stuart888
Regular
Needs some explanation. Help! I missed it. I subscribe (me and 35 others) and saw it earlier today.
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Needs some explanation. Help! I missed it. I subscribe (me and 35 others) and saw it earlier today.
stuart888
Regular
Below, the Telsa Chief Artificial Intelligence superstar, explains how they are transitioning all aspects to Neomorphic Software Solutions. He talks about all the C++ code that now is migrating to the weights of the Spiking Neomorphic Model. 
It just boosts and backs the entire Brainchip SNN focus. It is super to hear the brightest and best explain software's future.
Brainchip is on the right path!
It just boosts and backs the entire Brainchip SNN focus. It is super to hear the brightest and best explain software's future.
Brainchip is on the right path!
Brainchip's continued growth is this growth-rocket field is fascinating.
This is a nicely done IBM presentation on an important concept. I am not sure 90 days ago if I had ever heard of: Generative AI.
8 minutes, no commercials.
What are Generative AI models?
Nice. What is really impressive is how great she can write backwards so that we can read it.....
stuart888
Regular
Just thinking about Brainchip boosting. It is on the open web, the ChatGPT version 4x, 5x crawlers will eat the text!
This text goes into the next version of ChatGBT.
Everything we are posting to help build the smarts of humanity!
I like it myself.
There are some smart people here! The knowledge shared will help future generations.
This text goes into the next version of ChatGBT.
Everything we are posting to help build the smarts of humanity!
I like it myself.There are some smart people here! The knowledge shared will help future generations.
DJM263
LTH - 2015
I always get my "e" backwards when I try to write them backwardsNice. What is really impressive is how great she can write backwards so that we can read it.....
ndefries
Regular
Shhh we are trying to think
Damo4
Regular
mrgds
Regular
Just watching ASX - OLY ................. announcement regarding a "farm in agreement "
................. be like BRN announcing a "partnership agreement " ................... I WISH
PANTENE............... OUR DAY WILL COME
AKIDA BALLISTA
HopalongPetrovski
I'm Spartacus!
We were all having a meeting trying to decide if you should be declared our new social club president!
It would mean you have to burst forth from a cake, naked at the AGM and serenade Sean into doing a demonstration Tango, followed by individual lap dances for each of the other members of the board.
Up for it?
We are all waiting for the companies CFO to release information confirming that LDA Capital have deposited
"our funds into our account".
It was announced when we entered into the last of our obligations back in January, so I expect confirmation that it's
all been closed successfully...before the middle of April 2023.
Tech
"our funds into our account".
It was announced when we entered into the last of our obligations back in January, so I expect confirmation that it's
all been closed successfully...before the middle of April 2023.
Tech
Bravo
If ARM was an arm, BRN would be its biceps💪!
Wait! I found something!!!!
This was published online 2 hours ago.
You can't have a truly intelligent Connected Intelligent Edge IMO without AKIDA so I don't know what to think.
15
SOCIAL BUZZ
Qualcomm flaunts its ability in AI and Connected Intelligent EdgeSource: Shutterstock
He meant that Qualcomm’s mobile heritage and DNA put the company in “an incredible position to provide high-performance, low-power computing, on-device intelligence, all wireless technologies, and leadership across AI processing and connectivity and camera graphics and sensors.” For Qualcomm, Amon sees this as an opportunity to engage a US$700 billion addressable market in the next decade.
Fast forward to today, Qualcomm, as part of its ongoing campaign, “The Edge of Possible,” highlighted the significance of driving edge computing innovations to transform industries, power new consumer experiences, and fuel the growth of the digital economy. In a media briefing held in Kuala Lumpur on March 29, Qualcomm shared its progress in the space.
In terms of sector, for instance, Connected Intelligent Edge devices monitor patients in real-time, like tracking a patient’s vital signs, such as blood pressure and heart rate, and send the information to healthcare providers in real-time. This method allows medical professionals to identify issues and take appropriate action quickly.
