BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
buena suerte :-)
BOB Bank of Brainchip
It's not the monetary value...It's BRN finally finding a pulse and finally heading North.. You are so negative ...jeez :-(
David holland
Regular
No mate I just talk the facts, I've read all the posts about how where going to be rich and guess the shareprice by xmas, All the dot joining etc etc, But until I see it I'll be excited, is it coming probably, this forum was page after page everyday but it's flat, I've told people about this share and believe me unless they see profits your lose friendships, This is the Facts and yes I take the piss with the companies in-house secrecy for the sake of customers, It's a load of crap once it's out there if the product is good EVERYBODY Knows because news travels real fast on a good product
Damo4
Regular
Thanks Bacon
Pom down under
Top 20
RobjHunt
Regular
Even better if it’s a Green Friday
Fact Finder
Top 20
Hi All
The following research paper is interesting for two reasons:
1. Some suggest that manipulators do not exist and that they are simply providing balance which is needed to prevent here and HC becoming echo chambers. Well I am sure you will all remember the balanced opinions at HC and here from posters who claimed that we were all mad to believe that Brainchip AKIDA could be used in data centres and that its only value was narrow and at the edge. Indeed the last example of this on TSEx was an individual who claimed to be an Engineer who called me out and ridiculed the very suggestion that AKIDA could possibly be used in a data centre. In the end he/she/it was dispatched.
2. Some suggest that Brainchip management and Board have no idea what they are doing and have chosen the wrong direction and should be doing x, y & z and the posters making these claims sometimes even claim to be successful business owners who know what they are talking about.
Well it might well be that these researchers in this paper funded by the German Government and published on 4 January, 2024 have no idea but the following extracts suggest otherwise and also confirms that there has been and will be again a concerted sophisticated campaign of misinformation targeting Brainchip here and on HC for clear and transparent reasons:
Neuromorphic hardware for sustainable AI data centers
Bernhard Vogginger∗x, Amirhossein Rostami∗∥, Vaibhav Jain§, Sirine Arfa∗, Andreas Hantsch∗∗††, David Kappel¶, Michael Scha ̈fer†‡, Ulrike Faltings†, Hector A. Gonzalez∗∥‡‡, Chen Liu∗, Christian Mayr∗∥
∗Chair of Highly-Parallel VLSI-Systems and Neuro-Microelectronics, Technische Universita ̈t Dresden, Germany
†SHS - Stahl-Holding-Saar GmbH & Co. KGaA, Germany
‡KTH Royal Institute of Technology, Department of Materials Science and Engineering, Sweden
§Deutsches Forschungszentrum fu ̈r Ku ̈nstliche Intelligenz GmbH, Saarbru ̈cken, Germany
¶Institute for Neural Computation, Ruhr University Bochum, Germany
∥ScaDS.AI Dresden/Leipzig, Germany
∗∗eco2050 Institut fu ̈r Nachhaltigkeit – Institute for Sustainability GmbH, Nu ̈rnberg, Germany
††Hantsch Sustainability Consulting, Dresden, Germany
‡‡SpiNNcloud Systems GmbH, Dresden, Germany x
Email: bernhard.vogginger@tu-dresden.de
Abstract—As humans advance toward a higher level of artifi- cial intelligence, it is always at the cost of escalating computa- tional resource consumption, which requires developing novel so- lutions to meet the exponential growth of AI computing demand. Neuromorphic hardware takes inspiration from how the brain processes information and promises energy-efficient computing of AI workloads. Despite its potential, neuromorphic hardware has not found its way into commercial AI data centers. In this article, we try to analyze the underlying reasons for this and derive requirements and guidelines to promote neuromorphic systems for efficient and sustainable cloud computing: We first review currently available neuromorphic hardware systems and collect examples where neuromorphic solutions excel conventional AI processing on CPUs and GPUs. Next, we identify applications, models and algorithms which are commonly deployed in AI data centers as further directions for neuromorphic algorithms research. Last, we derive requirements and best practices for the hardware and software integration of neuromorphic systems into data centers. With this article, we hope to increase awareness of the challenges of integrating neuromorphic hardware into data centers and to guide the community to enable sustainable and energy-efficient AI at scale.
