BRN Discussion Ongoing

manny100

Top 20
Recent Anthony Lewis linked in comment:
M Anthony Lewis • FollowingCTO@BrainChip | AI, Robotics, Disruptive Computing3wWow. I have a simple goal: Just say true things. If everyone did that, the world would be a much better place. If people don't like the truth, you have to accept that.
In context makes his more recent comment pretty special for holders:
" TENNS, stay tuned"
 
  • Like
  • Fire
  • Love
Reactions: 24 users

TECH

Regular
Hey Believers,
How positive is Dr. Tony ? you've just got to love has enthusiasm, as mentioned to me, Tony was a top replacement for Peter, as smart, well that's a personal choice if you know both guys.

Peter has well and truly earned his stripes, Tony, despite being very intelligent, has yet to win the Australian shareholders over yet, in my opinion of course.

But I personally like how active and honest he comes across on LinkedIn.

TENN's is clearly ahead of the mob, I agree with the few who have mentioned Defense, I have commented a few times how I feel we will excel in the space sector, it appears our targeted markets, being, Aerospace, DOD, Cybersecurity, Medical and further down the revenue pipeline, Automotive we will excel.

SWaP is clearly one of our strengths moving forward, if you quietly check out with whom we are engaged with, their USD market caps prove to all non-believers that Brainchiip's technology at the far edge is currently out of the reach of our potential competitors, this isn't a child's little game, this is the real big league, and we are neck deep in these engagements.

Am I still backing a winner, despite the frustrating decade, yes I am and so are you lot..please don't get sucked into the day to day drama, we still have what they want, so hold tight..... Integrity resides at Brainchip !!

Just passing by...❤️ Tech.
 
  • Like
  • Love
  • Fire
Reactions: 50 users
Hey Believers,
How positive is Dr. Tony ? you've just got to love has enthusiasm, as mentioned to me, Tony was a top replacement for Peter, as smart, well that's a personal choice if you know both guys.

Peter has well and truly earned his stripes, Tony, despite being very intelligent, has yet to win the Australian shareholders over yet, in my opinion of course.

But I personally like how active and honest he comes across on LinkedIn.

TENN's is clearly ahead of the mob, I agree with the few who have mentioned Defense, I have commented a few times how I feel we will excel in the space sector, it appears our targeted markets, being, Aerospace, DOD, Cybersecurity, Medical and further down the revenue pipeline, Automotive we will excel.

SWaP is clearly one of our strengths moving forward, if you quietly check out with whom we are engaged with, their USD market caps prove to all non-believers that Brainchiip's technology at the far edge is currently out of the reach of our potential competitors, this isn't a child's little game, this is the real big league, and we are neck deep in these engagements.

Am I still backing a winner, despite the frustrating decade, yes I am and so are you lot..please don't get sucked into the day to day drama, we still have what they want, so hold tight..... Integrity resides at Brainchip !!

Just passing by...❤️ Tech.
He has most definitely won my vote here in Australia, absolutely.
How's the poetry, how goods that. i mean really good attitude that's is my thinking.Tony will be enlightening us again soon I believe 😉
 
  • Like
Reactions: 5 users

manny100

Top 20
Hey Believers,
How positive is Dr. Tony ? you've just got to love has enthusiasm, as mentioned to me, Tony was a top replacement for Peter, as smart, well that's a personal choice if you know both guys.

Peter has well and truly earned his stripes, Tony, despite being very intelligent, has yet to win the Australian shareholders over yet, in my opinion of course.

But I personally like how active and honest he comes across on LinkedIn.

TENN's is clearly ahead of the mob, I agree with the few who have mentioned Defense, I have commented a few times how I feel we will excel in the space sector, it appears our targeted markets, being, Aerospace, DOD, Cybersecurity, Medical and further down the revenue pipeline, Automotive we will excel.

