BRN Discussion Ongoing

[rgupta]

About 8 months ago, Tony Lewis said we were the first (to his knowledge), to run tiny language models at the edge with very low power.

However, it would appear from the article below that Qualcomm have pipped us to the post by integrating Personal AI's SLM's at the edge with their Snapdragon NPU.

I don't know what sort of power consumption is involved. Although it does say all day battery life.






View attachment 71547

Personal AI to Bring Enterprise-Grade AI to the NPU on PCs powered by Snapdragon X Series Processors​

October 21, 2024 16:30 ET| Source: Personal AIFollow

---

Share

SAN DIEGO, Oct. 21, 2024 (GLOBE NEWSWIRE) --

Highlights:

• Personal AI announces the integration of Personal AI's Small Language Models (SLMs) into PCs powered by Snapdragon X Series processors.
• This collaboration aims to enhance on-device AI, prioritizing accuracy, privacy, and security for critical enterprise users.

Personal AI announced a collaboration to bring AI directly to edge devices through Snapdragon® X Series platforms. This collaboration marks a step towards ubiquitous AI, combining Personal AI's expertise in private SLMs with Qualcomm Technologies' chipsets.
Showcased during Snapdragon Summit, Personal AI's SLMs were demonstrated on HP EliteBook Ultra Next-Gen AI PCs powered by Snapdragon X Series processors. Running on the Snapdragon NPU delivers enhanced privacy, security, and real-time AI processing capabilities to a wide range of devices, with a focus on enterprise-grade laptops.
"Our collaboration with Personal AI is a leap forward in on-device AI capabilities,” stated Rami Husseini, Director, Product Management at Qualcomm Technologies, Inc. “By utilizing Personal AI's technology on devices that contain our Snapdragon X Series platforms, we're enabling a new era of security-rich, privacy-focused, and powerful AI experiences directly on Windows PCs. Showcasing our commitment to driving innovation in AI and empowering users with cutting-edge technology that is designed to respect their privacy."
Suman Kanuganti, CEO and Co-founder of Personal AI, added, "Working with Qualcomm and HP allows us to bring our vision of highly efficient and scalable AI Personas to millions of users worldwide. By leveraging the NPU capabilities of Snapdragon, we're able to run our models directly on-device, ensuring that sensitive data never leaves the user's hardware. This collaboration underscores our mission to provide AI that enhances productivity, communication, and collaboration, while maintaining the highest standards of data protection and privacy."
Loretta Li-Sevilla, Global Head of Future of Work at HP, commented, "At HP, we're committed to delivering technology that empowers businesses to work smarter and more securely. HP next-generation AI PCs featuring Snapdragon X Series processors enables new compute capabilities. Personal AI Personas can now run offline for highly private inference use, offering our customers unparalleled AI performance and the all-day battery life they need to stay productive in today's fast-paced business environment."
The integration of Personal AI's technology into PCs powered by Snapdragon X Series Processors is already generating excitement among early adopters, who report significant improvements in productivity, accuracy, and data security.
The Chief Strategy Officer of a Personal AI customer shared his experience: "As a global group of iconic brands, solutions like Personal AI have the potential to completely transform how we operate. In today's fast-paced environment, we deal with vast amounts of data from every corner of the globe—market trends, consumer behaviors, competitive movements, pricing fluctuations. Traditional methods of analyzing this information simply can’t keep up with the speed at which we need to act. We can easily load our available public and enterprise information into the Personal AI engine, where we can interact with it like talking to a smart analyst about our meeting conclusions, action items, and capital markets reactions to recent industry movements. I see this as the beginning of adopting AI in a much easier way in our industry.”
About Personal AI
Personal AI develops a horizontal AI training and collaboration platform, focused on private, Small Language Models (SLMs) that multiply the capabilities of enterprise teams. Their technology enables organizations to build networks of AI Personas, each representing key roles within companies. These AI Personas are exclusively trained on proprietary data, ensuring unparalleled accuracy, transparency, and privacy. For more information, please visit https://personal.ai
Contact: jonathan.bikoff@personal.ai

Personal AI to Bring Enterprise-Grade AI to the NPU on PCs powered by Snapdragon X Series Processors

Personal AI collaborates with Qualcomm and HP to integrate private Small Language Models (SLMs) into next-gen PCs powered by Snapdragon X Series...

www.globenewswire.com

www.linkedin.com/posts/syntiant-corp_small-language-models-breach-customer-service-activity-7254263503807553537-ZalE?utm_source=share&utm_medium=member_android
Another SLM by syntiant

 

[HopalongPetrovski]

 

[Falling Knife]

Morning Chippers ,

One for Diogenese to unravel , possibly enlighten us.