Index Terms—neuromorphic hardware, cloud computing, ar- tificial intelligence, data center, sustainable computing…
Neuromorphic computing aims to design and build computer systems including hardware and
software that can perform cognitive tasks more efficiently by emulating how neurons and synapses work in the brain. Neuro- morphic systems incorporate the concept of synaptic plasticity, allowing synapses between spiking neurons to change and adapt based on the input patterns. This work addresses the integration of neuromorphic hardware into data centers for sustainable AI…
3) BrainChip: Akida is an event-based processor developed by BrainChip [27]. Akida supports a wide variety of neural networks and can execute complex networks. It also supports the AXI bus for connection to CPUs, allowing custom net- works not supported by Akida to be executed on the CPU. It comprises a data processing unit to preprocess input data, converting it into events, and uses an LPDDR4 interface for storing programs and parameters. Additionally, the PCIe inter- face can be used to connect to other Akida chips. Akida aims to support a broad range of applications, including robotics and automation in industry, real-time sensing in automotive, vital- signs prediction in on-device health monitoring, and intelligent automation in homes….
As an exception, BrainChip offers PCIe boards for integrating their Akida chips with CPU servers. This represents another option for integrating neuromorphic computing systems into data centers, similar to normal GPUs. Note, however, that this might limit the size of neuromorphic models that can be implemented compared to the larger systems discussed above.
2) Conclusion: The above examples show that a variety of neuromorphic systems have been successfully integrated into standard data center server racks….
So far, only BrainChip provides a model zoo for their Akida systems [101]. This allows us to retrain or fine-tune existing model architectures to customers’ needs, which not only offers a shorter time-to-solution but also reduces the environmental footprint, as training from scratch can be avoided…
VI. CONCLUSION
In this article, we reviewed neuromorphic hardware platforms and algorithms for their suitability in reducing energy consumption in AI data centers. We also discussed the current challenges that neuromorphic computing faces in becoming a mainstream technology used by the industry. In particular, we analyzed that the current AI model types supported by neuromorphic computing only partially match the AI models commonly run in AI data centers. We conclude that the neuromorphic computing community should focus on state-of-the-art ML technologies, such as transformers, and needs to establish standardized software frameworks that ensure interoperability among hardware vendors.
Data center sustainability is not only about saving energy during operations but also about saving water and materials while keeping social and governance issues in mind. These latter issues are becoming increasingly important as AI models use vast amounts of personal data. When considering the carbon footprint, one will eventually face the question of whether or not to integrate specialized hardware: the embodied footprint of an additional device may be greater than the operational footprint savings due to specialized solutions [102]. Neuromorphic engineers should therefore focus on the high utilization of their platforms.”
This is the link to this paper. It is a worthwhile read as it covers other technologies that are often thrown up by some as direct competitors about to crush Brainchip:
If you get nothing more from this paper than confirmation that you should not believe anything you read here or on HC until you have independently confirmed what is alleged it is worth its weight in gold.
My opinion only DYOR
Fact Finder
The following research paper is interesting for two reasons:
1. Some suggest that manipulators do not exist and that they are simply providing balance which is needed to prevent here and HC becoming echo chambers. Well I am sure you will all remember the balanced opinions at HC and here from posters who claimed that we were all mad to believe that Brainchip AKIDA could be used in data centres and that its only value was narrow and at the edge. Indeed the last example of this on TSEx was an individual who claimed to be an Engineer who called me out and ridiculed the very suggestion that AKIDA could possibly be used in a data centre. In the end he/she/it was dispatched.
2. Some suggest that Brainchip management and Board have no idea what they are doing and have chosen the wrong direction and should be doing x, y & z and the posters making these claims sometimes even claim to be successful business owners who know what they are talking about.