In transportation, Connected Intelligent Edge devices are used to make vehicles safer and more efficient. “For example, sensors placed throughout a car can monitor its performance and provide real-time data to the driver, alerting them to any issues. The information can help prevent accidents and improve fuel efficiency, reducing costs and environmental impact,” Lim told the press during the briefing.
From a client’s perspective, Malaysia’s telco provider YTL Communications shared how Qualcomm’s Connected Intelligent Edge devices have helped the company maintain a seamless operation. “We are fortunate to have been given early access to a Connected Intelligent Edge device known as the AI Box by Qualcomm to be deployed in our building,” CEO Wing K Lee shared.
The AI Box is an intelligent edge device that supports traditional IP camera video streams to be offloaded and processed via the box — powered by system-on-chip (SOC) designed for high computing and high concurrency of machine learning-based analytics across multiple camera streams.
“With the AI box, we have applied localized processing intelligence from an analytics standpoint. The AI Box approach is aligned with the industry’s shift from video management software (VMS) to Video software as a service (VsaaS) implementation, enabling us to optimize our operations,” Lee noted.
Separately, Lim also shared how Qualcomm and Microsoft collaborated on Snapdragon to enable these new AI-accelerated experiences for Windows 11 — without impacting performance and power efficiency. “Instead, Snapdragon intelligently offloads these computationally intensive tasks to a dedicated AI engine, which frees up the CPU and GPU resources,” she said.
To top it off, adding on-device AI processing to powerful CPU and GPU capabilities adds the ability to offload compute-intensive processes. “As a result, performance is dramatically increased, delivering a higher user experience. Snapdragon computes platforms offer AI-accelerated user experiences to reach a new level of mobile computing performance,” Lim shared.
techwireasia.com
This was published online 2 hours ago.
You can't have a truly intelligent Connected Intelligent Edge IMO without AKIDA so I don't know what to think.
15
SOCIAL BUZZ
Qualcomm flaunts its ability in AI and Connected Intelligent EdgeSource: Shutterstock
Qualcomm flaunts its ability in AI and Connected Intelligent Edge
By Dashveenjit Kaur | 3 April, 2023
- A few months after Qualcomm shared how the company is driving the emergence of the Connected Intelligent Edge, the US chip designer shared further updates in a media briefing in Kuala Lumpur.
He meant that Qualcomm’s mobile heritage and DNA put the company in “an incredible position to provide high-performance, low-power computing, on-device intelligence, all wireless technologies, and leadership across AI processing and connectivity and camera graphics and sensors.” For Qualcomm, Amon sees this as an opportunity to engage a US$700 billion addressable market in the next decade.
ANDROID PHONE MAKERS AND QUALCOMM COLLABORATE TO ENABLE SATELLITE TEXT MESSAGING
Dashveenjit Kaur | 1 March, 2023Fast forward to today, Qualcomm, as part of its ongoing campaign, “The Edge of Possible,” highlighted the significance of driving edge computing innovations to transform industries, power new consumer experiences, and fuel the growth of the digital economy. In a media briefing held in Kuala Lumpur on March 29, Qualcomm shared its progress in the space.
Connected Intelligent Edge with Qualcomm
For starters, the Connected Intelligent Edge, according to Qualcomm, is the convergence of 5G networks, edge computing, and AI. “This integration allows data to be processed and analyzed in real time, allowing faster decision-making and response times. As a result, various industries, including manufacturing, transportation, and security, can use this technology,” said Alicia Lim, head of marketing for Qualcomm Southeast Asia.In terms of sector, for instance, Connected Intelligent Edge devices monitor patients in real-time, like tracking a patient’s vital signs, such as blood pressure and heart rate, and send the information to healthcare providers in real-time. This method allows medical professionals to identify issues and take appropriate action quickly.
In transportation, Connected Intelligent Edge devices are used to make vehicles safer and more efficient. “For example, sensors placed throughout a car can monitor its performance and provide real-time data to the driver, alerting them to any issues. The information can help prevent accidents and improve fuel efficiency, reducing costs and environmental impact,” Lim told the press during the briefing.
