BRN Discussion Ongoing

MDhere

Top 20
I just had a vision that within 6 days there will be good news. by 21st sept.
I may need to check into specsavers on the 6th day if this vision does not improve!
 
Last edited:
  • Haha
  • Like
  • Wow
Reactions: 17 users

Getupthere

Regular
Last edited:
  • Like
  • Fire
  • Love
Reactions: 14 users

itsol4605

Regular
 
  • Like
  • Fire
Reactions: 4 users
So who paid to produce that Trim capital research report?
 
  • Like
  • Thinking
Reactions: 4 users
I just had a vision that within 6 days there will be good news. by 21st sept.
I may need to check into specsavers on the 6th day if this vision does not improve!
1757966236196.gif



1757966299938.gif
 
  • Haha
  • Like
Reactions: 8 users
So who paid to produce that Trim capital research report?
Sean did out of his own pocket so to keep the price low so he can get more shares at a low price for his bonus lol
No idea
Not advice or correct information
 
  • Haha
  • Like
  • Love
Reactions: 8 users

7für7

Top 20
  • Like
  • Haha
Reactions: 2 users
  • Haha
Reactions: 3 users

itsol4605

Regular
 
  • Like
  • Love
Reactions: 12 users

itsol4605

Regular
 
  • Like
  • Fire
  • Love
Reactions: 14 users

Pmel

Regular
Response from IR BrainChip about Trim report.
 

Attachments

  • Screenshot_20250916_125803_Outlook.jpg
    Screenshot_20250916_125803_Outlook.jpg
    417.2 KB · Views: 364
  • Like
  • Fire
  • Love
Reactions: 30 users
1758000367943.gif
 
  • Haha
  • Like
Reactions: 11 users

Diogenese

Top 20
The penny' dropped ...

Tony reportedly said that originally TENNs couldn't do recurrence.

So that meant that TENNs needed to be tied to the original Akida 1 NPU. - "Better with Akida".

But Tony also intimated that TENNs was sufficiently evolved to do recurrence by the time GenAI/Akida 3 were developed. He has also indicated that there is some (minimal) CPU involvement in the operation of TENNs, as distinct from AKida NPUs which do not require processor involvement in detection/inference/classification.

It was only after the announcement of GenAI/Akida 3 that we saw Akida 1 being spoken of only in terms of MACs, with no mention of the old NPUs.

So, when TENNs learned recurrence, was this the tipping point which meant that Akida 1 had been superseded?

I wonder what hardware improvements were involved in implementing recurrence with TENNs. I imagine that memory would be involved. In the Roadmap, JT mentioned that patents for improvements in memory operation were in the pipeline.

This is the patent application implementing recurrence:

US2025209313A1 METHOD AND SYSTEM FOR IMPLEMENTING ENCODER PROJECTION IN NEURAL NETWORKS 20231222 pub 250625

1758007193402.png


[0027] FIG. 10 is a flow chart of a method performed by the neural processor for performing, in the recurrent mode, encoder projection, mid-layer processing, and decoding which generates content using one or more neural network layers of the neural network in accordance with some embodiments.

The patent was filed in December 2023.

The patent application would have preceded the final circuit design. It may have been breadboarded in FPGA before th4e ASIC design was done for the commercial IP release.
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 28 users
Guess what 😂



 
  • Like
  • Fire
  • Thinking
Reactions: 5 users

TopCat

Regular
Apple's new AirPods with efficient on device AI with an instant translation feature. Sure do wish Brainchip has some sort of input in this. Otherwise, pretty cool anyway!



“I already use my Apple Watch constantly to track heart rate, so the idea that my AirPods can now do that too—plus handle real-time translation and adaptive audio—feels like the future landing right in my pocket. The magic behind it...Apple’s chip, built on Arm. It’s designed to run AI super efficiently on-device, so you get features that feel seamless, instant, and personal”
Edge devices such as earbuds hey! 😉

Can someone who knows explain to us , is there a difference between denoising and ANC.?

“At BrainChip, this mission connects directly to our work on aTENNuate, our new audio denoising solution. Built on Temporal Neural Networks (TENNs), aTENNuate delivers clear speech on edge devices such as earbuds and IoT products. It is lightweight, efficient, and designed for real-world environments where noise is unpredictable.”

 
  • Like
  • Thinking
  • Fire
Reactions: 8 users

7für7

Top 20
Step right up, step right up, ladies and gentlemen! No cotton candy here, no lottery tickets… this is the bet of the decade:

Will Sony tie Akida into their game …. yes or no?

2026, the magic year, the dice are already rolling… Who’s got the guts, who’s just blowing smoke?

You there …yes, you with the checkered shirt and the beer bottle! Exactly you!


You say: ‘No way, Sony won’t touch Akida.’ .. Good! The first skeptic has entered the ring.

Dolci shouts: ‘No!’ so we’ve got our first opposition.

But remember, friends: Mercedes isn’t laughing at BrainChip anymore … they’re already coding it in. Prophesee’s hand is already in Sony’s pocket .. and Prophesee dances with Akida! 50/50 guys…

Still don’t believe it? Excellent. A bet only has flavor when the crowd doubts.

So, gather round the table:

…..Chips on the left: ‘Sony & Akida, hand in hand.’

…..Chips on the right: ‘Never ever.’

…..And in the middle… the Akida crystal ball, 2026! 🔮✨

You heard it first on 7News



 
Last edited:
  • Like
  • Fire
Reactions: 9 users

Schwale

Regular
  • Thinking
  • Like
Reactions: 3 users
Top Bottom