BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
jtardif999
Regular
Not only did Dio but Nviso have made a stark comparison between the $50 Akida chip and the $30k Jetson Nano chip which uses almost 30 times more power and does not match Akida’s performance - let alone not be able to learn in real time,… and we are talking about AKD1000 tech, which apparently according to the commentator is a flop.IMO
This is the same person as shareman
Shareman also goes by the name pigsmightfly (name familiar with longtermers on other site)
It's quite clear why he keeps writing about Brainchip.
He has also compared akida with the jetson chip in the past which in my opinion was quite laughable .
I'm sure Dodgy knees has already compared these two pieces of Tech . Sharemans views are completly biased and without factual correctness.
Dozzaman1977
Regular
No change we are still in the asx200
Tothemoon24
Top 20
Nice little mention of the mighty chip
Edge computing is a potent platform for deploying foundational models in real-world applications. BrainChip's Akida processor is an advanced neural processing system for edge AI. And startups like Harvey are building co-pilots for lawyers, supercharging their workflows, and investing in systems that replicate best practices for establishing trust in knowledge work.
www.linkedin.com
Edge computing is a potent platform for deploying foundational models in real-world applications. BrainChip's Akida processor is an advanced neural processing system for edge AI. And startups like Harvey are building co-pilots for lawyers, supercharging their workflows, and investing in systems that replicate best practices for establishing trust in knowledge work.Gregory Renard on LinkedIn: frontiers, startups, 2023++
🚀 The future of technology is here, and AI is leading the way. ChatGPT and human-AI co-creation are just the beginning. In this article, you’ll explore the…
Good thing or not?
S
Straw
Guest
Yes?
From the info we have seen lately of the instos accumulating, you might assume that they knew we wouldn’t be kicked out of the 200
D
Deleted member 118
Guest
S
Straw
Guest
TheDrooben
Pretty Pretty Pretty Pretty Good
buena suerte :-)
BOB Bank of Brainchip
buena suerte :-)
BOB Bank of Brainchip
Labsy
Regular
Take home poinrs...
Lisa Su Saved AMD. Now She Wants Nvidia’s AI Crown
AMD's CEO orchestrated one of the great turnarounds in Silicon Valley history, driving the dying semiconductor maker's stock price up nearly 30-fold in less than a decade. Now she's preparing for battle in the coming AI revolution—and she expects to keep winning.www.forbes.com
“If you look out five years,” she says, “you will see AI in every single product at AMD, and it will be the largest growth driver.”
Dell do data centres. AMD power dell data centres. AMD say in 5 yrs every AMD chip will have AI.... do the maths and join some dots.
Boab
I wish I could paint like Vincent
Hi Ttm,Nice little mention of the mighty chip
Gregory Renard on LinkedIn: frontiers, startups, 2023++
🚀 The future of technology is here, and AI is leading the way. ChatGPT and human-AI co-creation are just the beginning. In this article, you’ll explore the…
It's worthwhile to check the credentials of Shyamal Anadkat from OpenAI (ChatGPT)
https://www.linkedin.com/in/zostale/
Read the full article to learn more: https://lnkd.in/gEN3NdXt
Bridging the gap between foundational models and their real-world applications, edge computing emerges as a potent platform for deploying these models, driving AI innovation to new frontiers. Earlier this year, Qualcomm AI Research successfully deployed a popular 1B+ parameter foundation model (stable diffusion) on an edge device through full-stack AI optimization. Edge AI is becoming essential due to its capability for real-time data processing, improved privacy, and enhanced security. It is becoming increasingly significant across various verticals due to the proliferation of devices with numerous sensors producing vast amounts of data. The complexity and resource demands of foundational models pose deployment challenges on edge devices. To counter this, the focus will shift toward specialized hardware, optimization techniques, and neural processor architectures. Being able to run optimized versions of foundational models at the edge/on-device will open up endless possibilities. Recognizing these emerging requirements, BrainChip has stepped forward with innovative solutions like the Akida processor, an advanced neural processing system for edge AI. It’s important to understand and assess edge AI technology to overcome deployment challenges and explore new potentials.
I wonder why he would mention a meme stock with coffee shop revenue, in imminent danger of being steamrolled by Nvidia, as the sole hardware AI processor chip in a sea of software AI applications?
Last edited:
Tothemoon24
Top 20
Hi Dio ,
Very impressive individual Shyamal Anadkat .
Dio in your opinion does the mighty chip have a place in edge data centres ? Or are we more on device .