From a client’s perspective, Malaysia’s telco provider YTL Communications shared how Qualcomm’s Connected Intelligent Edge devices have helped the company maintain a seamless operation. “We are fortunate to have been given early access to a Connected Intelligent Edge device known as the AI Box by Qualcomm to be deployed in our building,” CEO Wing K Lee shared.
The AI Box is an intelligent edge device that supports traditional IP camera video streams to be offloaded and processed via the box — powered by system-on-chip (SOC) designed for high computing and high concurrency of machine learning-based analytics across multiple camera streams.
“With the AI box, we have applied localized processing intelligence from an analytics standpoint. The AI Box approach is aligned with the industry’s shift from video management software (VMS) to Video software as a service (VsaaS) implementation, enabling us to optimize our operations,” Lee noted.
Separately, Lim also shared how Qualcomm and Microsoft collaborated on Snapdragon to enable these new AI-accelerated experiences for Windows 11 — without impacting performance and power efficiency. “Instead, Snapdragon intelligently offloads these computationally intensive tasks to a dedicated AI engine, which frees up the CPU and GPU resources,” she said.
To top it off, adding on-device AI processing to powerful CPU and GPU capabilities adds the ability to offload compute-intensive processes. “As a result, performance is dramatically increased, delivering a higher user experience. Snapdragon computes platforms offer AI-accelerated user experiences to reach a new level of mobile computing performance,” Lim shared.
Qualcomm flaunts its ability in AI and Connected Intelligent Edge
During Qualcomm Investor Day in 2021, President and CEO Cristiano Amon shared how they are leading the realization of the "connected intelligent edge".
techwireasia.com
Last edited:
I'm in, not sure they will enjoy the sight of it and the experience of it. if however they do enjoy the sight and experience, I will be selling all shares instantly as I will know they are weirdly outrageous and not fit to run a bath let alone our wonderful company!!We were all having a meeting trying to decide if you should be declared our new social club president!
It would mean you have to burst forth from a cake, naked at the AGM and serenade Sean into doing a demonstration Tango, followed by individual lap dances for each of the other members of the board.
Up for it?
HopalongPetrovski
I'm Spartacus!
I was rather expecting that they wouldn’t enjoy it, and that we could hold it over their collective heads as an ongoing threat for the following AGM should we not all be BRN billionaires by then!
Sorta
and a stick thingamajig all rolled up in 1.
Bravo
If ARM was an arm, BRN would be its biceps💪!
We were all having a meeting trying to decide if you should be declared our new social club president!
It would mean you have to burst forth from a cake, naked at the AGM and serenade Sean into doing a demonstration Tango, followed by individual lap dances for each of the other members of the board.
Up for it?
Just checking who won the vote? I've been practicing pole dancing if that helps.
Bravo
If ARM was an arm, BRN would be its biceps💪!
Here's another article about Qualcomm's ‘connected intelligent edge’,
Share on FacebookShare on Twitter
Qualcomm might be more familiar to the world as the people behind the mobile processors powering your smartphone, but they actually do much more than that. Together with partners YTL Communications Sdn Bhd and Microsoft Malaysia, they showed off just part of what they’ve been working on in the artificial intelligence scene.
For starters, there’s the idea of the ‘connected intelligent edge’, a convergence of 5G networks, edge computing and AI. Essentially, it sees part of the AI computing done on a device level together, with data being processed and analysed in real time for faster decision making and response times. This has a number of use cases for multiple industries, which include security, transportation, manufacturing and more.
In healthcare for instance, devices on the connected intelligent edge can monitor patients in real time, allowing medical professionals to watch over them with data such as blood pressure and heart rate to provide better care. Doctors can also identify any possible issues and take appropriate action quickly. Meanwhile in transport, passenger cars now have sensors throughout, letting the driver monitor performance and check if there’s any issues with their car. This information can help prevent accidents, improve fuel efficiency and reduce overall costs.
Another industry undergoing change due to artificial intelligence is the security industry. Plenty of buildings and houses have closed circuit television surveillance cameras installed, but these are nothing more than cameras with a feed that requires others to watch them for any suspicious activity. With Qualcomm’s AI solutions however, it can improve CCTVs by having artificial intelligence help secure and safeguard your environment.
