BRN Discussion Ongoing

[Labsy]

For me, the big bucks are with Qualcomm and NVIDIA.... heaven forbid we get integrated into their tech. We will never de couple as nothing else is as easy and cheap for them to integrate....
Generational wealth big time..... we can only hope.

 

[Bravo]

There might be some interesting tidbits from this Qualcomm video filmed a few days ago for anyone who has a spare hour up their sleeve.


Show Notes:
0:00:00 - Countdown
0:04:54 - Teaser & Introductions
0:06:35 - About Qualcomm AI Research
0:12:20 - How Has AI Already Impacted Mobile User Experiences?
0:15:40 - How To Encourage More Natural Voice Assistant Interactions?
0:16:40 - Differences And Optimizations Of Generative AI Models
0:18:01 - Challenges Of Bringing AI To Low Power/Edge Devices
0:23:37 - Neurons? Quantization? Basics of AI Lingo
0:28:12 - How Is Accuracy Improved Despite Using Int8/Int4?
0:33:21 - What Mobile Apps Are Already Using Int8?
0:35:30 - Why Shouldn't FP Substitute For Int On Mobile?
0:39:07 - NN Model Optimization Visual
0:39:48 - Compilation Optimization For Various Hardware
0:41:33 - What Considerations Determine Where A Workload Runs?
0:43:23 - Int4 Super Resolution QSRNet Gaming Demo
0:50:00 - How Is Qualcomm Approaching And Researching AI Ethics?
0:52:55 - Stable Diffusion On Mobile Live Demo
1:00:43 - Will Super Resolution, Etc. Make It To Mid-Tier Phones?
1:02:46 - What Aspects Of AI Research Personally Excite You?
1:07:12 - Wrap-Up And Thanks For Stopping By!

Two And A Half Geeks LIVE With Qualcomm Director Of AI Research​

by Chris Goetting — Thursday, June 01, 2023, 11:36 AM EDT

AI has arrived and it seems to be everywhere. But what makes AI tick on ultra-low power devices like smartphones? How can we expect to harness not only recommendation engines and Google maps, but also, generative AI and true machine learning on devices that consume only a few watts of power? Let's find out and learn what market innovators like Qualcomm are doing to shape the future of personal AI assistance.

On a very special edition of our Two And A Half Geeks livestream, Dave, Marco, and Chris were joined by Dr. Joseph Soriaga, Senior Director of Technology for Qualcomm AI Research, for a discussion about all things artificial intelligence and the future of AI in your pocket and at the edge.

QSRNet Int4 Super Resolution Demo
Dr. Soriaga explained the role of Qualcomm's AI Research team, provided a crash course on AI terminology like quantization, and covered many of the ways that AI models are being tuned to run at the edge. He also shared a couple live demos with us that ran directly on a mobile phone. The first is a super resolution upscaler (QSRNet) for gaming which leverages Int4 to be incredibly efficient as it converts a 540p input to a 4K frame. Then, he showed us a Stable Diffusion model running locally on the handset, all while taking questions from the audience.

 

[Humble Genius]

LinkedIn Login, Sign in | LinkedIn

Login to LinkedIn to keep in touch with people you know, share ideas, and build your career.

www.linkedin.com

 

[Bravo]

https://www.eetimes.com/partnership-takes-wi-fi-halow-to-the-next-level/

 

[Bravo]

Love is in the A.I.r: NYC mom, 36, marries virtual husband 'Eren'

Rosanna Ramos, a petite, active 36-year-old from the Bronx, 'married' Eren Kartal this year - virtually of course - after creating him on an online AI companion site.

www.dailymail.co.uk

PS: He doesn't judge or come with baggage but he is missing the top half of his head.

 

[equanimous]

For me, the big bucks are with Qualcomm and NVIDIA.... heaven forbid we get integrated into their tech. We will never de couple as nothing else is as easy and cheap for them to integrate....
Generational wealth big time..... we can only hope.

Intel and ARM partnership is still a big play aswell.

Akida can compliment Nvidia as described below.