Thankyou in advance Diogenese.

Nanoveu , ASX : NVU

Regards,
Esq.

Might be useful

 

[Guzzi62]

www.linkedin.com/posts/syntiant-corp_small-language-models-breach-customer-service-activity-7254263503807553537-ZalE?utm_source=share&utm_medium=member_android
Another SLM by syntiant

We are not alone anymore, but not surprising considering many are aware that it's something that's needed/wanted.

Let's just hope our TENN Pico can compete, and we will get a fair share of the cake.

Loading…

www.fierceelectronics.com

 

[toasty]

We are not alone anymore, but not surprising considering many are aware that it's something that's needed/wanted.

Let's just hope our TENN Pico can compete, and we will get a fair share of the cake.

Loading…

www.fierceelectronics.com

I think our best chance of big success is either a joint venture with or a takeover by a major.....like Nvidia...........

 

[rgupta]

We are not alone anymore, but not surprising considering many are aware that it's something that's needed/wanted.

Let's just hope our TENN Pico can compete, and we will get a fair share of the cake.

Loading…

www.fierceelectronics.com

Or they are using our technology to bring forward their solutions.

 

[Guzzi62]

I think our best chance of big success is either a joint venture with or a takeover by a major.....like Nvidia...........

I know this is from last year, but something I have very high hopes about:

Tata Elxsi's partnership with BrainChip will be driving Akida technology into medical devices and industrial applications.

Loading…

www.eetindia.co.in

Page 15:

Loading…

www.tataelxsi.com

Tata is a monster company with 1 million employees and 150 billion in revenue in 2023, very likely the largest company we interact with.

Okay, we are interacting with one of the satellite branches (Elxsi) with 10,000 people.

The Tata Group is an Indian group of companies headquartered in Mumbai. Established in 1868, it is India's largest business conglomerate, with products and services in over 150 countries, and operations in 100 countries. Wikipedia
Parent organization: Tata Sons
Founder: Jamshedji Tata
Subsidiaries: Tata Motors, Tata Consultancy Services · See more
Headquarters: Mumbai, India
Founded: 1868, Mumbai, India
Revenue: 12 trillion INR (US$150 billion, 2023)
Number of employees: 1,028,000 (FY 2023)

 

[TECH]

A must watch video on the link below.

BrainChip's technology would be the perfect fit for Qualcomm IMO. Yes, they have their own NPU, but their NPU doesn't have TENNs or the ultra low power consumption that Akida Pico offers.

As I've mentioned in the past, it would be great to have our Chief Technology Officer, Dr Tony Lewis explain in detail how our technology could compliment/improve Qualcomm's. Tony was was the former Senior Director of Technology at Qualcomm and was the creator of Qualcomm's Zeroth neural processing unit and its software API, which was subsequently incorporated into the SNAPDRAGON processor. So who better to drill down on this topic?

I know, NDA's blah, blah , blah.. Sigh...

View attachment 71546

https://www.telecoms.com/ai/qualcomm-s-edge-ai-network-vision

Hey Bravo....thank you for all your time and effort in ploughing through website after website in an attempt to gain that
bit of knowledge that ends up reassuring many posters...as you already know, this forum has many diverse personalities, some
who like to knock you down and others of us who think that our contribution adds positivity to our forum.

You could always send an email attention: Dr Tony Lewis and ask him what his thoughts are, worst case scenario, he doesn't reply.

I also think that Dio's suggestion earlier this year ? regarding the software approach being taken by autonomous vehicle
manufacturers has a lot of merit, hardware will follow, but right now I personally think we are still part of the inner circle, not
confirmed by the company, just my open opinion.

Regards....Tech (Chris)

 

[Diogenese]

Hi @Diogenese,

I just stumbled upon this announcement re the collaboration between VVDN and Axiado which may well be relevant to your 2022 post (above). And perhaps now even more so, given our partnership with VVDN?