According to Qualcomm, this is possible due to three recent technology improvements. The first is that security cameras are now moving towards using 4K cameras rather than the older FHD resolution. The second is that modern security cameras now have increased compute capabilities now, while the third is that 5G allows for high bandwidth and low latency connections.
As such, Qualcomm sees a simple way to change up the security scene with the help of an AI box, which is basically an intelligent edge device that can be hooked up to security cameras. It then offloads the streams and processes it via the box, with AI helping to detect if there’s any suspicious activity around. It’s aligned with the security industry’s shift away from a standard video management system towards video software as a service.
YTL CEO Wing K. Lee added that this switch towards a smart CCTV system won’t require massive investment as it is built upon existing ‘dumb’ CCTV setups, and can provide real-time alert for faster action. Qualcomm also noted that they already have several chips such as the QS8250 and the QRB5165 that’ll fit this task, and they’re 5G-enabled too.
On top of that, Qualcomm highlighted their AI chips being in consumer laptops too. Windows laptops and devices running Snapdragon chips remain few and far between compared to regular x86 devices now, but Qualcomm notes that there are some advantages to switching to ARM-based chips with features such as always on, always connected laptops and faster boot times.
In particular, Qualcomm’s Snapdragon chips for Windows now pack AI chips in them too. Devices such as the Microsoft Surface Pro 9 can use this on-device AI for better video conferencing with tools such as background blur and noise suppression. These devices can also depend on the AI processor for better security and privacy, as well as offloading some CPU and GPU tasks to it for better battery life.
soyacincau.com
Qualcomm showcases what AI can do for computing, transport and security
Share on FacebookShare on Twitter
Qualcomm might be more familiar to the world as the people behind the mobile processors powering your smartphone, but they actually do much more than that. Together with partners YTL Communications Sdn Bhd and Microsoft Malaysia, they showed off just part of what they’ve been working on in the artificial intelligence scene.
For starters, there’s the idea of the ‘connected intelligent edge’, a convergence of 5G networks, edge computing and AI. Essentially, it sees part of the AI computing done on a device level together, with data being processed and analysed in real time for faster decision making and response times. This has a number of use cases for multiple industries, which include security, transportation, manufacturing and more.
In healthcare for instance, devices on the connected intelligent edge can monitor patients in real time, allowing medical professionals to watch over them with data such as blood pressure and heart rate to provide better care. Doctors can also identify any possible issues and take appropriate action quickly. Meanwhile in transport, passenger cars now have sensors throughout, letting the driver monitor performance and check if there’s any issues with their car. This information can help prevent accidents, improve fuel efficiency and reduce overall costs.
Another industry undergoing change due to artificial intelligence is the security industry. Plenty of buildings and houses have closed circuit television surveillance cameras installed, but these are nothing more than cameras with a feed that requires others to watch them for any suspicious activity. With Qualcomm’s AI solutions however, it can improve CCTVs by having artificial intelligence help secure and safeguard your environment.
According to Qualcomm, this is possible due to three recent technology improvements. The first is that security cameras are now moving towards using 4K cameras rather than the older FHD resolution. The second is that modern security cameras now have increased compute capabilities now, while the third is that 5G allows for high bandwidth and low latency connections.
As such, Qualcomm sees a simple way to change up the security scene with the help of an AI box, which is basically an intelligent edge device that can be hooked up to security cameras. It then offloads the streams and processes it via the box, with AI helping to detect if there’s any suspicious activity around. It’s aligned with the security industry’s shift away from a standard video management system towards video software as a service.
YTL CEO Wing K. Lee added that this switch towards a smart CCTV system won’t require massive investment as it is built upon existing ‘dumb’ CCTV setups, and can provide real-time alert for faster action. Qualcomm also noted that they already have several chips such as the QS8250 and the QRB5165 that’ll fit this task, and they’re 5G-enabled too.
On top of that, Qualcomm highlighted their AI chips being in consumer laptops too. Windows laptops and devices running Snapdragon chips remain few and far between compared to regular x86 devices now, but Qualcomm notes that there are some advantages to switching to ARM-based chips with features such as always on, always connected laptops and faster boot times.