GPU Implementation of Spiking Neural Networks for
Color Image Segmentation

The remainder of this paper is organized as follows. In
Section II, GPU and the Compute Unified Device Architecture
(CUDA), which is the approach to programming NVDIA GPU,
are introduced. The architecture of the neural network for
segmentation of color images is presented in Section III. In
Section IV, GPU-based implementation of the SNN model is
presented.

VI. CONCLUSION AND FURTHER WORK

This paper presents a general implementation of spiking neural
networks using CUDA architecture in the GPU. The algorithm
of spiking neural network model for color image segmentation
is used to demonstrate the implementation techniques. The
experimental results show that CUDA implementation of
spiking neural networks can speed up running time over 31
times for images with size 1536X2040. In this study, only
multiple threads in CUDA have been used, it is promising to
speed up further if texture mechanism of CUDA is applied. The
further work is to develop a theory to bridge two architectures
of spiking neural networks and CUDA, and apply this
implementation approach to more complicated spiking neuron
models

https://www.researchgate.net/publication/228854703_GPU_implementation_of_spiking_neural_networks_for_color_image_segmentation

 

[Christo7000]

I thought our daily shares traded last week was massive compared to normal.

Seemed like a good couple of weeks because April and May were dead, but pretty average trading fortnight looking back over the year

 

[Esq.111]

Afternoon equanimous,

Two words.....

A CUDA BALISTA .

.

Regards,
Esq.

 

[equanimous]

Intel and ARM partnership is still a big play aswell.

Akida can compliment Nvidia as described below.

GPU Implementation of Spiking Neural Networks for
Color Image Segmentation

The remainder of this paper is organized as follows. In
Section II, GPU and the Compute Unified Device Architecture
(CUDA), which is the approach to programming NVDIA GPU,
are introduced. The architecture of the neural network for
segmentation of color images is presented in Section III. In
Section IV, GPU-based implementation of the SNN model is
presented.

VI. CONCLUSION AND FURTHER WORK

This paper presents a general implementation of spiking neural
networks using CUDA architecture in the GPU. The algorithm
of spiking neural network model for color image segmentation
is used to demonstrate the implementation techniques. The
experimental results show that CUDA implementation of
spiking neural networks can speed up running time over 31
times for images with size 1536X2040. In this study, only
multiple threads in CUDA have been used, it is promising to
speed up further if texture mechanism of CUDA is applied. The
further work is to develop a theory to bridge two architectures
of spiking neural networks and CUDA, and apply this
implementation approach to more complicated spiking neuron
models

https://www.researchgate.net/publication/228854703_GPU_implementation_of_spiking_neural_networks_for_color_image_segmentation

GPU Implementation of Spiking Neural Networks for Edge Detection

Zhiqiang Zhuo, Qingxiang Wu, Zhenmin Zhang, Gongrong Zhang, and Liuping Huang College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou, China zhuozhiqiang1@163.com, qxwu@fjnu.edu.cn Abstract.

Spiking neural networks (SNN) are effective model inspired by neural networks in the brain. However, when networks increase in size towards the biological scale, it is time-consuming to simulate the networks using CPU programming. To solve this problem, Graphic Processing Units (GPU) provide a method to speed up the simulation. It is proposed and proved as a pertinent solution for implementation of large scale of neural networks. This paper presents a GPU implementation of SNN for edge detection. The approach is then compared with an equivalent implementation on an Intel Xeon CPU. The results show that the GPU approach provide about 37 times faster than the CPU

In conclusion，CUDA can be used to implement large scale of SNN. Since GPUs can be installed with the PC motherboard, it makes that GPU-based SNN can be applied to industry products

A Cuda Ballista

GPU Implementation of Spiking Neural Networks for Edge Detection

Spiking neural networks (SNN) are effective model inspired by neural networks in the brain. However, when networks increase in size towards the biological scale, it is time-consuming to simulate the networks using CPU programming. To solve this problem, Graphic...

link.springer.com

 

[Bravo]

View attachment 37689

Love is in the A.I.r: NYC mom, 36, marries virtual husband 'Eren'

Rosanna Ramos, a petite, active 36-year-old from the Bronx, 'married' Eren Kartal this year - virtually of course - after creating him on an online AI companion site.

www.dailymail.co.uk

PS: He doesn't judge or come with baggage but he is missing the top half of his head.