Axiado and VVDN Technologies Collaborate to Showcase AI-Enhanced Platform Security and OCP-Compliant Data Center Solutions at 2024 OCP Global Summit​

---

News provided by​

Axiado
Oct 09, 2024, 18:39 ET

​

---

AI-Driven hardware anchored Platform Security Solutions Set New Standard for Secure, Scalable OCP Compliant Data Center Infrastructure
SAN JOSE, Calif. and GURUGRAM, India, Oct. 9, 2024 /PRNewswire/ -- 2024 OCP Global Summit – Axiado Corporation, a leading AI-driven, hardware-anchored platform security solutions company, and VVDN Technologies, a global provider of software, product engineering, electronics manufacturing services and solutions, today announced a collaboration to showcase AI-enhanced hardware cybersecurity solutions for Open Compute Project (OCP)-compliant data center and telco O-RAN servers at the 2024 OCP Global Summit October 15-17, 2024 in San Jose.
The partnership combines Axiado's Trusted Control/Compute Unit (TCU) with VVDN's expertise in designing and manufacturing OCP-compliant server architectures. This joint effort aims to accelerate the adoption of AI-driven platform security and redefine energy-efficient, secure computing for next-generation data centers and telecom networks.
"Enterprises today demand immediate, scalable solutions that secure their AI-driven infrastructure from the ground up," said Gopi Sirineni, President and CEO of Axiado. "With Axiado's TCU technology seamlessly integrated into VVDN's OCP-compliant designs, we are redefining the future of cybersecurity for hyperscale AI-centric data centers. This partnership enables organizations to implement AI-driven, hardware-anchored protection that not only combats advanced cyber threats in real time but also enhances energy efficiency and sustainability across their infrastructure."
Key Collaboration Highlights:

• OCP Global Summit Demonstration: Axiado and VVDN will demonstrate an OCP-compliant AI server powered by Axiado's AX3000 and AX2000 TCUs, providing an integrated security solution for data centers and telecom environments.
• AI-Powered Platform Security: Axiado's TCUs, with embedded AI and machine learning, provide real-time, pre-emptive threat detection, isolating and mitigating attacks at the hardware level, significantly enhancing zero-trust architecture.
• Dynamic Thermal Management: Axiado's TCU features Dynamic Thermal Management (DTM) technology, leveraging AI to optimize cooling efficiency, reduce CO2 emissions, and lower energy consumption by up to 11% in large-scale data center environments.
• Designing and Manufacturing Servers: VVDN is co-designing and manufacturing OCP-compliant AI servers using AMD EPYC™ CPUs and AMD Instinct™ accelerators that cater to the evolving needs of cloud, data center, and Open RAN applications, while addressing critical challenges in security and sustainability.

"The strength of our long-lasting partnership with Axiado begins at the hardware level and extends across our entire OCP-compliant server portfolio," said Puneet Agarwal, Co-Founder and CEO of VVDN Technologies. "Together, we are integrating Axiado's groundbreaking TCU technology with our state-of-the-art server designs to deliver AI-driven, hardware-anchored cybersecurity solutions that redefine platform security and efficiency. This partnership is a testament to our commitment to providing secure, scalable, and energy-efficient solutions for the cloud and telecom sectors."
Axiado's AX3000 and AX2000 TCUs represent a new category of forensic-enabled cybersecurity processors designed to enhance zero-trust models. The TCU integrates AI and machine learning into a single system-on-chip (SoC) to deliver pre-emptive threat detection, real-time protection, and energy efficiency. The TCU includes hardware anchored root-of-trust (RoT), baseboard management controller (BMC), trusted platform module (TPM), secure NIC, hardware security module, and firewall technologies, making it the most comprehensive cybersecurity solution for AI-driven data centers and 5G networks.
Availability
Axiado's AX3000 and AX2000 TCUs as well as OCP DC-SCM 2.0 Compliant Axiado SCM3002 and Axiado SCM3003 are available now for purchase. Please contact Axiado for samples and pricing.
OCP Global Summit Demonstration
Visit booth C49 at the 2024 OCP Global Summit to see how Axiado and VVDN are shaping the future of AI and cloud networks. Axiado and VVDN will showcase their collaboration, featuring the Axiado DC-SCM 2.0 module integrated into VVDN's OCP-compliant motherboard. This demonstration will highlight how Axiado's TCU technology enhances platform security, offers real-time threat mitigation, and improves energy efficiency for data center and telco environments.
About Axiado
Axiado Corporation is an AI-driven Platform Security Solutions company focused on protecting cloud data centers, 5G networks, and critical infrastructure against ransomware, supply chain, side-channel, and other cyberattacks. Axiado's Trusted Control/Compute Unit (TCU) delivers real-time, pre-emptive threat detection and platform security, while its Dynamic Thermal Management (DTM) solution reduces energy consumption and operational costs in data centers, advancing the goal of carbon-net zero emissions. For more information, visit axiado.com or follow us on LinkedIn.
About VVDN Technologies
Founded in 2007, VVDN is a technology innovation company focusing primarily on Software Services, Product Engineering and Manufacturing Services. VVDN's India HQ is located at Gurgaon, India, and its North America HQ is located in Fremont, CA, USA. VVDN has a presence across the world with offices in US, Canada, Europe, Vietnam, South Korea, and Japan. With 11 advanced R&D Centers, VVDN is fully equipped to design, develop & test the complete hardware, mechanical & software required for a complete product or solution. VVDN's 7 Manufacturing facilities are located at Manesar, Gurgaon, and Pollachi, Tamil Nadu, India, which includes in-house best-in-class SMT Factory, Mold & Tooling Factory, Injection Molding, Die Casting, Powder Coating, Sheet Metal, Product Assembly Factory, and Product Certifications labs. Company offers a comprehensive suite of services from Hardware to Mechanical, Embedded Software to Cloud & Apps, Testing & Validation to Automation as well as Mass Manufacturing to its global customers. For more information, visit vvdntech.com.

