BRN Discussion Ongoing

[Pom down under]

The sell side just keeps on increasing and increasing.

 

[Labsy]

If was a whale wanting to establish a strong position... I would buy in bursts and gobble as it settles ...
Watch the trend....

 

[buena suerte :-)]

The sell side just keeps on increasing and increasing.

View attachment 75175

Yep not great!

 

[Pom down under]

Yep not great!

View attachment 75176

 

[DingoBorat]

Was that a whale I saw!

 

[TheDrooben]

Nice churn between 42c-43c this morning..........Dave is doing his best but the buyers are still there. Interesting afternoon session coming up

 

[DingoBorat]

Nice churn between 42c-43c this morning..........Dave is doing his best but the buyers are still there. Interesting afternoon session coming up

Huge 4.2 million share wall, at 44 cents..

 

[Pom down under]

Huge 4.2 million share wall, at 44 cents..

Huge 14 million in total up to .47

 

[Esq.111]

Huge 4.2 million share wall, at 44 cents..

One of these and she's wiped , if they took two ...... which i think they may ....$0.46 wiped as well.

Time to haul Dave in ,

 

[Diogenese]

Thoughts if you get the chance @Diogenese

TIA.

All sounds somewhat familiar from Carnegie.

CMU Researchers Introduce TNNGen: An AI Framework that Automates Design of Temporal Neural Networks (TNNs) from PyTorch Software Models to Post-Layout Netlists

Designing neuromorphic sensory processing units (NSPUs) based on Temporal Neural Networks (TNNs) is a highly challenging task due to the reliance on manual, labor-intensive hardware development processes. TNNs have been identified as highly promising for real-time edge AI applications, mainly...

www.google.com.au

CMU Researchers Introduce TNNGen: An AI Framework that Automates Design of Temporal Neural Networks (TNNs) from PyTorch Software Models to Post-Layout Netlists​

By
Aswin Ak
-
December 29, 2024


Designing neuromorphic sensory processing units (NSPUs) based on Temporal Neural Networks (TNNs) is a highly challenging task due to the reliance on manual, labor-intensive hardware development processes. TNNs have been identified as highly promising for real-time edge AI applications, mainly because they are energy-efficient and bio-inspired. However, available methodologies lack automation and are not very accessible. Consequently, the design process becomes complex, time-consuming, and requires specialized knowledge. It is through overcoming these challenges that one can unlock the full potential of TNNs for efficient and scalable processing of sensory signals.

The current approaches to TNN development are fragmented workflows, as software simulations and hardware designs are handled separately. Advancements such as ASAP7 and TNN7 libraries made some aspects of hardware efficient but remain proprietary tools that require significant expertise. The fragmentation of the process restricts usability, prevents the easier exploration of design configurations with increased computational overhead, and can’t be used for more application-specific rapid prototyping or large-scale deployment purposes.

Researchers at Carnegie Mellon University introduce TNNGen, a unified and automated framework for designing TNN-based NSPUs. The innovation lies in the integration of software-based functional simulation with hardware generation in a single streamlined workflow. It combines a PyTorch-based simulator, modeling spike-timing dynamics and evaluating application-specific metrics, with a hardware generator that automates RTL generation and layout design using PyVerilog. Through the utilization of TNN7 custom macros and the integration of a variety of libraries, this framework realizes considerable enhancements in simulation velocity as well as physical design. Additionally, its predictive abilities facilitate precise forecasting of silicon metrics, thereby diminishing the dependency on computationally demanding EDA tools.

TNNGen is organized around two principal elements. The functional simulator, constructed using PyTorch, accommodates adaptable TNN configurations, allowing for swift examination of various model architectures. It has GPU acceleration and accurate spike-timing modeling, thus ensuring high simulation speed and accuracy. The hardware generator converts PyTorch models into optimized RTL and physical layouts. Using libraries such as TNN7 and customized TCL scripts, it automates synthesis and place-and-route processes while being compatible with multiple technology nodes like FreePDK45 and ASAP7.

TNNGen achieves excellent performance in both clustering accuracy and hardware efficiency. The TNN designs for time-series clustering tasks show competitive performance with the best deep-learning techniques while drastically reducing the utilization of computational resources. The approach brings major energy efficiency improvements, obtaining a reduction in die area and leakage power compared to conventional approaches. In addition, the runtime of the design is dramatically reduced, especially for larger designs, which benefit most from the optimized workflows. Moreover, the comprehensive forecasting instrument provides accurate estimations of hardware parameters, allowing researchers to evaluate design viability without the necessity of engaging in physical hardware procedures. Taken together, these findings position TNNGen as a viable approach for streamlining and expediting the creation of energy-efficient neuromorphic systems.

TNNGen is the next step in the fully automated development of TNN-based NSPUs by unifying simulation and hardware generation into an accessible, efficient framework. The approach addressed key challenges in the manual design process and made this tool much more scalable and usable for edge AI applications. Future work would involve extending its capabilities toward support for more complex TNN architectures and a much wider range of applications to become a critical enabler of sustainable neuromorphic computing.

---

Check out the Paper. All credit for this research goes to the researchers of this project

The innovation lies in the integration of software-based functional simulation with hardware generation in a single streamlined workflow. It combines a PyTorch-based simulator, modeling spike-timing dynamics and evaluating application-specific metrics, with a hardware generator that automates RTL generation and layout design using PyVerilog. Through the utilization of TNN7 custom macros and the integration of a variety of libraries, this framework realizes considerable enhancements in simulation velocity as well as physical design. Additionally, its predictive abilities facilitate precise forecasting of silicon metrics, thereby diminishing the dependency on computationally demanding EDA tools.

Sounds like they've cloned Anil.

 

[DingoBorat]

Huge 14 million in total up to .47

I don't know..