Well it might well be that these researchers in this paper funded by the German Government and published on 4 January, 2024 have no idea but the following extracts suggest otherwise and also confirms that there has been and will be again a concerted sophisticated campaign of misinformation targeting Brainchip here and on HC for clear and transparent reasons:
Neuromorphic hardware for sustainable AI data centers
Bernhard Vogginger∗x, Amirhossein Rostami∗∥, Vaibhav Jain§, Sirine Arfa∗, Andreas Hantsch∗∗††, David Kappel¶, Michael Scha ̈fer†‡, Ulrike Faltings†, Hector A. Gonzalez∗∥‡‡, Chen Liu∗, Christian Mayr∗∥
∗Chair of Highly-Parallel VLSI-Systems and Neuro-Microelectronics, Technische Universita ̈t Dresden, Germany
†SHS - Stahl-Holding-Saar GmbH & Co. KGaA, Germany
‡KTH Royal Institute of Technology, Department of Materials Science and Engineering, Sweden
§Deutsches Forschungszentrum fu ̈r Ku ̈nstliche Intelligenz GmbH, Saarbru ̈cken, Germany
¶Institute for Neural Computation, Ruhr University Bochum, Germany
∥ScaDS.AI Dresden/Leipzig, Germany
∗∗eco2050 Institut fu ̈r Nachhaltigkeit – Institute for Sustainability GmbH, Nu ̈rnberg, Germany
††Hantsch Sustainability Consulting, Dresden, Germany
‡‡SpiNNcloud Systems GmbH, Dresden, Germany x
Email: bernhard.vogginger@tu-dresden.de
Abstract—As humans advance toward a higher level of artifi- cial intelligence, it is always at the cost of escalating computa- tional resource consumption, which requires developing novel so- lutions to meet the exponential growth of AI computing demand. Neuromorphic hardware takes inspiration from how the brain processes information and promises energy-efficient computing of AI workloads. Despite its potential, neuromorphic hardware has not found its way into commercial AI data centers. In this article, we try to analyze the underlying reasons for this and derive requirements and guidelines to promote neuromorphic systems for efficient and sustainable cloud computing: We first review currently available neuromorphic hardware systems and collect examples where neuromorphic solutions excel conventional AI processing on CPUs and GPUs. Next, we identify applications, models and algorithms which are commonly deployed in AI data centers as further directions for neuromorphic algorithms research. Last, we derive requirements and best practices for the hardware and software integration of neuromorphic systems into data centers. With this article, we hope to increase awareness of the challenges of integrating neuromorphic hardware into data centers and to guide the community to enable sustainable and energy-efficient AI at scale.
Index Terms—neuromorphic hardware, cloud computing, ar- tificial intelligence, data center, sustainable computing…
Neuromorphic computing aims to design and build computer systems including hardware and
software that can perform cognitive tasks more efficiently by emulating how neurons and synapses work in the brain. Neuro- morphic systems incorporate the concept of synaptic plasticity, allowing synapses between spiking neurons to change and adapt based on the input patterns. This work addresses the integration of neuromorphic hardware into data centers for sustainable AI…
3) BrainChip: Akida is an event-based processor developed by BrainChip [27]. Akida supports a wide variety of neural networks and can execute complex networks. It also supports the AXI bus for connection to CPUs, allowing custom net- works not supported by Akida to be executed on the CPU. It comprises a data processing unit to preprocess input data, converting it into events, and uses an LPDDR4 interface for storing programs and parameters. Additionally, the PCIe inter- face can be used to connect to other Akida chips. Akida aims to support a broad range of applications, including robotics and automation in industry, real-time sensing in automotive, vital- signs prediction in on-device health monitoring, and intelligent automation in homes….
As an exception, BrainChip offers PCIe boards for integrating their Akida chips with CPU servers. This represents another option for integrating neuromorphic computing systems into data centers, similar to normal GPUs. Note, however, that this might limit the size of neuromorphic models that can be implemented compared to the larger systems discussed above.
2) Conclusion: The above examples show that a variety of neuromorphic systems have been successfully integrated into standard data center server racks….
So far, only BrainChip provides a model zoo for their Akida systems [101]. This allows us to retrain or fine-tune existing model architectures to customers’ needs, which not only offers a shorter time-to-solution but also reduces the environmental footprint, as training from scratch can be avoided…
VI. CONCLUSION
In this article, we reviewed neuromorphic hardware platforms and algorithms for their suitability in reducing energy consumption in AI data centers. We also discussed the current challenges that neuromorphic computing faces in becoming a mainstream technology used by the industry. In particular, we analyzed that the current AI model types supported by neuromorphic computing only partially match the AI models commonly run in AI data centers. We conclude that the neuromorphic computing community should focus on state-of-the-art ML technologies, such as transformers, and needs to establish standardized software frameworks that ensure interoperability among hardware vendors.
Data center sustainability is not only about saving energy during operations but also about saving water and materials while keeping social and governance issues in mind. These latter issues are becoming increasingly important as AI models use vast amounts of personal data. When considering the carbon footprint, one will eventually face the question of whether or not to integrate specialized hardware: the embodied footprint of an additional device may be greater than the operational footprint savings due to specialized solutions [102]. Neuromorphic engineers should therefore focus on the high utilization of their platforms.”
This is the link to this paper. It is a worthwhile read as it covers other technologies that are often thrown up by some as direct competitors about to crush Brainchip:
If you get nothing more from this paper than confirmation that you should not believe anything you read here or on HC until you have independently confirmed what is alleged it is worth its weight in gold.
My opinion only DYOR
Fact Finder
Last edited:
RobjHunt
Regular
That’s what I like about your comments and sarcasm, bugger all!