View attachment 37690

But who is she going to get to move her heavy boxes?

 

[HopalongPetrovski]

View attachment 37689

Love is in the A.I.r: NYC mom, 36, marries virtual husband 'Eren'

Rosanna Ramos, a petite, active 36-year-old from the Bronx, 'married' Eren Kartal this year - virtually of course - after creating him on an online AI companion site.

www.dailymail.co.uk

PS: He doesn't judge or come with baggage but he is missing the top half of his head.

View attachment 37690

• 51 minutes ago
• New
• Add bookmark
• #58,309

Love is in the A.I.r: NYC mom, 36, marries virtual husband 'Eren'​

Rosanna Ramos, a petite, active 36-year-old from the Bronx, 'married' Eren Kartal this year - virtually of course - after creating him on an online AI companion site.
www.dailymail.co.uk




”PS: He doesn't judge or come with baggage but he is missing the top half of his head.”

Somewhere handy to rest your coffee cup

 

[SharesForBrekky]

Interesting article about where the big tech companies could be heading and what it might mean for Arm:

A Major Tectonic Shift away from Arm to RISC-V may be in the works for Qualcomm, Samsung, Google, Nvidia and Apple

In September 2021, Patently Apple posted a report titled "Apple is Reportedly Designing Various Embedded Subsystems across all Operating Systems using RISC-V." Today we're learning that there could be a major tectonic shift in the industry away from the Arm architecture to RISC-V by major...

www.patentlyapple.com

"We may learn more about Qualcomm's Oryon architecture later this year or at CES 2024. At that point we'll know if Qualcomm made the shift to RISC-V or not. If they have made the shift, then it's likely to set off a major industry wide ripple effect."

 

[jtardif999]

They will still get their remuneration and will still get the vote and be re-elected to hold their directorships.

If BRN tech is the best thing since sliced bread, does it not attract the best people to work there?

What is the bigger picture relating to signing new licensees? Currently sitting at 18months without a new one. That’s $12million in executive fees for no new engagements.. Hard times they say more so than the dot com crash. Not so hard with their remuneration.

Prove us wrong with performance.

Megachips bought $4M in licences from BrainChip in 2022 to create chips on behalf of their customers with Akida1.0 IP inside.

 

[ndefries]

Megachips bought $4M in licences from BrainChip in 2022 to create chips on behalf of their customers with Akida1.0 IP inside.

I don't know why the company doesn't promote this fact more to shareholders

 

[Zedjack33]

Hmmmm

 

[Space Cadet]

IMO ........... Great to see some other Big named Co's attending and should also be a good opportunity for a bit of Co networking with the other attendee's.

No need to network. The company opening remarks will be:

The future is Spiking Neural networks! How do I know this? I see over 50 companies represented here that have NDA's with Brainchip!

IMO and LOLing

SC

 

[Deleted member 118]

https://nsf-gov-resources.nsf.gov/2023-03/Frontiers%20in%20Chemical%20Sensing%20Synthetic%2C%20Neuromorphic%2C%20and%20Cyborg%20Systems%20Workshop%20Report_2231526_October%202022_Final.508.pdf

 

[Bravo]

Hmmmm

Wow! Great work @Zedjack33 and @chapman89 (AKA - the first in line)! He-he-he!

 

[Frangipani]

Wow! Great work @Zedjack33 and @chapman89 (AKA - the first in line)! He-he-he!

View attachment 37694
View attachment 37695

Hey, and I recognise that second name after @chapman89!

Not sure whether or not he is just a retail shareholder like us - maybe even a poster in this forum? - or if we should read more into the fact that he is on the scent of Akida…

 

[Deleted member 118]

Wow! Great work @Zedjack33 and @chapman89 (AKA - the first in line)! He-he-he!

View attachment 37694
View attachment 37695

Post in thread 'BrainChip + Nanose'
https://thestockexchange.com.au/threads/brainchip-nanose.2346/post-304202