SWaP is clearly one of our strengths moving forward, if you quietly check out with whom we are engaged with, their USD market caps prove to all non-believers that Brainchiip's technology at the far edge is currently out of the reach of our potential competitors, this isn't a child's little game, this is the real big league, and we are neck deep in these engagements.

Am I still backing a winner, despite the frustrating decade, yes I am and so are you lot..please don't get sucked into the day to day drama, we still have what they want, so hold tight..... Integrity resides at Brainchip !!

Just passing by...❤️ Tech.
We will win one way or the other.:)
Worst case scenario is the value of our patent portfolio.
The roadmap plans ahead include GenAI and AKIDA GEN 3. Also LLMs, NLP, SSM's etc.
Only gets better.
The above in context of expected growth in Neuromorphic Edge AI and BRN's current leadership position.
 
  • Like
  • Fire
Reactions: 16 users

CHIPS

Regular
I read somewhere they were axing any division which didn't guarantee at least 30% return on investment, or something along those lines. Perhaps Loihi 2 is in that category?

I hope so. I guess that Loihi2 is not urgent enough for them to invest staff and money in further development at this stage.
Intel is now reducing costs in all areas.
 
  • Like
  • Thinking
Reactions: 4 users

jrp173

Regular
He has most definitely won my vote here in Australia, absolutely.
How's the poetry, how goods that. i mean really good attitude that's is my thinking.Tony will be enlightening us again soon I believe 😉


It isn't poetry, it the lyrics to a song called "Something's Coming" from Westside story..
 
  • Like
Reactions: 6 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
😆 Have you notice the majority of famous people have small noses, bar Al Pacino and likes course 😉
Could be a sign youll become rich and famous one day yourself Bravo 🙏 .

I like the way you think Smoothie! Hehehe! 🤣

If I ever become rich and famous, I’ll need some friends to come sailing with me around the Bahamas and you’ll be the first on my list of invitees.

We can look out from the yacht’s jacuzzi and wave at Mr and Mrs Bezos as they float past us in their inferior vessel. And then we can pretend we can’t hear what they‘re saying while they desperately try to discover where we bought our humungous yet totally groovy glasses from.
 
  • Like
  • Haha
  • Love
Reactions: 10 users

Frangipani

Top 20
Speaking of interns:

Ghazaleh Ostovar recently started her summer internship with our Laguna Hills office (working remotely). Unlike other summer interns, who are usually still enrolled at uni, she has a PhD and years of work experience “in mathematical modeling, numerical simulation, and machine learning for biological systems”.

Given her background in health/medical physics and her stated interest in “applying data science and ML to problems in biotech and healthcare”, she presumably applied for Project 6, which was slated to have a team size of 4-5?


46205430-BC88-451C-8645-1D5890ECB316.jpeg



6463BC16-516E-418A-9077-12125484468E.jpeg



The BrainChip 2025 Summer Internship Program is out.

As every year, the University of Washington’s Department of Electrical and Computer Engineering is encouraging their students to apply - and in previous years, a number of UW students did in fact succeed in landing an internship with our company.

Sadly, though, as usual, this document would have benefitted from proper proofreading pre-publication, sigh…
XX projects we are looking for Interns”?!
And Project 4 is missing altogether?!

Depending on their respective project, the incoming summer interns will be assigned to various BrainChip engineers such as Ritik Shrivastava (a UW alumnus himself), Dhvani Kothari, Kurt Manninen…


The project I found especially intriguing is

Project 8: Neuromorphic Compute in the Cloud
Leverage cloud FPGAs for large scale event based computation

Objectives:
To design and implement a large scale neuromorphic event-based network on a cloud FPGA infrastructure


Description: BrainChip currently has multiple neuromorphic architectures which run on local FPGAs. This limits the size and location of networks for testing and demonstration. In this project, we would take one architecture and scale it up to very large size, and run it on cloud FPGAs from Amazon or Intel.
(…)