https://www.prnewswire.com/news-rel...ions-at-2024-ocp-global-summit-302272183.html

​

View attachment 71562

Hi Bravo,

Axiado has patents for NNs but does not seem to know about spikes:

US2023289482A1 MACHINE LEARNING METHODS AND SYSTEMS FOR DETECTING PLATFORM SIDE-CHANNEL ATTACKS

US2023060207A1 SYSTEMS AND METHODS USING NETWORK ARTIFICIAL INTELLIGENCE TO MANAGE CONTROL PLANE SECURITY IN REAL-TIME 20210821

[0070] Computer system 1200 includes one or more processor(s) 1201 (e.g., central processing units (CPUs), general purpose graphics processing units (GPGPUs), or quantum processing units (QPUs)) that carry out functions. Processor(s) 1201 optionally contains a cache memory unit 1202 for temporary local storage of instructions, data, or computer addresses. Processor(s) 1201 are configured to assist in execution of computer readable instructions. Computer system 1200 may provide functionality for the components depicted in FIG. 12 as a result of the processor(s) 1201 executing non-transitory, processor-executable instructions embodied in one or more tangible computer-readable storage media, such as memory 1203 , storage 1208 , storage devices 1235 , and/or storage medium 1236

[0033] In some embodiments, the deep learning method comprises one or more algorithms that learns by extracting new features to predict outputs.

They do have a NN processor that drives their secure AI:

 

[Tothemoon24]

Not sure if this paper has been shared discussing Spiking Neural Networks for autonomous driving .
Brainchip is mentioned;
We look to be a shining star against the mentioned competitors
Solid hour of reading : Link below

Abstract​

The rapid progress of autonomous driving (AD) has triggered a surge in demand for safer and more efficient autonomous vehicles, owing to the intricacy of modern urban environments. Traditional approaches to autonomous driving have heavily relied on conventional machine learning methodologies, particularly convolutional neural networks (CNNs) and recurrent neural networks (RNNs), for tasks such as perception, decision-making, and control. Presently, major companies such as Tesla, Waymo, Uber, and Volkswagen Group (VW) leverage neural networks for advanced perception and autonomous decision-making. However, concerns have been raised about the escalating computational requirements of training these neural models, primarily in terms of energy consumption and environmental impact. In the situation of optimisation and sustainability, Spiking Neural Networks (SNNs), inspired by the temporal processing of the human brain, have come forth as a third-generation of neural networks, famed for their energy efficiency, potential for handling real-time driving scenarios and processing temporal information efficiently. However, SNNs have not yet achieved the performance levels of their predecessors in critical AD tasks, partly due to the intricate dynamics of neurons, their non-differentiable spike operations, and the lack of specialised benchmark workloads and datasets, among others. This paper examines the principles, models, learning rules, and recent advancements of SNNs in the AD domain. Neuromorphic hardware, hand in hand with SNNs, shows potential but has challenges in accessibility, cost, integration, and scalability. This examination aims to bridge gaps by providing a comprehensive understanding of SNNs in the AD field. It emphasises the role of SNNs in shaping the future of AD while considering optimisation and sustainability.