RobjHunt
Regular
Spot on the money mate. That person reminds me of other negative posters we’ve come across during our journey over the last few years. Think I need to find that Round Up again
Bravo
If ARM was an arm, BRN would be its biceps💪!
OpenAI reportedly working on next big product: A ChatGPT that can use devices
Artificial intelligence could spell the end of “smart assistants” as we know them.1081Total views
5Total shares
Listen to article
2:55
NEWS
Collect article
Own this piece of history as an NFT
Join us on social networks
OpenAI is reportedly developing an autonomous artificial intelligence (AI) assistant system capable of assuming control of a user’s device to perform tasks.The potential new product was first reported by The Information, citing a source familiar with the matter.
While details are scarce — OpenAI didn’t immediately respond to Cointelegraph’s requests for comment and clarification — it stands to reason that the next logical step beyond generative AI systems such as ChatGPT would be action agents.
Action agents
Generative AI systems such as ChatGPT and Google’s Gemini are designed to generate humanlike media such as text, images, audio and video.Typically, in order to get one of these models to perform a real-world action, such as operating a robot, developers must cobble them together with external applications that adapt the AI’s output into a programmable executable.
Related: Huawei researchers say giving AI a ‘body’ is the next step toward human-level agents
The technology underpinning most smart assistants and similar systems isn’t quite as robust as what’s working under the hood of ChatGPT, Gemini or even Amazon’s own generative and foundational AI products.
Advertisement
Unlock premium trading experience with Markets Pro. Start now with up to 70% New Years discount!
Ad
It stands to reason that a virtual assistant built on large language model technology (such as that used to create ChatGPT) would have greater potential for autonomous action than the comparatively simple systems powering the previous generation of smart assistants.
Death of the user interface
Until it’s known exactly what OpenAI intends to do with its reported autonomous action agents, all that one can do is speculate as to their potential capabilities.The Information’s report indicated that the new AI system would be capable of operating users’ devices to perform requested tasks. It cited an example where a user asks the AI to copy data from one platform to another.
Ostensibly, any physical function a human can perform — such as swiping, tapping, clicking, double-clicking, typing and even solving CAPTCHA puzzles to prove one is not a robot —could be performed by an AI system with sufficient device privileges.
Autonomy and security
While this technology might sound like something straight out of a Marvel film — Iron Man’s JARVIS, for example — the reality is that the road to autonomous assistance systems is littered with privacy and security challenges.Current state-of-the-art generative AI systems aren’t discrete. They require connectivity to massive cloud compute centers. While it is possible to run some AI functions entirely on laptops and smartphones, it’s unlikely that an AI action agent, as imagined, would be able to run on an onboard AI chip alone.
This could pose a potentially massive privacy threat. Coupled with the obvious security threat of giving a corporate AI system unfettered access to private information and the average smartphone’s ability to exchange data at internet scale, the realization of an autonomous action agent could represent a critical new cyberthreat with global implications.
Preparing For An AI-Driven Future In Chips
Designs need to be flexible enough to handle an onslaught of continuous and rapid changes, but secure enough to protect data.
semiengineering.com
Frangipani
Regular
View attachment 55846
Remember this June 2023 This is our Mission podcast?
Episode 27: Podcast with USC Professor Dr. Gaurav Sukhatme on Innovation in AI, Robotics & Autonomy
Listen to Episode 27 of our podcast featuring USC Professor Dr. Gaurav Sukhatme as we explore innovation in AI, robotics, and autonomy.brainchip.com
After introducing his guest, who also serves as the Executive Vice Dean at the USC Viterbi School of Engineering, Nandan Nayampally says “You know, we go back a long way … in fact, we had common alma maters.” (03:14 min)
Gaurav Sukatme:
From 25:32 min: “I think the partnership between industry and academia is crucial here to make progress.”
From 27:13 min: “You know, companies like yours, like Brainchip, what you are doing with the University Accelerator Program, I like very much - in fact, we’re looking into it, as you know, we’ll be having a phone [?] conversation about exploring that further. I think programs like that are unique and can really make the nexus between a leading company and academia sort of be tighter and be stronger.”
At the end of the podcast, Nandan Nayampally thanks his guest for sharing his insights and closes with the words “…and hopefully we’ll work together much closer soon.” (35:15 min)
Which makes Brainchip’s involvement in CONCRETE (Center of Neuromorphic Computing and Extreme Environment”), well, not concrete, but certainly more likely…
Another USC professor very much aware of Brainchip & Akida:
(The Hughes Aircraft Electrical Engineering Center houses the Ming Hsieh Department of Electrical and Computer Engineering-Systems, cf.
https://viterbi.usc.edu/news/news/2012/hughes-aircraft-electrical.htm - sections of the now defunct aerospace and defense contractor that gifted its name to the building live on in Raytheon and Boeing.)
