complex 2nm chip is massive, estimated to be over $725 million. This includes immense R&D, software, and intellectual property (IP) licensing fees. These development costs are amortized over the total volume of chips produced, meaning companies need to sell millions of units to make the endeavor economically viable.

Welcome to BrainChip

Power innovation with BrainChip's first-to-market neuromorphic AI. Advance solutions to the Edge. Explore now!

shop.brainchipinc.com

Calling me a turd, eh!

Calling our management, highly educated people with many many years in the industry, sxxx are pretty low.

I will therefore not be reading any further posts from you, bye-bye on ignore you go, clown!!!!

Oh dear......................

YOU CHILD........

This was almost 12 mths ago.......

Episode 24: Brainchip

Jon Tapson (JT): At BrainChip, we are currently finishing off our Akida 2.0 architecture. And this is an expansion on all of BrainChip’s prior work. It’s essentially a neuromorphic chip, it’s event-based, and it makes use of the intrinsic sparsity in signals to achieve high levels of efficiency


But, but, Joh. Didn't we try to sell the Akida 2.0 architecture as IP 3 years ago?????


WTF Guzzi62???? Are you a used car sales person??????

 

[FJ-215]

Ripping song, one of my favorites.

How does this relate to BRN, I wonder???????????

 

[itsol4605]

BrainChip & Partners at CES 2026 | Patricia Bower

Fantastic week at CES and thrilled to participate with the BrainChip team. Excellent discussions with folks covering a wide range of product and market segments on the value and opportunity for HaiLa’s extreme low power Wi-Fi and Bluetooth connectivity combined with efficient low-power on-device...

www.linkedin.com