View attachment 83391

View attachment 83392 View attachment 83393 View attachment 83394 View attachment 83395


View attachment 83396
38cbaad5-4dde-490d-9775-0e924fc2151d-jpeg.83397
View attachment 83398

03CC521E-063E-44D1-A3D5-0AF851E0790C.jpeg
 
  • Like
  • Fire
  • Love
Reactions: 23 users

JoMo68

Regular
Big noaeI like the way you think Smoothie! Hehehe! 🤣

If I ever become rich and famous, I’ll need some friends to come sailing with me around the Bahamas and you’ll be the first on my list of invitees.

We can look out from the yacht’s jacuzzi and wave at Mr and Mrs Bezos as they float past us in their inferior vessel. And then we can pretend we can’t hear what they‘re saying while they desperately try to discover where we bought our humungous yet totally groovy glasses from.
Are only friends with small noses invited? Just asking for a friend…
GIF by Matea Radic
 
  • Haha
  • Like
Reactions: 8 users
Something is definitely “ar-eye“ because they‘re pretty big and bulky.

I have a really tiny nose, it’s practically invisible. I reckon these glasses would probably just slip right off my face.

Presumably this is just the prototype and following versions would be slimmed down for the more fashion conscious or nasally-challenged people amongst us.
1751011129931.gif
 
  • Haha
  • Like
Reactions: 7 users
  • Haha
  • Like
Reactions: 13 users
I like the way you think Smoothie! Hehehe! 🤣

If I ever become rich and famous, I’ll need some friends to come sailing with me around the Bahamas and you’ll be the first on my list of invitees.

We can look out from the yacht’s jacuzzi and wave at Mr and Mrs Bezos as they float past us in their inferior vessel. And then we can pretend we can’t hear what they‘re saying while they desperately try to discover where we bought our humungous yet totally groovy glasses from.
Now that's poetry
 
  • Haha
Reactions: 2 users
The answer is I personally believe Brainchip has already gained real traction in at least the following markets.

1. Aerospace and Defence

2. Drones (civilian)

3. Medical

4. Industrial

5. Cyber security

6. Transportation

7. RISC-V Ai extension

and yet we still hang around at what I consider to be well below true value based on the lowest of two analyst reports commencing at $AU1.20 and terminating at $AU1.97.

My opinion only DYOR

Fact Finder
 
  • Like
  • Fire
Reactions: 26 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
Are only friends with small noses invited? Just asking for a friend…
GIF by Matea Radic

Not at all Jo! Whatever size your schnoz is, is fine by me.

So count yourself invited!!!🥳 🍾🏖️🪇

And if you do happen to have an abnormally large honker, then you can safeguard my glasses by wearing them on-top of your own pair when I go for a swim.
 
  • Haha
  • Love
  • Like
Reactions: 8 users

Frangipani

Top 20
SWaP is clearly one of our strengths moving forward, if you quietly check out with whom we are engaged with, their USD market caps prove to all non-believers that Brainchiip's technology at the far edge is currently out of the reach of our potential competitors, this isn't a child's little game, this is the real big league, and we are neck deep in these engagements.

Hi TECH,

are you privy to know more about the depth of engagement that our competitors have with their partners?

Have a look at the ecosystems of two of those companies that, just like us, already have products on the market. Pretty unknown names, huh? Oh, wait…



EA82F8A3-7D58-47DC-A762-6B2006E0AC73.jpeg


906C9839-F5E9-4220-B8E1-359808C05254.jpeg




F1349A16-3288-4373-B1E0-56523C6B40D8.jpeg

9C94E1F1-250F-4DB8-91FF-855A53B648C3.jpeg
0C21FCC8-B3B4-40F1-A4DB-5ACCC495EF6D.jpeg
 

Attachments

  • C2990EAC-1AF2-4DC3-9177-5FECF502DFD9.jpeg
    C2990EAC-1AF2-4DC3-9177-5FECF502DFD9.jpeg
    63.9 KB · Views: 34
  • Like
  • Fire
  • Love
Reactions: 12 users
Not at all Jo! Whatever size your schnoz is, is fine by me.