Seems to be a fast growing industry
World Report Now - Unveiling New Technologies and the Power of Science
citylife.capetown
Akida can be used wherever sensor output classification is required.Hi Dio ,
Very impressive individual Shyamal Anadkat .
Dio in your opinion does the mighty chip have a place in edge data centres ? Or are we more on device .
Seems to be a fast growing industry
World Report Now - Unveiling New Technologies and the Power of Science
The principles underlying Akida can be used all the way up to the cloud.
BRN chose the edge because that was where there was the least competition and the largest potential market. The closer you get to the cloud, the smaller the potential market in terms of the number of chips.
So, yes, Dell edge servers are a candidate.
Late edition: In fact, with the problem of climate change, there should be a legislative requirement for Akida all the way through to the cloud.
Last edited:
Tothemoon24
Top 20
Cheers 
mate
mate
Frangipani
Regular
Drone detection prototypes involving neuromorphic event-based cameras are already being tested - a perfect future use case for Akida. The Canadian researchers in the article below used a DVXplorer event camera, after having previously experimented with a DAVIS 346 event camera, both made by Swiss company iniVation - see https://dl.acm.org/doi/pdf/10.1145/3546790.3546800 - published Sept 7, 2022. While we can practically exclude that Akida was used in the prototypes described, the Canadian researchers are concluding: “Moreover, we will continue to follow the improvement of neuromorphic hardware.” (taken from the just quoted PDF)
So in case of a possible collaboration between iniVation and Brainchip (that I had wondered about in a previous post, after noticing promotion of their new Aeveon sensor technology was not mentioning their former partner SynSense, while at the same time using images of a wallaby - of all animals - as illustration), a future event-based iniVation camera might well contain Akida.
Then of course there is Prophesee as another manufacturer of neuromorphic cameras that is already partnering with Brainchip. And lots of armed forces worldwide interested in this technology. I would be very surprised if Akida were ultimately not be taken into consideration for this type of drone detection.
Valcartier test range, Interconnect Bravo-Bravo basecamp. Credit: Michel Guitard, science visual documentation at DRDC.
Drones take up a lot of airspace around the world these days—filming movie scenes, delivering goods, gathering agricultural data, supporting search-and-rescue operations as well as conducting military surveillance, targeting and attack. Their sizes can range from small recreational units that fit into the palm of your hand to military drones weighing upwards of 600 kilograms. And the commercial drone market is expected to grow from over US$20 billion today to US$500 billion by 2028.
As their numbers surge, uncrewed aerial systems (UASs), commonly known as drones, will pose more hazards than ever, whether planned or unplanned. When photographing weddings and events, they could encroach on the public's privacy. While flying over airports, prisons or military facilities, they could compromise security. And in war zones, they can pose danger to lives, homes and infrastructure.
"Over the past year, we've seen a rapid evolution of UAS use on the battlefield in Ukraine," says Andrew Scheidl, Program Lead of the Multimedia Analytics Tools for Security program at the National Research Council of Canada (NRC). "Those developments will affect future deployments of the Canadian Armed Forces, but they will also migrate to other threat actors. Reliable detection and countermeasure systems will be increasingly important for military and public safety applications."
Autel Evo II FLIR drone. Credit: Michel Guitard, science visual documentation at DRDC.
In other high-profile incidents, the world has seen a drone crash onto the White House lawn, several circle around a nuclear power plant in France and others bomb a Ukrainian army weapons warehouse.
With the number of scenarios for illegal drone activities growing every day, the need for innovative drone-detection systems is intensifying. And in combat zones, having the ability to identify and counter enemy drones is particularly important.
A longstanding collaboration between the NRC and Defence Research and Development Canada (DRDC) sparked the development of a new approach to drone detection that disrupted the status quo, one that uses AI and classifies drones by their propeller speeds. The highly skilled team has brought all the necessary expertise to the table: optics, physics, signal processing, machine learning and vision, and neuromorphic systems.
Matrice 200 drone carrying NRC prototype visual frequency detection system that was tested at Interconnect Bravo-Bravo basecamp. Credit: Michel Guitard, science visual documentation at DRDC.
While several methods of detecting drones have been in use for a long time, none are totally dependable, particularly in dense urban areas and forests. This is because radio frequency, acoustic and optical detection systems can be misled by noise in complex environments and cause false or missed detections. For example, tall buildings and trees can with interfere with the ability of visible-light and infrared cameras to match the appearance of a live drone to images in a large database of UAS models. As well, while ground-based radars detect drones efficiently, their reliability can be affected by the environment and geography. Using these radar systems is also an expensive approach that requires bulky equipment and a lot of power. In addition, some of them transmit an active signal, thus exposing the devices.
