BRN Discussion Ongoing

Definitely the company Intel as you click and it takes to their page
I tried that, but it appears to be just an image for me..

Sounds more like an excited intern?..

Would be better, if it had the actual person saying it, as it sounds more like a personal comment.
 
  • Like
Reactions: 3 users

HopalongPetrovski

I'm Spartacus!
Yes - it's above my pay grade and very heavy going.

In speech recognition, in some cases, the speech must first be converted to text although, it is also possible to work with phonemes.

The processor needs to understand the nature of the words:
Nouns
Verbs
Adjectives
Adverbs
Prepositions
Conjunctions
Articles

... then to comprehend the context.

One problem is discovering how far back you need to go to find the correct context.

In written language, a lot of context would be found in a single sentence. A paragraph would capture a lot more context. But the context. In a book, it may be necessary to recall a chapter to descry the context.

In normal speech, the context should be close at hand (or ear), unless it is a familiar term.

LSTM, Transformers, and Attention, not to mention LLMs, have come along in quick succession.

This 2021 paper gives an inkling of the complexity:

Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognition
Priyabrata Karmakar, Shyh Wei Teng, Guojun Lu

https://arxiv.org/pdf/2102.07259.pdf

There have been several attempts to find the optimal Attention system:

TABLE I

DIFFERENT TYPES OF ATTENTION MECHANISM FOR AS
R

Name Short description

Global/Soft [10] At each decoder time step, all encoder hidden states are attended.

Local/Hard [23] At each decoder time step, a set of encoder hidden states (within a window) are attended.

Content-based [24] Attention calculated only using the content information of the encoder hidden states.

Location-based [25] Attention calculation depends only on the decoder states and not on the encoder hidden states.

Hybrid [11] Attention calculated using both content and location information.

Self [20] Attention calculated over different positions(or tokens) of a sequence itself.

2D [26] Attention calculated over both time-and frequency-domains.

Hard monotonic [27] At each decoder time step, only one encoder hidden state is attended.

Monotonic chunkwise [28] At each decoder time step, a chunk of encoder states (prior to and including the hidden state identified by the hard monotonic attention) are attended.

Adaptive monotonic chunkwise [29] At each decoder time step, the chunk of encoder hidden states to be attended is computed adaptively. models




This is a diagram of the configuration of a transformer-based encoder/decoder:


View attachment 57212
Unfortunately, the paper does not cover TeNNs.

It's getting to where there's only one chair left. Who will find a seat when the music stops?
Yikes!
I better rephrase my previous admonition to "I think I have a slight grasp of the basic concept as an abstract ideation" and thank God herself I am pretty. 🤣
 
  • Haha
  • Like
Reactions: 10 users

BrainShit

Regular
View attachment 57211


Wonder what they mean by more hmm

GlobalFoundries and Biden-Harris Administration Announce CHIPS and Science Act Funding for Essential Chip Manufacturing


So, Sam + ARM + Intel + Brainchip + ..... meeting @ 21.02.24 Convention Intel Foundry right? 😃
 
  • Like
  • Fire
  • Love
Reactions: 34 users

overpup

Regular
Something seems off about that job advertisement. You would pay more per hour for a freelancer in Poland or Ukraine for a web dev let alone finding someone with akida2 experience in the UK to work freelance for 3 to 6 months. Please correct me if I was reading this wrong?


If this is not wrong; is this the opposite to trashing a company for shorting purposes by seeding positivity?
30 bucks (or pounds maybe) an hour?
In London?!
 
  • Like
  • Love
Reactions: 4 users

Pmel

Regular
The first comment, @TTM in #77306 postet the screenshot, was "Looking forward with you connecting next week". This one was deleted? Now it shows "Can´t wait to hear more about your cutting-edge tech on Wednesday". ?

Senders slightly different.
2 different comments. One on Twitter and the other one on linkedin
 

Attachments

  • Screenshot_20240219_224358_LinkedIn.jpg
    Screenshot_20240219_224358_LinkedIn.jpg
    748.8 KB · Views: 166
  • Screenshot_20240219_224315_Chrome.jpg
    Screenshot_20240219_224315_Chrome.jpg
    633.3 KB · Views: 166
  • Like
  • Fire
Reactions: 26 users

cassip

Regular
  • Like
Reactions: 3 users

Pmel

Regular
ok, thank you, that makes sense ;)
unfortunately the whole post (including Brainchips article) disappeared on Linkedin now and Twitter says at Brainchips: "content can not be loaded atm"
Just took the screenshot and double checked. All the comments are still intact.
 
  • Like
  • Fire
Reactions: 8 users
Brainchip was approved by Intel to appear and demonstrate AKIDA technology at this event?

It seems logical that on the way to being selected for inclusion in Intel Foundry Services and attending this event that Brainchip has created positive relationships with Intel employees reinforced by the employment of Mr. Stephen Thorne as VP of Sales at Brainchip?

The public nature of the relationship between Brainchip and Intel employees would not preclude friendly, positive remarks about looking forward to seeing Brainchip at this event?

Not sure what the issue is that demands so much discussion.

Perhaps someone can assist me to understand.

My opinion only DYOR
Fact Finder
 
  • Like
  • Fire
  • Love
Reactions: 20 users

cassip

Regular
Hi FF,

there was some confusion. Everything has been clarified now.

Regards
Cassip
 
Last edited:
  • Like
  • Fire
Reactions: 7 users
Brainchip was approved by Intel to appear and demonstrate AKIDA technology at this event?

