58 minutes ago - 2 applicants. The tech layoffs will ensure there is no shortage of quality candidates.
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
thelittleshort
Top Bloke
Excellent Post J.......fact after fact.....great to see our two Perth Data Scientist/s Engineers named as inventors in the latest AU Patent, that is,
Keith and Milind...top stuff, our Perth office is full of brilliant talent!
Tech
Hey @TECH you know who Douglas McLelland is? Seems to be the only one on the list external to BrainChip
Bravo
If ARM was an arm, BRN would be its biceps💪!
Here's what Adam White, President of Infineon Technologies’ Power and Sensor Systems division said in an interview in November 2022.
EXTRACT ONLY
EXTRACT ONLY
AARONASX
Holding onto what I've got
Douglas seems to know his stuff!
Douglas McLelland
BrainChip - Cité(e) 417 fois - Computational Neuroscience - Spiking Neural Networks - Neural Network Quantization
5 reasons MLops teams are using more Edge ML
5 reasons MLops teams are using more edge ML — VentureBeat
As the number of machine learning (ML) use cases grows and evolves, an increasing number of MLops organizations are using more ML at the edge — that is, they are investing in running ML models on devices at the periphery of a network, including smart cameras, IoT computing devices, mobile...apple.news
As the number of machine learning (ML) use cases grows and evolves, an increasing number of MLops organizations are using more ML at the edge — that is, they are investing in running ML models on devices at the periphery of a network, including smart cameras, IoT computing devices, mobile devices or embedded systems.
ABI Research, a global technology intelligence firm, recently forecast that the edge ML enablement market will exceed $5 billion by 2027. While the market is still in a “nascent stage,” according to Lian Jye Su, research director at ABI Research, companies looking to ease the challenges of edge ML applications are turning to a variety of platforms, tools and solutions to boost an end-to-end MLops workflow.
“We are absolutely seeing MLops organizations increase the use of EdgeML,” said Lou Flynn, senior product manager for AI and analytics at SAS. “Enterprises big and small are running to the cloud for various reasons, but the cloud doesn’t lend itself to every use case. So organizations from nearly every industry, including aerospace, manufacturing, energy and automotive, leverage Edge AI to gain competitive advantage.”
Here are five reasons MLops teams are giving edge ML a thumbs-up:
1. Edge devices have become faster and more powerful.
“We have seen multiple companies focus on end-to-end processes around edge ML,” said Frederik Hvilshøj, lead ML engineer at data-centric computer vision company Encord. The two major reasons, he explained, are: Edge devices have become increasingly powerful while model compression has become more effective, which allows for running more powerful models at a higher speed; and edge devices also typically live much closer to the data source, which removes the necessity to move big volumes of data.
“The combination of the two means that high performance models can be run on edge devices at a close-to-real time speed,” he said. “Previously, GPUs living on central servers were necessary to get the high model throughput — but at the cost of having to transfer data back and forth, which made the use case less practical.”
2. Edge ML offers greater efficiency.
Today’s distributed data landscape is ripe with opportunity to analyze content to gain efficiencies, said Lou Flynn, senior product manager for AI and analytics at SAS.
“Many data sources originate from remote locations, such as a warehouse, a standalone sensor at a large agricultural site or even a CubeSat [a square-shaped miniature satellite] as part of a constellation of electro-optical imaging sensors,” he explained. “Each of these scenarios depicts use cases that could gain efficiencies by running edge ML vs. waiting for data to reconcile in cloud storage.”
3. Bandwidth and cost savings are key.
“You need to run ML models on the edge because of physics (bandwidth limitations, latency) and cost,” said Kjell Carlsson, head of data science strategy at Domino Data Lab. Carlsson explained that IoT is not feasible if data from every sensor needs to be streamed to the cloud to be analyzed.
“The network in a supermarket would not support the high-definition streaming from a couple dozen cameras, let alone the hundreds of cameras and other sensors you would want in a smart store,” he said. By running ML on the edge, you also avoid the cost of data transfer, he added.
“For example, a Fortune 500 manufacturer is using edge ML to continuously monitor equipment to predict equipment failure and alert staff to potential issues,” he said. “Using Domino’s MLops platform, they are monitoring 5,000+ signals with 150+ deep learning models.”
4. EdgeML helps scale the right data.
The real value of edge ML, said Hvilshøj, is that with distributed devices, you can scale your model inference without having to buy larger servers.
“With scaling inference out of the way, the next issue is collecting the right data for the next training iteration,” he said. In many cases, collecting raw data is not hard, but choosing data to label next becomes hard for large volumes of data. The compute resources on the edge devices can help identify what might be more relevant to label.