Close-up Autel Evo II drone controller. Credit: Michel Guitard, science visual documentation at DRDC.
Over the past 4 years, an R&D team of engineers and scientists from the NRC's Digital Technologies Research Centre and the DRDC have developed an innovative technological solution for passively spotting drones in cluttered settings. It incorporates AI to accurately detect, track and characterize drones on the basis of the signal generated by their rotating propellers rather than by using an image bank. This method generates very few false alarms and accurately detects low-flying drones that use topography to evade discovery. The "signature" of a drone propeller can also be used to discriminate or classify aircraft by type, such as identifying it as a helicopter and not a drone.
The DRDC team initially lab-tested the feasibility of passive detection using drone characteristics. The next step was to develop energy-efficient detection algorithms and predict the performance of systems using different hardware. After some ground testing, the team built the first prototypes by combining the hardware and software and replacing some of the physical modelling of sensor responses with machine learning and AI technologies.
"Our results clearly disrupted the status quo, which depended on image banks to identify drones," says Guillaume Gagné, Defence Scientist at the DRDC Valcartier Research Centre. "The test showed that this lightweight technology can be housed in a small box, consume very little power and—most importantly—guarantee excellent accuracy in a visually congested environment."
While the technology is not yet scalable for commercial use, the multi-talented research team is working on modifications that will take it to the next level.
"We're developing the next generation of the prototype that has recently been tested in collaboration with the DRDC and the Canadian Armed Forces," says Marc-Antoine Drouin, Senior Research Officer with the NRC's Computer Vision and Graphics team. "We expect to double the detection range, add a radio link to communicate detection and connect the system to command and control software—allowing full integration into the drone-detection ecosystem." The tests will pinpoint missing features or limitations that need to be addressed before it can be market-ready.
This success aligns with the DRDC's mandate to develop technology in support of the CAF's operational needs. "We are crafting a road map for a multi-year project with the NRC's Digital Technologies Research Centre to continue advancing the current prototype using emerging approaches and technologies," adds Guillaume.
He also points out that the 3-year project builds on the collaboration between these two government entities that goes back more than 75 years. This history creates the ideal partnership to support national defence and align military and civil security. Their continuing inventiveness will contribute to Canada's national security well into the future.
For a more in-depth look at the research behind the story, read the team's recent article, A Virtual Fence for Drones: Efficiently Detecting Propeller Blades with a DVXplorer Event Camera.
Contact us
Media Relations, National Research Council of Canada
1-855-282-1637 (toll-free in Canada only)
1-613-991-1431 (elsewhere in North America)
001-613-991-1431 (international)
media@nrc-cnrc.gc.ca
Follow us on Twitter: @NRC_CNRC
———————————————————————————-
The above link is the article’s abstract and in turn links to the PDF that I referred to in my second paragraph:
So in case of a possible collaboration between iniVation and Brainchip (that I had wondered about in a previous post, after noticing promotion of their new Aeveon sensor technology was not mentioning their former partner SynSense, while at the same time using images of a wallaby - of all animals - as illustration), a future event-based iniVation camera might well contain Akida.
Then of course there is Prophesee as another manufacturer of neuromorphic cameras that is already partnering with Brainchip. And lots of armed forces worldwide interested in this technology. I would be very surprised if Akida were ultimately not be taken into consideration for this type of drone detection.
Eye on the sky: new drone detection technology advances national security
May 30, 2023 - Ottawa, Ontario
Valcartier test range, Interconnect Bravo-Bravo basecamp. Credit: Michel Guitard, science visual documentation at DRDC.
Drones take up a lot of airspace around the world these days—filming movie scenes, delivering goods, gathering agricultural data, supporting search-and-rescue operations as well as conducting military surveillance, targeting and attack. Their sizes can range from small recreational units that fit into the palm of your hand to military drones weighing upwards of 600 kilograms. And the commercial drone market is expected to grow from over US$20 billion today to US$500 billion by 2028.
As their numbers surge, uncrewed aerial systems (UASs), commonly known as drones, will pose more hazards than ever, whether planned or unplanned. When photographing weddings and events, they could encroach on the public's privacy. While flying over airports, prisons or military facilities, they could compromise security. And in war zones, they can pose danger to lives, homes and infrastructure.
"Over the past year, we've seen a rapid evolution of UAS use on the battlefield in Ukraine," says Andrew Scheidl, Program Lead of the Multimedia Analytics Tools for Security program at the National Research Council of Canada (NRC). "Those developments will affect future deployments of the Canadian Armed Forces, but they will also migrate to other threat actors. Reliable detection and countermeasure systems will be increasingly important for military and public safety applications."