https://www.sciencedirect.com/science/article/pii/S0952197624015732?dgcid=coauthor

https://www.sciencedirect.com/science/article/pii/S0952197624015732?dgcid=coauthor

 

[Tothemoon24]

Neuromorphic NPU Sips Power to Handle Edge Machine-Learning Models

BrainChip’s Akida Pico neural processing unit, which leverages spiking neural networks, targets low-power IoT and edge-computing devices.

www.electronicdesign.com

 

[Tothemoon24]

 

[Esq.111]

Afternoon Chippers ,

Just came upon this at the the other site .

Don't think I have seen this image before .

Interesting none the less.

Regards,
Esq.

 

[Diogenese]

Neuromorphic NPU Sips Power to Handle Edge Machine-Learning Models

BrainChip’s Akida Pico neural processing unit, which leverages spiking neural networks, targets low-power IoT and edge-computing devices.

www.electronicdesign.com

View attachment 71588
View attachment 71589

But is Jerome talking through his hat?

 

[TasTroy77]

Afternoon Chippers ,

Just came upon this at the the other site .

Don't think I have seen this image before .

Interesting none the less.

View attachment 71592

Regards,
Esq.

Renesas !

 

[Bravo]

Not sure if this paper has been shared discussing Spiking Neural Networks for autonomous driving .
Brainchip is mentioned;
We look to be a shining star against the mentioned competitors
Solid hour of reading : Link below

Abstract​

The rapid progress of autonomous driving (AD) has triggered a surge in demand for safer and more efficient autonomous vehicles, owing to the intricacy of modern urban environments. Traditional approaches to autonomous driving have heavily relied on conventional machine learning methodologies, particularly convolutional neural networks (CNNs) and recurrent neural networks (RNNs), for tasks such as perception, decision-making, and control. Presently, major companies such as Tesla, Waymo, Uber, and Volkswagen Group (VW) leverage neural networks for advanced perception and autonomous decision-making. However, concerns have been raised about the escalating computational requirements of training these neural models, primarily in terms of energy consumption and environmental impact. In the situation of optimisation and sustainability, Spiking Neural Networks (SNNs), inspired by the temporal processing of the human brain, have come forth as a third-generation of neural networks, famed for their energy efficiency, potential for handling real-time driving scenarios and processing temporal information efficiently. However, SNNs have not yet achieved the performance levels of their predecessors in critical AD tasks, partly due to the intricate dynamics of neurons, their non-differentiable spike operations, and the lack of specialised benchmark workloads and datasets, among others. This paper examines the principles, models, learning rules, and recent advancements of SNNs in the AD domain. Neuromorphic hardware, hand in hand with SNNs, shows potential but has challenges in accessibility, cost, integration, and scalability. This examination aims to bridge gaps by providing a comprehensive understanding of SNNs in the AD field. It emphasises the role of SNNs in shaping the future of AD while considering optimisation and sustainability.


View attachment 71572



View attachment 71571

https://www.sciencedirect.com/science/article/pii/S0952197624015732?dgcid=coauthor

https://www.sciencedirect.com/science/article/pii/S0952197624015732?dgcid=coauthor

Wow @Tothemoon24!

This research paper is really ahead of it's time!

Obviously a quarterly publication.

Please don't anyone go mentioning to the usual suspects on the Crapper that Loihi is, as this paper re-confirms, "still in development" or they might blow a gasket.

 

[CHIPS]

Hopefully one of their 43 followers, is in need of our tech and has some weight behind them!

Every "little bit" of exposure helps, I guess..

47... she now has 47 followers

 

[DingoBorat]

47... she now has 47 followers

Yeah, so I guess that's you and 3 others off of here?

Unless "it's" you, how did you know they are a "she" ..

 

[IloveLamp]

ASX AI Stocks: 5 Biggest Companies in 2024

Artificial intelligence (AI) continues to evolve and advance rapidly, becoming increasingly integrated in the automation of everyday life and a focal point of growth in the technology sector.AI is also becoming a major focus for the Australian government, whose budget for the 2023/2024 fiscal...

investingnews.com

 

[Euks]

This would be nice to be us in some way shape or form. I mean come on. We are overdue….. I know Rob’s gone but maybe just maybe….