In particular, Qualcomm’s Snapdragon chips for Windows now pack AI chips in them too. Devices such as the Microsoft Surface Pro 9 can use this on-device AI for better video conferencing with tools such as background blur and noise suppression. These devices can also depend on the AI processor for better security and privacy, as well as offloading some CPU and GPU tasks to it for better battery life.
Qualcomm showcases what AI can do for computing, transport and security - SoyaCincau
Qualcomm has shared the latest in their work on artificial intelligence, highlighting the use cases AI devices have in several industries ranging from healthcare to security.
soyacincau.com
Bravo
If ARM was an arm, BRN would be its biceps💪!
Micro tile inferencing....So this is how Qualcomm are reducing their power consumption?
"The company also announced a new technology called micro tile inferencing, which breaks a neural network into many small pieces so that it can be processed all at once, rather than layer by layer, and very efficiently, saving a great deal of power."
March 7, 2023 6:20 AM
Image Credit: Adobe Images
Presented by Qualcomm Technologies, Inc.
To data scientists, the raw potential of AI and complex neural networks was clear from the start, or close to it. But it’s only in the past five years that device hardware has become sophisticated enough to make good on the full promise, and bring AI all the way to the edge. On-device AI is what makes AI a reality for the consumers. And now devices of every size, even with lower battery capacity, are able to handle powerful, power-efficient on-device neural networks. It’s the evolution of computing from the cloud, taking inferencing right to the source.
“We’ve spent almost a decade of research on how to make AI work best on the edge,” says Ziad Asghar, senior vice president of product management, Qualcomm Technologies, Inc. “From that, we’ve developed hardware that’s able to do more inferencing for any given amount of power, and AI software stack (Qualcomm AI Stack) and tools to bring the Connected Intelligent Edge to life.”
On the consumer-facing side, use cases embrace everything from smartphones, XR, compute and earbuds to connected intelligent vehicles and smart homes. On the business side, they support digital transformation in the industrial and manufacturing space, connected healthcare and a leap ahead for the AI software tools and platforms companies need to stay competitive in a rapidly changing environment.
Asghar describes the Connected Intelligent Edge itself as a network with multiple nodes, or different products, within it — and many of the new possibilities lie in these device clouds. In a smart home, for example, that might include security cameras, the cars in the garage, appliances, PCs, mobile devices and tablets, all with some amount of AI processing capability.
Those security cameras might recognize a family member in order to open up the smart lock at the front door and activate environmental controls. But the Connected Intelligent Edge also disseminates AI across the whole network, so that use cases are handled with the best accuracy with the best power consumption. If there’s not enough processing power on one product, it can be handed up the line to a more powerful device.
For instance, a security camera shifting a possible false alarm to the unit that can handle anomalies and more complex incidents. The data never leaves the device or local network, so that privacy is assured. And handling latency-sensitive use cases on the device means real-time results, and a a better consumer experience.
That means more processing for any given amount of power. It also means the ability to write software quickly and get to a product quicker, because time to market is key. At the same time, developers need the flexibility of using AI frameworks they’re familiar with, and tools to optimize and improve performance even further. On the hardware side, Qualcomm offers the Hexagon processor with three accelerators (scalar, vector and tensor) that allow a developer to go from mapping directly to how a neural network is set up all the way to the fully connected layer.
At the most recent Snapdragon Summit, Qualcomm had several significant AI announcements, among them, considerable hardware improvements, including an upgrade of Snapdragon 8 Gen 2 AI performance by a factor up to 4.35x. It’s the first commercial design on the edge that can do integer 4-bit (INT4) AI inferencing, which means the same calculations take far fewer bits, and expend significantly less energy while maintaining accuracy.
The company also announced a new technology called micro tile inferencing, which breaks a neural network into many small pieces so that it can be processed all at once, rather than layer by layer, and very efficiently, saving a great deal of power.