So count yourself invited!!!🥳 🍾🏖️🪇

And if you do happen to have an abnormally large honker, then you can safeguard my glasses by wearing them on-top of your own pair when I go for a swim.
1751014221115.gif
 
  • Like
  • Haha
Reactions: 2 users
Hi TECH,

are you privy to know more about the depth of engagement that our competitors have with their partners?

Have a look at the ecosystems of two of those companies that, just like us, already have products on the market. Pretty unknown names, huh? Oh, wait…



View attachment 87728

View attachment 87733



View attachment 87729
View attachment 87730 View attachment 87732
Impressive
 
  • Like
Reactions: 1 users

Frangipani

Top 20
So I guess Loihi 2 will have to wait now … and BrainChip will profit from that situation. More good engineers are now also looking for a new job.
I read somewhere they were axing any division which didn't guarantee at least 30% return on investment, or something along those lines. Perhaps Loihi 2 is in that category?
I hope so. I guess that Loihi2 is not urgent enough for them to invest staff and money in further development at this stage.
Intel is now reducing costs in all areas.

I doubt the neuromorphic team at Intel Labs will be affected much, if at all…
The appointment of Sachin Katti as Intel’s CTO, AI Officer and Head of Intel Labs suggests otherwise.



“Lip-Bu Tan, the newly appointed chief executive of Intel has launched a major leadership overhaul aimed at streamlining decision-making at the company, according to Reuters. With the new changes, Sachin Katti will become the chief technology office officer of Intel and will lead the company's AI effort. Also, the new management structure will get flatter and technical leaders from key groups will get direct lines with the CEO.

"Sachin Katti is expanding his role to include chief technology and AI officer for Intel," a spokesperson for Intel confirmed to Tom's Hardware. "As part of this, he will lead our overall AI strategy and AI product roadmap, as well as Intel Labs and our relationship with the startup and developer ecosystems."

New CTO

Up until now, Sachin Katti was in charge for Intel's networking and edge computing business unit and prior to that he was CTO of that unit. However, with the new expansion of his role, he will become chief technology officer of the whole company and the head of Intel Labs, therefore responsible for all the fundamental and applied research at Intel, which includes fundamental research for Intel's process technologies.

The appointment of a dedicated AI chief is perhaps a long overdue job as Intel's AI strategy so far has not exactly been a success.
Perhaps the problem is that AI was a part of Intel's data center unit and was considered as somewhat of a second-class citizen and therefore competed both for resources and management attention. With a dedicated lead, this could change, but keep in mind that Sachin Katti will not be solely dedicated to AI as he will be Intel's CTO as well as in charge of the edge and networking business.

(…) That said, Katti will not be the first Intel CTO with additional responsibilities. However, Katti's CTO and AI responsibilities are both strategically important for the company's future and the fusion of the roles may be a strategic move by Lip-Bu Tan (…)”



Here are two press releases from MWC Barcelona 2024, when Sachin Katti was in charge of Intel’s Network and Edge Group. At that event, Ericsson demoed a radio receiver algorithm prototype targeting Loihi 2.



427548C5-546F-4884-9240-56F707F05281.jpeg




1AC8D6A1-B5B9-43FC-9246-1C123E52E79A.jpeg



And check out this video:







Also, Intel recently hired Jean-Didier Allegrucci:

“Allegrucci has been named VP of AI System on Chip (SoC) Engineering. He will be responsible for managing the development of multiple SoCs that will be part of Intel’s AI roadmap. He joins from Rain AI, an innovative startup where he led AI silicon engineering. Prior to joining Rain, he spent 17 years at Apple where he oversaw the development of more than 30 SoCs used across many of the company’s flagship products.”