“For example, if the edge device is a phone and the user of the phone dismisses a prediction, this can be a good indicator that the model was wrong,” he said. “In turn, the particular piece of data would be good for retraining the model with proper labels.”
5. MLops organizations want more flexibility.
According to Flynn, MLops organizations should use their models to not only make better decisions, but to optimize these models for different hardware profiles — for example, using technology like the Apache TVM (Tensor Virtual Machine) to compile models to run more efficiently on different cloud providers and across devices with varying hardware (CPU, GPU and/or FPGAs). One SAS customer — Georgia-Pacific, an American pulp and paper company — uses edge computing at many of its remote manufacturing facilities where high-speed connectivity often isn’t reliable or cost-effective.
“This flexibility gives MLops teams agility to support a wide variety of use cases, enabling them to bring processing to their data on a growing pool of devices,” Flynn said. “While the range of devices are vast, they often come with resource limitations that could constrain model deployment. This is where model compression comes into play. Model compression reduces the footprint of the model and enables it to run on more compact devices (like an edge device) while improving the model’s computational performance.”
I hadn't thought the supermarket case was so strong. You have mains power and a second or two of latency is not critical, but when you add several 'cash" registers scanning items with CNN that creates an overload for the shop's comms network. Everything here is Akida to a tee - compressed model library - ML - speed - reduced data transfer ...
Hi. Doug has been with us for a number of years now, based at of LA or attached to our US office..he's been named a few times over the years as an engineer working on different projects for the company.
Regards...Chris
thelittleshort
Top Bloke
Taproot
Regular
I know this post by Luca above is old news, but closer inspection reveals more.
Adam Osseiran's comment on Luca Verre's post, well and truly puts to bed any speculation regarding the time that Prophesee and Brainchip have been aware of each others existence.
The reactions list is something well worth delving into. A total of 269 likes / loves etc. is a very small percentage of the world's total population. You can then weed out a few of the TSE members that liked his post, you can also weed out those connected to Brainchip and Prophesee. You can weed out Insto's, tech journo's / research etc. What remains is quite amazing.
Likes that are relevant to the motion blur speculation include:
Michel Sarkis
Principal Engineer / Mgr at Qualcomm
Evgeni Gousev
Senior Director at Qualcomm
Michael Scherer
Advanced Camera Technology at Samsung
Another group of individuals that stood out from this post by Luca were from Meta.
Hui Chen
Optical Scientist at Meta
Chris Harrison
AI Recruiter at Meta
Pietro Caragiulo
AR / VR Silicon at Meta
First post here about anything for a long time. No promises I get it right ok.
But I thought I would share a few points highlighted in the following letter. This letter we have all seen before back in early Feb 2023 from a poster here, where Rob replies with some valuable points to consider!
Sections are extracted below.
--------------------------------------------------------------------------------------------------------------------
Investor Relations - IR Brainchip Inc. < ir@brainchip.com> Thurs 2 Feb 2023
Thank you for your email and support of Brainchip.
.............
Although you can't see it in the 4C reports there is a huge amount of work being done to secure commercial bookings and this work is increasing as we continue to add new people in key roles within our sales team, both in the Us and in key global markets. The other thing that is not visible in the 4C reports is the focus we have on developing new products to meet the diverse and growing requirments of customers. As you will have noted, we have recently announced the tapeout of akida 1500, which is a variant of the Akida 1000 and was developed because of direct engagement with our customers. We are also working on the release of our next generation chip, Akida2000 later this year which we believe will appeal to many customers.
In conclusion, while I hear your comments and note your fustration with the time its taking for us to deliver on our promise, I would counsel that you be patient and give us more time. the only thing that has happened in the past 12 months is that we've become a much stronger and more focused company and our technology has become better known and understood by the market. It's only a matter of time before that translated into commercial success.
Tony Dawe
Director Global Investor Relations
.............................................................................................................................................
OK.
1. they are securing commercial bookings - (getting in front of potential customers.)
2. developing new products to meet the growing requirements of customers - (positive interaction on product development with customers)
3.recent announcement of AKIDA 1500 - (we are all aware of this and WHY Akida 1500 is being taped out and by WHOM)
4. (Akida 1500) was developed because of DIRECT engagement with customers - ( again direct engagement with customers)
5. RELEASE OF OUR NEXT GENERATION CHIP , AKIDA 2000.........LATER THIS YEAR - (AKIDA 2000 being released in 2023)
6. matter of time before all this translates into commercial success - ( strong words, to make a promise like this -ie: give it time & there will be commercial success)
the only problem I see is the lack of engaging the Australian (and world) Stock markets and thereby BRN shareholders and potential NEW shareholders on the ASX with any form of company update regarding these factors.