And just before MWC, the company announced that it was able to run Stable Diffusion, a text-to-image AI model on a reference device powered by Snapdragon 8 Gen 2. Typically, generating images using Stable Diffusion requires vast amounts of computing power in the cloud but thanks to Qualcomm Technologies’ AI research and the power of on-device AI on the Snapdragon 8 Gen 2, they were able to not only optimize, quantize and deploy these large models using Qualcomm AI Stack onto the device but they were able to run these models in a matter of seconds. This is a significant leap from current capabilities and will allow massive AI models to run locally on devices which means better convenience, power savings, security and more.
But, Asghar says, having great hardware for AI isn’t enough. As the company continues to optimize its hardware, they’ve focused on leveling up software and tools at the same time. For instance, a loss in accuracy has historically been a primary challenge behind reducing a network running at 32-bit floating point down to four bits. Now the Qualcomm AI Studio provides the tools necessary to maintain precision even at integer INT, reducing the power by a factor of 64 and exponentially increasing the number of neural networks that can be run in the same power envelope. This is critical to do AI processing at the edge.
“The huge benefit to the Qualcomm AI Stack is enabling people to use Qualcomm technology easily and effectively without having to do a lot of setup work,” he explains. “Now I can take a mobile model to a security camera application without having to do new work. Why? Because it’s the same AI stack across all of our products. It’s really the notion of create once, and then take it anywhere.”
The Qualcomm AI stack supports popular AI frameworks and runtimes and offers developer libraries and services. The company has built SDKs for its product lines on top of this foundation — for example, Snapdragon Ride for automotive, Intelligent Multimedia SDK for IoT processing, Spaces (part of the Snapdragon Spaces XR Developer Platform for AR glasses) and more, including SDKs focused on specific verticals.
In Snapdragon Spaces, for example, Qualcomm has built AR-specific functions directly into the platform for hand and eye tracking for foveated rendering, 3D reconstruction of spaces, plane detection and more. A developer creating a new use case using AR or VR can pick up those routines and other pre-built pieces and build the final product on top, and get to a finished product faster.
The recently announced Qualcomm AI Studio brings together all the AI stack tools into a new GUI, along with visualization tools to simplify the developer experience — and provide the ability to see the complete model workflow from model design to optimization to deployment and profiling in action.
“If you’re doing anything at the edge, in a constrained power envelope or form factor, then really the best technology for you to bring it into production is based on Qualcomm,” he says. “With Qualcomm AI stack we want to make it as easy as possible for developers to be able to deploy their projects and get to market fast.”
venturebeat.com
"The company also announced a new technology called micro tile inferencing, which breaks a neural network into many small pieces so that it can be processed all at once, rather than layer by layer, and very efficiently, saving a great deal of power."
Unlocking unexpected new AI use cases with the Connected Intelligent Edge
March 7, 2023 6:20 AM
Image Credit: Adobe Images
Presented by Qualcomm Technologies, Inc.
To data scientists, the raw potential of AI and complex neural networks was clear from the start, or close to it. But it’s only in the past five years that device hardware has become sophisticated enough to make good on the full promise, and bring AI all the way to the edge. On-device AI is what makes AI a reality for the consumers. And now devices of every size, even with lower battery capacity, are able to handle powerful, power-efficient on-device neural networks. It’s the evolution of computing from the cloud, taking inferencing right to the source.
“We’ve spent almost a decade of research on how to make AI work best on the edge,” says Ziad Asghar, senior vice president of product management, Qualcomm Technologies, Inc. “From that, we’ve developed hardware that’s able to do more inferencing for any given amount of power, and AI software stack (Qualcomm AI Stack) and tools to bring the Connected Intelligent Edge to life.”
Leveling up AI use cases and unlocking new ones
AI use cases have made their way to devices already — AI enhanced pictures and videos, AI-based voice assistants, better sound and voice quality, real-time language translation, and more are significantly improved with connectivity and data processing, while numerous brand-new use cases are just starting to make themselves known across camera, gaming, sensors and connectivity, on all devices at the edge.On the consumer-facing side, use cases embrace everything from smartphones, XR, compute and earbuds to connected intelligent vehicles and smart homes. On the business side, they support digital transformation in the industrial and manufacturing space, connected healthcare and a leap ahead for the AI software tools and platforms companies need to stay competitive in a rapidly changing environment.