 
  • Like
  • Fire
  • Love
Reactions: 12 users

FromBeyond

Member
  • Like
  • Love
  • Haha
Reactions: 6 users

Frangipani

Top 20
And then there are also those who have recently joined BrainChip, such as Winston Tang and Aras Pirbadian, bringing along their individual talents, skills and interests:


View attachment 83933

View attachment 83936



View attachment 83937 View attachment 83938



15803C25-D75A-42F6-B879-C82995960DF8.jpeg




How to Solve the Size, Weight, Power and Cooling Challenge in Radar & Radio Frequency Modulation Classification​

By Aras Pirbadian and Amir Naderi
June 27, 2025
cropa-280x112.webp

Modern radar and Radio Frequency (RF) signal processing systems—especially those deployed on platforms like drones, CubeSats, and portable systems—are increasingly limited by strict Size, Weight, Power and Cooling (SWaP-Cool) constraints. These environments demand real-time performance and efficient computation, yet many conventional algorithms are too resource-intensive to operate within such tight margins. As the need for intelligent signal interpretation at the edge grows, it becomes essential to identify processing methods that balance accuracy within these constraints.

One such essential task in radar and RF applications is Automatic Modulation Classification (AMC). AMC enables systems to autonomously recognize the modulation type of incoming signals without prior coordination, a function crucial for dynamic spectrum access, electronic warfare, and cognitive radar systems. However, many existing AI-based AMC models, such as deep CNNs or hybrid ensembles, are computationally heavy and ill-suited for low- SWaP-Cool deployment, creating a pressing gap between performance needs and implementation feasibility.

In this post, we’ll show how BrainChip’s Temporal Event-Based Neural Network (TENN), a state space model, overcomes this challenge. You’ll learn why conventional models fall short in AMC tasks—and how TENN enables efficient, accurate, low-latency classification, even in noisy RF environments.

Why Traditional AMC Models Fall Short at the Edge​

AMC is essential for identifying unknown or hostile signals, enabling cognitive electronic warfare, and managing spectrum access. But systems like UAVs, edge sensors, and small satellites can’t afford large models that eat power and memory.
Unfortunately, traditional deep learning architectures used for AMC come with real drawbacks:
  • Hundreds of millions of Multiply Accumulate (MAC) operations resulting in high power consumption and large parameter counts demanding large memory
  • Heavy preprocessing requirements (e.g., Fast Fourier Transform (FFTs), spectrograms)
  • Still fail to maintain accuracy under 0 dB Signal-to-Noise Ratio (SNR), where signal and noise have similar power.
In mobile, airborne, and space-constrained deployments, these inefficiencies are showstoppers.

BrainChip’s TENN Model: A Low-SWaP-Cool Breakthrough for Real-Time RF Signal Processing​

BrainChip’s TENN model provides a game-changing alternative. It replaces traditional CNNs with structured state-space layers and is specifically optimized for low SWaP-Cool high-performance RF signal processing. State‑Space Models (SSMs) propagate a compact hidden state forward in time, so they need only constant‑size memory at every step. Modern SSM layers often recast this recurrent update as a convolution of the input with a small set of basis kernels produced by recurrence. Inference‑time efficiency therefore matches that of classic RNNs, but SSMs enjoy a major edge during training: like Transformers, they expose parallelizable convolutional structure, eliminating the strict step‑by‑step back‑propagation bottleneck that slows RNN training. The result is a sequence model that is memory‑frugal in deployment yet markedly faster to train than traditional RNNs, while still capturing long‑range dependencies without the quadratic cost of attention of Transformers.