The average Australian shareholder/investor knows nothing about this and really anything about BrainChip at all. The ASX is a dead space for researching info about BrainChip that is an Australian registered company and this is just dead wrong, unbelievable!
Next week (22nd feb) ASX price sensitive coming out according to TECH.
What might be released before that maybe/hopefully?
Yak52
sorry wanted to insert image (JPEG) of the email mentioned above but cannot seem to download pics from my desktop. ??
But I thought I would share a few points highlighted in the following letter. This letter we have all seen before back in early Feb 2023 from a poster here, where Rob replies with some valuable points to consider!
Sections are extracted below.
--------------------------------------------------------------------------------------------------------------------
Investor Relations - IR Brainchip Inc. < ir@brainchip.com> Thurs 2 Feb 2023
Thank you for your email and support of Brainchip.
.............
Although you can't see it in the 4C reports there is a huge amount of work being done to secure commercial bookings and this work is increasing as we continue to add new people in key roles within our sales team, both in the Us and in key global markets. The other thing that is not visible in the 4C reports is the focus we have on developing new products to meet the diverse and growing requirments of customers. As you will have noted, we have recently announced the tapeout of akida 1500, which is a variant of the Akida 1000 and was developed because of direct engagement with our customers. We are also working on the release of our next generation chip, Akida2000 later this year which we believe will appeal to many customers.
In conclusion, while I hear your comments and note your fustration with the time its taking for us to deliver on our promise, I would counsel that you be patient and give us more time. the only thing that has happened in the past 12 months is that we've become a much stronger and more focused company and our technology has become better known and understood by the market. It's only a matter of time before that translated into commercial success.
Tony Dawe
Director Global Investor Relations
.............................................................................................................................................
OK.
1. they are securing commercial bookings - (getting in front of potential customers.)
2. developing new products to meet the growing requirements of customers - (positive interaction on product development with customers)
3.recent announcement of AKIDA 1500 - (we are all aware of this and WHY Akida 1500 is being taped out and by WHOM)
4. (Akida 1500) was developed because of DIRECT engagement with customers - ( again direct engagement with customers)
5. RELEASE OF OUR NEXT GENERATION CHIP , AKIDA 2000.........LATER THIS YEAR - (AKIDA 2000 being released in 2023)
6. matter of time before all this translates into commercial success - ( strong words, to make a promise like this -ie: give it time & there will be commercial success)
the only problem I see is the lack of engaging the Australian (and world) Stock markets and thereby BRN shareholders and potential NEW shareholders on the ASX with any form of company update regarding these factors.
The average Australian shareholder/investor knows nothing about this and really anything about BrainChip at all. The ASX is a dead space for researching info about BrainChip that is an Australian registered company and this is just dead wrong, unbelievable!
Next week (22nd feb) ASX price sensitive coming out according to TECH.
What might be released before that maybe/hopefully?
Yak52
sorry wanted to insert image (JPEG) of the email mentioned above but cannot seem to download pics from my desktop. ??
Bravo
If ARM was an arm, BRN would be its biceps💪!
You could change your handle to resident "Linkedin Sherlock "
Or "Linkroot" because it has certain ring to it.
Colorado23
Regular
Surely they can only be talking about one thing!!!!
Mazewolf
Regular
At what stage of the adoption of a neuromorphic SNN technology do non-disclosure agreements have a cost benefit ratio less than one? What are some critical milestones that need to be met before the use of new technology becomes a positive selling point for adopters?
chatgpt: 'Non-disclosure agreements (NDAs) are typically used in the early stages of technology development to protect intellectual property, trade secrets, and other confidential information. As the technology moves closer to commercialization, the cost-benefit ratio of NDAs may decrease, as companies need to share information with potential partners and customers to generate interest and secure funding.
In the case of neuromorphic SNN technology, critical milestones that need to be met before the use of the new technology becomes a positive selling point for adopters include:
Not a bad response I thought!
chatgpt: 'Non-disclosure agreements (NDAs) are typically used in the early stages of technology development to protect intellectual property, trade secrets, and other confidential information. As the technology moves closer to commercialization, the cost-benefit ratio of NDAs may decrease, as companies need to share information with potential partners and customers to generate interest and secure funding.
In the case of neuromorphic SNN technology, critical milestones that need to be met before the use of the new technology becomes a positive selling point for adopters include:
- Demonstrated performance: The technology needs to be shown to work reliably and effectively in a range of applications.