Maybe a dolphin herding technique? Esq?..

Still need a toothed whale to do the damage, in my "professional" opinion..

 

[Pom down under]

I don't know..

Maybe a dolphin herding technique? Esq?..


View attachment 75181


Still need a toothed whale to do the damage, in my "professional" opinion..

Maybe it’s the whale taking some profit?

 

[DingoBorat]

Maybe it’s the whale taking some profit?

You mean taking a dump?..

They still looked mighty hungry yesterday..

Possibly was a Market Mover?..

 

[7für7]

Maybe it’s the whale taking some profit?

Or maybe just “one punch man” waiting to blow up the wall? He seams to be relaxed… hmm he looks trustworthy…. F…it… I trust this guy… looks very confident!

 

[Falling Knife]

This article is yet to be released. I can offer the references if required.

Im playing with Perplexity and asked for an article
"highlighting the disruptive nature of Akida from Brainchip (ASX code BRN).
Outline the progress towards commercial success for the company and what sort of deals could come from current company progress"

So writing an article could be very simple and hence reading many of them becomes a little repetitive because all are based on the current knowledge and information offered online.
We LTI know all this but reading again often has consequences bc one feels compelled to top up


The Disruptive Nature of Akida
Akida's disruptive potential lies in its unique approach to AI processing: Event-Based Architecture: Unlike conventional AI models that require constant processing, Akida operates on an event-based system. This means it only activates in response to specific stimuli, significantly reducing power consumption
https://www.embedded.com/brainchips...-ai-processing-with-event-based-architecture/
. Ultra-Low Power Consumption: Akida can operate on less than a single milliwatt, making it ideal for battery-powered devices and applications where energy efficiency is crucial
https://www.embedded.com/brainchips...-ai-processing-with-event-based-architecture/
. On-Chip Learning: Akida enables on-chip training, learning, and inference, eliminating the need for constant cloud connectivity. This enhances data privacy and security while reducing latency
https://brainchip.com/technology/
. Versatility: The technology is applicable across various sectors, including retail, security, smart cities, automotive, and industrial processes
https://www.wevolver.com/article/akida-edge-ai-box-edge-computing-with-neuromorphic-technology

Progress Towards Commercial Success​

BrainChip has made significant strides towards commercializing its Akida technology: Partnerships and Collaborations: The company has secured several high-profile partnerships, including:

• A commercial license agreement with Frontgrade Gaisler, a Swedish leader in radiation-hardened microprocessors for space applications
• Collaborations with the European Space Agency and Airbus Defence and Space
  https://www.fool.com.au/2024/12/27/up-119-this-year-can-brainchip-shares-soar-again-in-2025/
• A $1.8 million contract with the Air Force Research Laboratory (AFRL) for neuromorphic radar signal processing
  https://www.fool.com.au/2024/12/27/up-119-this-year-can-brainchip-shares-soar-again-in-2025/

Market Expansion: BrainChip is expanding its presence in both the AI and aerospace sectors, demonstrating the versatility of its technology
https://www.fool.com.au/2024/12/27/up-119-this-year-can-brainchip-shares-soar-again-in-2025/
. Revenue Generation: The company has begun to secure contracts and partnerships that are expected to generate revenue streams, addressing previous concerns about consistent income from its Akida technology
https://www.fool.com.au/2024/12/27/up-119-this-year-can-brainchip-shares-soar-again-in-2025/

Potential Future Deals​

Given BrainChip's current trajectory, several types of deals could materialize: Space and Defense Contracts: The partnership with Frontgrade Gaisler and the AFRL contract suggest potential for more aerospace and defense-related deals
https://www.fool.com.au/2024/12/27/up-119-this-year-can-brainchip-shares-soar-again-in-2025/
https://brainchip.com/edgx-announce...sruptive-data-processing-solutions-for-space/
. IoT and Edge Computing Partnerships: Akida's suitability for edge AI applications could lead to partnerships with IoT device manufacturers and companies focusing on smart city technologies
https://www.wevolver.com/article/akida-edge-ai-box-edge-computing-with-neuromorphic-technology
. Healthcare Technology Integration: The ultra-low power characteristics of Akida make it ideal for medical devices requiring continuous monitoring, such as glucose sensors or wearable heart rate monitors
https://www.embedded.com/brainchips...-ai-processing-with-event-based-architecture/
. Automotive Industry Collaborations: As the automotive sector increasingly integrates AI for autonomous driving and advanced driver-assistance systems, BrainChip could secure deals with car manufacturers or automotive technology providers. Industrial IoT Applications: BrainChip's technology could be particularly valuable for anomaly detection in motors or other mechanical systems, potentially leading to partnerships with industrial equipment manufacturers
https://www.embedded.com/brainchips...-ai-processing-with-event-based-architecture/
. While BrainChip has made significant progress, the company's future success will depend on its ability to convert these partnerships and technological advantages into sustainable revenue streams. As the neuromorphic computing and Edge AI markets are expected to quadruple in size by 2030, BrainChip is well-positioned to capitalize on this growth
https://stocksdownunder.com/article/brainchip-asxbrn/
. The coming years will be crucial in determining whether Akida can truly disrupt the AI industry and establish BrainChip as a leader in edge computing solutions.

 

[Pom down under]

Sell side gradually getting thinner

 

[Pmel]

Sell side gradually getting thinner

If you look in commsec website there are big single order . Could be just to set panic.

 

[7für7]

Sell side gradually getting thinner

It’s the one punch man effect!

 

[DingoBorat]

If you look in commsec website there are big single order . Could be just to set panic.

"They" are trying to cause panic and yet that wall at 44, is starting to look nervous??..

 

[Rach2512]

Am I reading that right, someONE wants almost 1.2 million shares all to themselves?