Unfortunately, I don’t have any login credentials, so someone else needs to find out what the authors say about Akida in 17.4.
The preview includes the book’s preface, though, in which our company gets a mention, too.
Attachments
buena suerte :-)
BOB Bank of Brainchip
Yep you certainly had a good supply RobjSpot on the money mate. That person reminds me of other negative posters we’ve come across during our journey over the last few years. Think I need to find that Round Up again
You mean “lunch”? Right?
jtardif999
Regular
I think it’s more likely that AMD have been developing their edge chip for longer than they’ve known about an alternative better. Like I said once before, companies have been doing their R&D for a long time and they want to reap the costs they’ve incurred this time around. LDN always used to frame this as we have to intersect a company at the right time in their development cycle otherwise they are not going to be shopping.
Smoothsailing
Regular
Brilliant
Bravo
If ARM was an arm, BRN would be its biceps💪!
OpenAI reportedly working on next big product: A ChatGPT that can use devices
Artificial intelligence could spell the end of “smart assistants” as we know them.
1081Total views
5Total shares
Listen to article
2:55
NEWS
Collect article
Own this piece of history as an NFT
Join us on social networks
OpenAI is reportedly developing an autonomous artificial intelligence (AI) assistant system capable of assuming control of a user’s device to perform tasks.
The potential new product was first reported by The Information, citing a source familiar with the matter.
While details are scarce — OpenAI didn’t immediately respond to Cointelegraph’s requests for comment and clarification — it stands to reason that the next logical step beyond generative AI systems such as ChatGPT would be action agents.
Action agents
Generative AI systems such as ChatGPT and Google’s Gemini are designed to generate humanlike media such as text, images, audio and video.
Typically, in order to get one of these models to perform a real-world action, such as operating a robot, developers must cobble them together with external applications that adapt the AI’s output into a programmable executable.
Related: Huawei researchers say giving AI a ‘body’ is the next step toward human-level agents
The technology underpinning most smart assistants and similar systems isn’t quite as robust as what’s working under the hood of ChatGPT, Gemini or even Amazon’s own generative and foundational AI products.
Advertisement
Unlock premium trading experience with Markets Pro. Start now with up to 70% New Years discount!
Ad
It stands to reason that a virtual assistant built on large language model technology (such as that used to create ChatGPT) would have greater potential for autonomous action than the comparatively simple systems powering the previous generation of smart assistants.
Death of the user interface
Until it’s known exactly what OpenAI intends to do with its reported autonomous action agents, all that one can do is speculate as to their potential capabilities.
The Information’s report indicated that the new AI system would be capable of operating users’ devices to perform requested tasks. It cited an example where a user asks the AI to copy data from one platform to another.
Ostensibly, any physical function a human can perform — such as swiping, tapping, clicking, double-clicking, typing and even solving CAPTCHA puzzles to prove one is not a robot —could be performed by an AI system with sufficient device privileges.
Autonomy and security
While this technology might sound like something straight out of a Marvel film — Iron Man’s JARVIS, for example — the reality is that the road to autonomous assistance systems is littered with privacy and security challenges.
Current state-of-the-art generative AI systems aren’t discrete. They require connectivity to massive cloud compute centers. While it is possible to run some AI functions entirely on laptops and smartphones, it’s unlikely that an AI action agent, as imagined, would be able to run on an onboard AI chip alone.
This could pose a potentially massive privacy threat. Coupled with the obvious security threat of giving a corporate AI system unfettered access to private information and the average smartphone’s ability to exchange data at internet scale, the realization of an autonomous action agent could represent a critical new cyberthreat with global implications.
I find the below extract from an article dated 6 Nov 2023 very interesting.
We all know OpenAI and Mercedes are collaborating.
And remember that the Mercedes EQXX featured AKIDA-powered neuromorphic AI voice control technology which Mercedes engineers said was 5 to 10 times more efficient than conventional voice control.
Sooo...I wonder....
White Horse
Regular
Hi DH,
Clearly, BRN are not alone in their belief of the customers right to privacy.
Taken from Frangipani's earlier post.
Quote,
The Company remains encouraged that demand for Sondrel's ASIC services, including in the US, remains strong and that the Group continues to trade in line with current market expectations with a number of new ASIC business opportunities at advanced stages of negotiation. The Group does not comment on the identity of customers.
Similar threads