- Scalability: The technology needs to be scalable to meet the needs of large-scale applications.
- User-friendly interface: The technology needs to have a user-friendly interface that allows non-experts to easily use and integrate the technology into their systems.
- Cost-effectiveness: The technology needs to be cost-effective, both in terms of the hardware and software required to implement it and in terms of the time and effort required to learn and use the technology.
- Regulatory compliance: The technology needs to comply with relevant regulations, including those related to safety, privacy, and data protection.
Not a bad response I thought!
Taproot
Regular
And just for you, there was even an " Infineon " in there as well.Or "Linkroot" because it has certain ring to it.
Yoda
Regular
That's a great response from Tony Dawe, there's a lot to be encouraged about in that response which you've rightly pointed outFirst post here about anything for a long time. No promises I get it right ok.
But I thought I would share a few points highlighted in the following letter. This letter we have all seen before back in early Feb 2023 from a poster here, where Rob replies with some valuable points to consider!
Sections are extracted below.
--------------------------------------------------------------------------------------------------------------------
Investor Relations - IR Brainchip Inc. < ir@brainchip.com> Thurs 2 Feb 2023
Thank you for your email and support of Brainchip.
.............
Although you can't see it in the 4C reports there is a huge amount of work being done to secure commercial bookings and this work is increasing as we continue to add new people in key roles within our sales team, both in the Us and in key global markets. The other thing that is not visible in the 4C reports is the focus we have on developing new products to meet the diverse and growing requirments of customers. As you will have noted, we have recently announced the tapeout of akida 1500, which is a variant of the Akida 1000 and was developed because of direct engagement with our customers. We are also working on the release of our next generation chip, Akida2000 later this year which we believe will appeal to many customers.
In conclusion, while I hear your comments and note your fustration with the time its taking for us to deliver on our promise, I would counsel that you be patient and give us more time. the only thing that has happened in the past 12 months is that we've become a much stronger and more focused company and our technology has become better known and understood by the market. It's only a matter of time before that translated into commercial success.
Tony Dawe
Director Global Investor Relations
.............................................................................................................................................
OK.
1. they are securing commercial bookings - (getting in front of potential customers.)
2. developing new products to meet the growing requirements of customers - (positive interaction on product development with customers)
3.recent announcement of AKIDA 1500 - (we are all aware of this and WHY Akida 1500 is being taped out and by WHOM)
4. (Akida 1500) was developed because of DIRECT engagement with customers - ( again direct engagement with customers)
5. RELEASE OF OUR NEXT GENERATION CHIP , AKIDA 2000.........LATER THIS YEAR - (AKIDA 2000 being released in 2023)
6. matter of time before all this translates into commercial success - ( strong words, to make a promise like this -ie: give it time & there will be commercial success)
the only problem I see is the lack of engaging the Australian (and world) Stock markets and thereby BRN shareholders and potential NEW shareholders on the ASX with any form of company update regarding these factors.
The average Australian shareholder/investor knows nothing about this and really anything about BrainChip at all. The ASX is a dead space for researching info about BrainChip that is an Australian registered company and this is just dead wrong, unbelievable!
Next week (22nd feb) ASX price sensitive coming out according to TECH.
What might be released before that maybe/hopefully?
Yak52
sorry wanted to insert image (JPEG) of the email mentioned above but cannot seem to download pics from my desktop. ??
I'm sure it will turn out happily ever after because the Prophesee glass slipper fits Akida like a glove.Brainchip stays at home alone is that what you mean?
But why?
... but does their motor work?Traditional manufacturers are much more advanced than Tesla. After Mercedes, it is BMW Group's turn to start automatic valet in collaboration with Valeo. This offers a turnkey ecosystem to facilitate the automation of connected parking. Read it up
https://lnkd.in/eP3-49rG
The Bavarian brand, which was overtaken by Mercedes in level 3 driving and level 4 fully automated parking, wants to catch up. And the key technology partner will be Valeo.
I repeat Bavarian!!!
View attachment 29804
BMW accélère dans la conduite automatisée
La marque bavaroise, qui a été devancée par Mercedes pour la conduite de niveau 3 et pour le stationnement entièrement automatisé de niveau 4, entend bien rattraper le retard. Et le partenaire technologique de référence sera Valeo.www.autonews.fr
JK200SX
Regular
I've spent a bit of time going through the products on the EmbeddedWorldGermany website and identified the ones that have something to do with AI / edge AI applications. Many of the products seem to be using Hailo, but it would be interesting to see what everyone elses take is on these products and which may contain AKIDA.