Autel Evo II FLIR drone. Credit: Michel Guitard, science visual documentation at DRDC.
In other high-profile incidents, the world has seen a drone crash onto the White House lawn, several circle around a nuclear power plant in France and others bomb a Ukrainian army weapons warehouse.
With the number of scenarios for illegal drone activities growing every day, the need for innovative drone-detection systems is intensifying. And in combat zones, having the ability to identify and counter enemy drones is particularly important.
A longstanding collaboration between the NRC and Defence Research and Development Canada (DRDC) sparked the development of a new approach to drone detection that disrupted the status quo, one that uses AI and classifies drones by their propeller speeds. The highly skilled team has brought all the necessary expertise to the table: optics, physics, signal processing, machine learning and vision, and neuromorphic systems.
AI helps dodge the perils and pitfalls of drone detection
Matrice 200 drone carrying NRC prototype visual frequency detection system that was tested at Interconnect Bravo-Bravo basecamp. Credit: Michel Guitard, science visual documentation at DRDC.
While several methods of detecting drones have been in use for a long time, none are totally dependable, particularly in dense urban areas and forests. This is because radio frequency, acoustic and optical detection systems can be misled by noise in complex environments and cause false or missed detections. For example, tall buildings and trees can with interfere with the ability of visible-light and infrared cameras to match the appearance of a live drone to images in a large database of UAS models. As well, while ground-based radars detect drones efficiently, their reliability can be affected by the environment and geography. Using these radar systems is also an expensive approach that requires bulky equipment and a lot of power. In addition, some of them transmit an active signal, thus exposing the devices.
Close-up Autel Evo II drone controller. Credit: Michel Guitard, science visual documentation at DRDC.
Over the past 4 years, an R&D team of engineers and scientists from the NRC's Digital Technologies Research Centre and the DRDC have developed an innovative technological solution for passively spotting drones in cluttered settings. It incorporates AI to accurately detect, track and characterize drones on the basis of the signal generated by their rotating propellers rather than by using an image bank. This method generates very few false alarms and accurately detects low-flying drones that use topography to evade discovery. The "signature" of a drone propeller can also be used to discriminate or classify aircraft by type, such as identifying it as a helicopter and not a drone.
The DRDC team initially lab-tested the feasibility of passive detection using drone characteristics. The next step was to develop energy-efficient detection algorithms and predict the performance of systems using different hardware. After some ground testing, the team built the first prototypes by combining the hardware and software and replacing some of the physical modelling of sensor responses with machine learning and AI technologies.
Changing the drone-detection game
For a week in October 2022, the team assessed the first 2 prototypes at the Valcartier, Quebec, military base."Our results clearly disrupted the status quo, which depended on image banks to identify drones," says Guillaume Gagné, Defence Scientist at the DRDC Valcartier Research Centre. "The test showed that this lightweight technology can be housed in a small box, consume very little power and—most importantly—guarantee excellent accuracy in a visually congested environment."
While the technology is not yet scalable for commercial use, the multi-talented research team is working on modifications that will take it to the next level.
"We're developing the next generation of the prototype that has recently been tested in collaboration with the DRDC and the Canadian Armed Forces," says Marc-Antoine Drouin, Senior Research Officer with the NRC's Computer Vision and Graphics team. "We expect to double the detection range, add a radio link to communicate detection and connect the system to command and control software—allowing full integration into the drone-detection ecosystem." The tests will pinpoint missing features or limitations that need to be addressed before it can be market-ready.
This success aligns with the DRDC's mandate to develop technology in support of the CAF's operational needs. "We are crafting a road map for a multi-year project with the NRC's Digital Technologies Research Centre to continue advancing the current prototype using emerging approaches and technologies," adds Guillaume.
He also points out that the 3-year project builds on the collaboration between these two government entities that goes back more than 75 years. This history creates the ideal partnership to support national defence and align military and civil security. Their continuing inventiveness will contribute to Canada's national security well into the future.
For a more in-depth look at the research behind the story, read the team's recent article, A Virtual Fence for Drones: Efficiently Detecting Propeller Blades with a DVXplorer Event Camera.
Contact us
Media Relations, National Research Council of Canada
1-855-282-1637 (toll-free in Canada only)
1-613-991-1431 (elsewhere in North America)
001-613-991-1431 (international)
media@nrc-cnrc.gc.ca
Follow us on Twitter: @NRC_CNRC
———————————————————————————-
The above link is the article’s abstract and in turn links to the PDF that I referred to in my second paragraph:
Last edited:
Similar threads
