BRN Discussion Ongoing

[Townyj]

A refresher tweet from Brn.

Looks blank..

 

[Rise from the ashes]

Looks blank..

Weird I posted it here 19 mins ago but the tweet is younger than that
Got a screen saying that tweet was deleted. Must have been some typo or something in the body of the tweet that needed correction.

 

[Townyj]

Weird I posted it here 19 mins ago but the tweet is younger than that
Got a screen saying that tweet was deleted. Must have been some typo or something in the body of the tweet that needed correction.

Hahah.. maybe your in the future some how...

 

[Townyj]

Race 6 horse 4 2:30 tomorrow randwick. Go all in!
But in regards to that tweet it will be very very interesting to see some benchmarking.

You don't happen to be part owner in said horse..??

Yeah i am keen to see how it fares against the competition.. Akida that is!

 

[IloveLamp]

Mercedes-Benz Media

Exklusive Einblicke und individuelle Angebote: Erleben Sie mit Mercedes-Benz das Maximum aus digitaler Live-PR. Exclusive insights and individual offers: Experience the maximum of digital live PR with Mercedes-Benz.

mb4.me

 

[supersonic001]

Sign Up | LinkedIn

500 million+ members | Manage your professional identity. Build and engage with your professional network. Access knowledge, insights and opportunities.

www.linkedin.com

 

[Esq.111]

Morning Chippers,

Just looking at the daily news articles on Google....found this short clip which is amazing.

Google > Ameca expressions with GPT3 / 4.

YouTube. Engineered Arts . 3d.

* Might just be me but the voice of the interviewer sounds very much like... Simon Thorpe.??..
* Requires a savey chipper to post link, thanks in advance.

Regards,
Esq.

 

[Esq.111]

Morning Rise,

Bingo.

Regards,
Esq.

 

[Pmel]

Airbus employee post.

 

[GazDix]

Airbus employee post.

Nice find. I thought there was a connection there.
Here is Edge Impulse's point of view:

 

[chef]

"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."


All right - so now you have my attention:

Qualcomm:
WO2023049655A1 TRANSFORMER-BASED ARCHITECTURE FOR TRANSFORM CODING OF MEDIA 2021-09-27

[This is so hot off the press, the ink isn't dry ... 2023-03-30 ... and the specification is not available on line via Espacenet, but you may find it at google Patents]

Systems and techniques are described herein for processing media data using a neural network system. For instance, a process can include obtaining a latent representation of a frame of encoded image data and generating, by a plurality of decoder transformer layers of a decoder sub-network using the latent representation of the frame of encoded image data as input, a frame of decoded image data. At least one decoder transformer layer of the plurality of decoder transformer layers includes: one or more transformer blocks for generating one or more patches of features and determine self-attention locally within one or more window partitions and shifted window partitions applied over the one or more patches; and a patch un-merging engine for decreasing a respective size of each patch of the one or more patches.



View attachment 33566


Does this not sound a bit like our ViT/TENNs of Gen2?


https://brainchip.com/brainchip-introduces-second-generation-akida-platform/

The second-generation of Akida now includes Temporal Event Based Neural Nets (TENN) spatial-temporal convolutions that supercharge the processing of raw time-continuous streaming data, such as video analytics, target tracking, audio classification, analysis of MRI and CT scans for vital signs prediction, and time series analytics used in forecasting, and predictive maintenance. These capabilities are critically needed in industrial, automotive, digital health, smart home and smart city applications. The TENNs allow for radically simpler implementations by consuming raw data directly from sensors – drastically reduces model size and operations performed, while maintaining very high accuracy. This can shrink design cycles and dramatically lower the cost of development.
Another addition to the second generation of Akida is Vision Transformers (ViT) acceleration, a leading edge neural network that has been shown to perform extremely well on various computer vision tasks, such as image classification, object detection, and semantic segmentation. This powerful acceleration, combined with Akida’s ability to process multiple layers simultaneously and hardware support for skip connections, allows it to self-manage the execution of complex networks like RESNET-50 completely in the neural processor without CPU intervention and minimizes system load.