Hi Yak,First post here about anything for a long time. No promises I get it right ok.
But I thought I would share a few points highlighted in the following letter. This letter we have all seen before back in early Feb 2023 from a poster here, where Rob replies with some valuable points to consider!
Sections are extracted below.
--------------------------------------------------------------------------------------------------------------------
Investor Relations - IR Brainchip Inc. < ir@brainchip.com> Thurs 2 Feb 2023
Thank you for your email and support of Brainchip.
.............
Although you can't see it in the 4C reports there is a huge amount of work being done to secure commercial bookings and this work is increasing as we continue to add new people in key roles within our sales team, both in the Us and in key global markets. The other thing that is not visible in the 4C reports is the focus we have on developing new products to meet the diverse and growing requirments of customers. As you will have noted, we have recently announced the tapeout of akida 1500, which is a variant of the Akida 1000 and was developed because of direct engagement with our customers. We are also working on the release of our next generation chip, Akida2000 later this year which we believe will appeal to many customers.
In conclusion, while I hear your comments and note your fustration with the time its taking for us to deliver on our promise, I would counsel that you be patient and give us more time. the only thing that has happened in the past 12 months is that we've become a much stronger and more focused company and our technology has become better known and understood by the market. It's only a matter of time before that translated into commercial success.
Tony Dawe
Director Global Investor Relations
.............................................................................................................................................
OK.
1. they are securing commercial bookings - (getting in front of potential customers.)
2. developing new products to meet the growing requirements of customers - (positive interaction on product development with customers)
3.recent announcement of AKIDA 1500 - (we are all aware of this and WHY Akida 1500 is being taped out and by WHOM)
4. (Akida 1500) was developed because of DIRECT engagement with customers - ( again direct engagement with customers)
5. RELEASE OF OUR NEXT GENERATION CHIP , AKIDA 2000.........LATER THIS YEAR - (AKIDA 2000 being released in 2023)
6. matter of time before all this translates into commercial success - ( strong words, to make a promise like this -ie: give it time & there will be commercial success)
the only problem I see is the lack of engaging the Australian (and world) Stock markets and thereby BRN shareholders and potential NEW shareholders on the ASX with any form of company update regarding these factors.
The average Australian shareholder/investor knows nothing about this and really anything about BrainChip at all. The ASX is a dead space for researching info about BrainChip that is an Australian registered company and this is just dead wrong, unbelievable!
Next week (22nd feb) ASX price sensitive coming out according to TECH.
What might be released before that maybe/hopefully?
Yak52
sorry wanted to insert image (JPEG) of the email mentioned above but cannot seem to download pics from my desktop. ??
Welcome back (finished decontamination/quarantine/exorcism from the other place?).
What I gleaned from Tony's message and other information released by the company is that Akida 1500 is not the earlier planned Akida 1500 with LSTM/transformer. It is a pared down version of Akida 1000 without the ARM Cortex. This has a couple of advantages including not having to pay the ARM licence, and a smaller silicon footprint so more chips per wafer.
Also it is being produced in Global Foundries' 22 nm FD-SoI. Coincidentally a new NASA SBIR was released calling for a NN design in 22 nm FD-SoI and without the encumbrance of a processor.
The lack of a processor means it is designed to work as an accelerator with another CPU/GPU which can be programmed to configure the Akida NN.
Another peripherally relevant matter is that there was a recent announcement that NASA was looking favourably on SiFive/RISC-V processors, and they are our mates.
https://www.sifive.com/press/nasa-selects-sifive-and-makes-risc-v-the-go-to-ecosystem
September 06, 2022
NASA Makes RISC-V the Go-to Ecosystem for Future Space Missions
SiFive X280 delivers 100x increase in computational capability with leading power efficiency, fault tolerance, and compute flexibility to propel next-generation planetary and surface missionsSan Mateo, Calif., September 6, 2022 - SiFive, Inc., the founder and leader of RISC-V computing, today announced it is providing the core CPU for NASA’s next generation High-Performance Spaceflight Computing (HPSC) processor. HPSC is expected to be used in virtually every future space mission, from planetary exploration to lunar and Mars surface missions. HPSC will utilize a multiple SiFive® Intelligence™ X280 RISC-V vector core, with additional SiFive RISC-V cores, to deliver 100x the computational capability of today’s space computers. This massive increase in computing performance will help usher in new possibilities for a variety of mission elements such as autonomous rovers, vision processing, space flight, guidance systems, communications, and other applications.
Last edited:
Similar threads