Asghar describes the Connected Intelligent Edge itself as a network with multiple nodes, or different products, within it — and many of the new possibilities lie in these device clouds. In a smart home, for example, that might include security cameras, the cars in the garage, appliances, PCs, mobile devices and tablets, all with some amount of AI processing capability.
Those security cameras might recognize a family member in order to open up the smart lock at the front door and activate environmental controls. But the Connected Intelligent Edge also disseminates AI across the whole network, so that use cases are handled with the best accuracy with the best power consumption. If there’s not enough processing power on one product, it can be handed up the line to a more powerful device.
For instance, a security camera shifting a possible false alarm to the unit that can handle anomalies and more complex incidents. The data never leaves the device or local network, so that privacy is assured. And handling latency-sensitive use cases on the device means real-time results, and a a better consumer experience.
Purpose-built AI hardware and developer tools
“From an AI developer perspective, they want a product that excels in terms of performance and in terms of power,” Asghar says. “Which means you want the best-in-class underlying hardware capability.”That means more processing for any given amount of power. It also means the ability to write software quickly and get to a product quicker, because time to market is key. At the same time, developers need the flexibility of using AI frameworks they’re familiar with, and tools to optimize and improve performance even further. On the hardware side, Qualcomm offers the Hexagon processor with three accelerators (scalar, vector and tensor) that allow a developer to go from mapping directly to how a neural network is set up all the way to the fully connected layer.
At the most recent Snapdragon Summit, Qualcomm had several significant AI announcements, among them, considerable hardware improvements, including an upgrade of Snapdragon 8 Gen 2 AI performance by a factor up to 4.35x. It’s the first commercial design on the edge that can do integer 4-bit (INT4) AI inferencing, which means the same calculations take far fewer bits, and expend significantly less energy while maintaining accuracy.
The company also announced a new technology called micro tile inferencing, which breaks a neural network into many small pieces so that it can be processed all at once, rather than layer by layer, and very efficiently, saving a great deal of power.
And just before MWC, the company announced that it was able to run Stable Diffusion, a text-to-image AI model on a reference device powered by Snapdragon 8 Gen 2. Typically, generating images using Stable Diffusion requires vast amounts of computing power in the cloud but thanks to Qualcomm Technologies’ AI research and the power of on-device AI on the Snapdragon 8 Gen 2, they were able to not only optimize, quantize and deploy these large models using Qualcomm AI Stack onto the device but they were able to run these models in a matter of seconds. This is a significant leap from current capabilities and will allow massive AI models to run locally on devices which means better convenience, power savings, security and more.
But, Asghar says, having great hardware for AI isn’t enough. As the company continues to optimize its hardware, they’ve focused on leveling up software and tools at the same time. For instance, a loss in accuracy has historically been a primary challenge behind reducing a network running at 32-bit floating point down to four bits. Now the Qualcomm AI Studio provides the tools necessary to maintain precision even at integer INT, reducing the power by a factor of 64 and exponentially increasing the number of neural networks that can be run in the same power envelope. This is critical to do AI processing at the edge.
“The huge benefit to the Qualcomm AI Stack is enabling people to use Qualcomm technology easily and effectively without having to do a lot of setup work,” he explains. “Now I can take a mobile model to a security camera application without having to do new work. Why? Because it’s the same AI stack across all of our products. It’s really the notion of create once, and then take it anywhere.”
The Qualcomm AI stack supports popular AI frameworks and runtimes and offers developer libraries and services. The company has built SDKs for its product lines on top of this foundation — for example, Snapdragon Ride for automotive, Intelligent Multimedia SDK for IoT processing, Spaces (part of the Snapdragon Spaces XR Developer Platform for AR glasses) and more, including SDKs focused on specific verticals.