TENN introduces the following innovations:​

  • A compact state-space modeling that simplifies modulation classification by reducing memory usage and computation—offering a leaner alternative to transformer-based models.
  • Tensor contraction optimization, applying efficient strategies to minimize memory footprint, computation and maximize throughput.
  • Hybrid SSM architecture that replaces CNN layers and avoids attention mechanisms, maintaining feature richness with lower computational cost.
  • Real-time, low-latency inference by eliminating the need for FFTs or buffering at inference time

Matching Accuracy with a Fraction of the Compute​

The Convolutional Long Short-Term Deep Neural Network (CLDNN), introduced by O’Shea et al. (2018), was selected as the benchmark model for comparison with BrainChip’s TENN. Although the original RadioML paper did not use the CLDNN acronym, it proposed a hybrid architecture combining convolutional layers with LSTM and fully connected layers—an architecture that has since become widely referred to as CLDNN in the AMC literature.
This model was chosen as a reference because it comes from the foundational paper that introduced the RadioML dataset—making it a widely accepted standard for evaluation. As a hybrid of convolutional and LSTM layers, CLDNN offers a meaningful performance baseline by capturing both spectral and temporal features of the input signals in the In-phase (I) and Quadrature (Q) (I/Q) components, which are used to represent complex signals in communication systems.

While more recent models like the Mixture-of-Experts AMC (MoE-AMC) have achieved state-of-the-art accuracy on the RadioML 2018.01A dataset, they rely on complex ensemble strategies involving multiple specialized networks, making them unsuitable for low-SWaP-Cool deployments due to their high computational and memory demands. In contrast, TENN matches or exceeds the accuracy of CLDNN, while operating at a fraction of the resource cost—delivering real-time, low-latency AMC performance with under 4 million MACs and no reliance on using multi-model ensembles or hand-crafted features like spectral pre-processing.

With just ~3.7 million MACs and 276K parameters, TENN is over 100x more efficient than CLDNN, while matching or exceeding its accuracy—even in low-SNR regimes. Moreover, the latency in the table refers to the simulated latency on a A30 GPU for both models.
20250627_1.webp


On the RadioML 2018.01A dataset (24 modulations, –20 to +30 dB), TENN consistently outperforms CLDNN especially in mid to higher SNR scenarios. Here is the performance of TENN compared to CLDNN's over the SNR range of -20 to +30 dB:
20250627_2.webp

Ready to bring low SWaP-Cool AI to your RF platforms?​

Today’s RF systems need fast, accurate signal classification that fits into small power and compute envelopes. CLDNN and similar models are simply too resource intensive. With TENN, BrainChip offers a smarter, more scalable approach—one that’s purpose-built for edge intelligence.

By leveraging efficient state-space modeling, TENN delivers:
  • Dramatically reduces latency, power consumption, and cooling requirements
  • Robust accuracy across noisy environments
  • Seamless deployment on real-time, mobile RF platforms
Whether you're deploying on a drone, CubeSat, or embedded system, TENN enables real-time AMC at the edge—without compromise.

Schedule a demo with our team to benchmark your modulation use cases on BrainChip’s event-driven AI platform and explore how TENN can be tailored to your RF edge deployment.
Book Demo

Tools and Resources Used​

  • Dataset: RadioML 2018.01A – A widely used AMC benchmark with 2 million samples:
  • DeepSig Inc., "Datasets," [Online]. Available: https://www.deepsig.io/datasets
  • BrainChip Paper: Pei , Let SSMs be ConvNets: State-Space Modeling with Optimal Tensor Contractions arXiv, 2024. Available: https://arxiv.org/pdf/2501.13230
  • Reference Paper: O’Shea, T. J., Roy, T., & Clancy, T. C. (2018). Over-the-air deep learning based radio signal classification. IEEE Journal of Selected Topics in Signal Processing, 12(1), 168–179. Available: https://doi.org/10.1109/JSTSP.2018.2797022
  • Framework: PyTorch was used to implement and train the TENN-based SSM classifier
  • Thop is a library designed to profile PyTorch models; it calculates the number of MACs and parameters.
 
  • Like
  • Fire
  • Love
Reactions: 22 users
Top Bottom