... but remember what Ella says.

i don't get it can you please explain why this is exciting? a potential competitor realeses a patent of a "similar" way to process data. what should BC profit of? I would say QC is a even harder competitor now, no?

 

[stuart888]

@Townyj

Thanks Rise for the heads up. Looking forward to this benchmarking! The momentum of the Brainchip low power smarts is trending nicely!

I searched for: low power edge tinyml benchmarking best practices. Lots of info on this, deep stuff.

The Brainchip team will put it in a format that everyone will understand. Should be awesome.

https://www.wevolver.com/article/the-art-and-science-of-benchmarking-neural-network-architectures

The variety of available neural network architectures, configurations, and performance-related parameters makes it challenging to compare alternative ML/DL products and services. To facilitate this, engineers often turn to proven benchmarks for compute intense and data intense systems. For example:

• The Standard Performance Evaluation Corporation (SPEC) family of benchmarks focuses on computational workloads over different computing architectures including cloud-based systems.
• The LINPACK Benchmarks provide measures of a computer’s floating-point rate of execution i.e., they focus on floating-point computing power.
• The TPC consortium includes industry leaders in computing systems and datasets, which have provided a suite of benchmarks for stress testing the transaction processing and data warehousing capabilities of data intensive systems.
• The High Performance Conjugate Gradients (HPCG) benchmark provides novel metrics that enable the evaluation and ranking of High Performance Computing (HPC) systems.

These benchmarks aid in evaluating different components of ML/DL systems, which are typically deployed over computationally intensive platforms. However, they are overly focused on conventional computational workloads and hence not sufficient for training and executing deep learning tasks that are typically more complex.

 

[SharesForBrekky]

"Amazon Web Services has bought the right to draw down 51 megawatts of electricity from the power grid from Mercury Energy to power data centres it is building in New Zealand.

The 15-year power deal will allow Amazon’s cloud computing arm to consume the equivalent of about 0.5% of the country’s current total installed generating capacity."

Stuff

i.stuff.co.nz

 

[TheFunkMachine]

Question to Chat Gp3:
Who do you think is the leading company providing neuromorphic IP technology today and why ?

As an AI language model, I do not have personal opinions. However, based on industry reports and analysis, one of the leading companies providing neuromorphic IP technology today is BrainChip Inc. Their Akida™ Neuromorphic System-on-Chip (NSoC) is capable of processing data in a massively parallel fashion, which significantly reduces power consumption and increases speed compared to traditional computing methods. This technology has applications in various fields, including edge computing, autonomous vehicles, and smart homes. Additionally, BrainChip has a strong partnership with Socionext, a global semiconductor design and manufacturing company, to enhance the scalability and accessibility of their technology.

 

[HopalongPetrovski]

Position requires a PhD in artificial intelligence yet it pays $28 an hour.
The US is fucked.

It’s ok old chap, they live on the chips………. errrr tips.

 

[Tothemoon24]

Gee it’s been quiet in here the last few days , don’t tell me some of you have been made to sign NDA’s

 

[RobjHunt]

Gee it’s be quiet in here the last few days , don’t tell me some of you have been made to sign NDA’s

Some have just been Pantenely waiting

 

[HopalongPetrovski]

Gee it’s be quiet in here the last few days , don’t tell me some of you have been made to sign NDA’s

Just been busy in confo meetings about the various colour schemes and numbers of cup holders in our lambo’s and EQ’s on order so we don’t clash at the AGM and the advisability of swimming pools on yachts? The big question of course is, does one stock them with sturgeon or simply have the caviar flown in fresh daily?

 

[Tothemoon24]

Incoming Ann !!

 

[Shadow59]

Incoming Ann !!

Expiring options