In Snapdragon Spaces, for example, Qualcomm has built AR-specific functions directly into the platform for hand and eye tracking for foveated rendering, 3D reconstruction of spaces, plane detection and more. A developer creating a new use case using AR or VR can pick up those routines and other pre-built pieces and build the final product on top, and get to a finished product faster.
The recently announced Qualcomm AI Studio brings together all the AI stack tools into a new GUI, along with visualization tools to simplify the developer experience — and provide the ability to see the complete model workflow from model design to optimization to deployment and profiling in action.
“If you’re doing anything at the edge, in a constrained power envelope or form factor, then really the best technology for you to bring it into production is based on Qualcomm,” he says. “With Qualcomm AI stack we want to make it as easy as possible for developers to be able to deploy their projects and get to market fast.”
Unlocking unexpected new AI use cases with the Connected Intelligent Edge
Device hardware has now become sophisticated enough to make good on the full promise of AI, brining it all the way to the edge.
Fullmoonfever
Top 20
On Qualcomm fwiw...some prev posts on a couple of presentations they have done past year or so with outlines on what they up to, heading, edge and on device learning etc.
thestockexchange.com.au
thestockexchange.com.au
thestockexchange.com.au
thestockexchange.com.au
thestockexchange.com.au
BRN Discussion Ongoing
We are 100 % going to be part of Mercedes Benz, the worlds number 1 car marker . The rest will , follow the Leader . Some exciting quotes below https://www.autodaily.com.au/mercedes-rival-to-the-tesla-model-3-imagined/ Wow some sound dale's figures for our accountants to ponder over... Akida...
thestockexchange.com.au
BRN Discussion Ongoing
https://www.msn.com/en-au/news/techandscience/we-zoom-in-on-the-google-pixel-7-pro-e2-80-99s-camera/ar-AA12FVtc Gizmodo Australia FollowView Profile We Zoom In on the Google Pixel 7 Pro’s Camera Asha Barbaschow - 1h ago During Made By Google this morning, the search giant unveiled its new...
thestockexchange.com.au
BRN Discussion Ongoing
https://www.msn.com/en-au/news/techandscience/we-zoom-in-on-the-google-pixel-7-pro-e2-80-99s-camera/ar-AA12FVtc Gizmodo Australia FollowView Profile We Zoom In on the Google Pixel 7 Pro’s Camera Asha Barbaschow - 1h ago During Made By Google this morning, the search giant unveiled its new...
thestockexchange.com.au
BRN Discussion Ongoing
https://www.msn.com/en-au/news/techandscience/we-zoom-in-on-the-google-pixel-7-pro-e2-80-99s-camera/ar-AA12FVtc Gizmodo Australia FollowView Profile We Zoom In on the Google Pixel 7 Pro’s Camera Asha Barbaschow - 1h ago During Made By Google this morning, the search giant unveiled its new...
thestockexchange.com.au
BRN Discussion Ongoing
https://www.msn.com/en-au/news/techandscience/we-zoom-in-on-the-google-pixel-7-pro-e2-80-99s-camera/ar-AA12FVtc Gizmodo Australia FollowView Profile We Zoom In on the Google Pixel 7 Pro’s Camera Asha Barbaschow - 1h ago During Made By Google this morning, the search giant unveiled its new...
thestockexchange.com.au
rgupta
Regular
I was just thinking we know human brain is the smartest on this planet. But can we say with confidence that human is the smartest vision.
I assume all birds have better eyes than humans. Dragon fly eyes are 50000 times smarter than humans.
But on the other hand they don't have that smart brain. Does it mean they cannot process all the information they get or there is much less brain is required to get a fully functional eye.
I assume 2 million spikes may be less for human brain but could be sufficient for a dragon fly. Which means to make a best vision system we may require much less than what we think.
Dyor
I assume all birds have better eyes than humans. Dragon fly eyes are 50000 times smarter than humans.
But on the other hand they don't have that smart brain. Does it mean they cannot process all the information they get or there is much less brain is required to get a fully functional eye.
I assume 2 million spikes may be less for human brain but could be sufficient for a dragon fly. Which means to make a best vision system we may require much less than what we think.
Dyor
Similar threads