It seems logical that on the way to being selected for inclusion in Intel Foundry Services and attending this event that Brainchip has created positive relationships with Intel employees reinforced by the employment of Mr. Stephen Thorne as VP of Sales at Brainchip?

The public nature of the relationship between Brainchip and Intel employees would not preclude friendly, positive remarks about looking forward to seeing Brainchip at this event?

Not sure what the issue is that demands so much discussion.

Perhaps someone can assist me to understand.

My opinion only DYOR
Fact Finder
It's not the positive remarks, as you say..

"The public nature of the relationship between Brainchip and Intel employees would not preclude friendly, positive remarks about looking forward to seeing Brainchip at this event?"

These are personal type comments, that you would expect (at least I would) to have a name attached to them.

Not the sort of comments I'd expect an USD184 billion, faceless Corporation, to be making.

I'm happy to see them, it just seems odd, to me personally.
 
  • Like
Reactions: 8 users
It's not the positive remarks, as you say..

"The public nature of the relationship between Brainchip and Intel employees would not preclude friendly, positive remarks about looking forward to seeing Brainchip at this event?"

These are personal type comments, that you would expect (at least I would) to have a name attached to them.

Not the sort of comments I'd expect an USD184 billion, faceless Corporation, to be making.

I'm happy to see them, it just seems odd, to me personally.
Thank you DB.

So it seems odd to you.

I have to ask.

Do you think someone has faked an Intel Twitter and LinkedIn account or even hacked same to post two innocuous friendly remarks?

If so for what purpose have they gone to this trouble?

My opinion only DYOR
Fact Finder
 
  • Like
  • Haha
  • Thinking
Reactions: 10 users
Thank you DB.

So it seems odd to you.

I have to ask.

Do you think someone has faked an Intel Twitter and LinkedIn account or even hacked same to post two innocuous friendly remarks?

If so for what purpose have they gone to this trouble?

My opinion only DYOR
Fact Finder
No I don't think that, but it doesn't change the fact, that it seems odd to me.

Does me saying "I'm happy to see them".

Lead you to believe and ask if I "think someone has faked an Intel Twitter and LinkedIn account or even hacked same to post two innocuous friendly remarks?"

Aren't I allowed, to have my own opinion?
 
Last edited:
  • Like
  • Love
Reactions: 7 users
No I don't think that, but it doesn't change the fact, that it seems odd to me.

Aren't I allowed, to have my own opinion?
Did I say that?

No I am trying to understand why something you think is odd is odd and why it might have a bearing on my investment.

My opinion only DYOR
Fact Finder
 
  • Like
  • Love
Reactions: 6 users
Did I say that?

No I am trying to understand why something you think is odd is odd and why it might have a bearing on my investment.

My opinion only DYOR
Fact Finder
I already tried to explain my reasons to you.

 
  • Haha
  • Like
  • Thinking
Reactions: 10 users

Kachoo

Regular
On the SP price perspective I'll say nobody here has a clue what the price will be tomorrow or the next day. Neither do I. LT is suspect up hence I'm here lol.

Lots happening IMO mostly positive outlooks.
 
  • Like
  • Fire
Reactions: 9 users

Jasonk

Regular
30 bucks (or pounds maybe) an hour?
In London?!
Good point you make; getting a little used to geolocation altering rates, my bad. After a quick google it seems to be above a lot of other roles.
 
Last edited:
  • Like
Reactions: 4 users

BrainShit

Regular
Learn how to deploy @NVIDIA's TAO (Train Adapt Optimize) models to devices equipped with an Arm-based CPU, GPU, or NPU for efficient privacy preservation.

From detection, model conversion, image capture, and more, this guide covers it all. 🧠 okt.to/4HRgWE
 

Attachments

  • Screenshot_20240219_150659_X.jpg
    Screenshot_20240219_150659_X.jpg
    892.2 KB · Views: 56
Last edited:
  • Like
  • Fire
Reactions: 11 users

cosors

👀
View attachment 57211


Wonder what they mean by more hmm
I had a cursory look. Maybe it's because they're presenting their new roadmap and Brainchip will be part of it?

1708355765124.png


"IFS Direct Connect
Intel will disclose further manufacturing plans


On February 21, Intel will host IFS Direct Connect in San Jose . This will be a conference where Intel will continue to execute on its Intel Foundry Services (IFS) strategy and possibly announce additional customers and partnerships. In addition to Intel, companies such as Synopsys, Cadence, Siemens, Ansys will be on site.

One of the presentations will be given by Dr. Ann Kelleher, Head of the Development Department. Her presentation is entitled "Unveiling Our Roadmap Beyond 5N4Y" – i.e. the announcement of the roadmap that is to come into force after the current period of the "Five Nodes in Four Years" strategy (5N4Y). So far, Intel hasn't commented on what's coming after Intel 18A. So this will now happen on February 21st.
1708356074566.jpeg

At IEDM 2023 , Intel showcased some technological approaches to scaling manufacturing . Here, after Intel 18A, everything was still referred to as "Intel Next". Also at the IEDM (IEEE International Electron Devices Meeting), TSMC talked about its plans going beyond N2 . Here, too, the corresponding designations A14 and A10 are chosen for the Ångström era."


"Intel to reveal its roadmap beyond the 18A (1.8nm) process node in a few weeks — the company will share its post-5N4Y plans during February event​

We'll get to see Intel's post-5N4Y roadmap soon.

Along with introducing its IDM 2.0 paradigm in 2021, which involves using both internal and external production capacities, Intel also outlined its impressive plan for 'five nodes in four years,' now dubbed '5N4Y.' The culmination of that impressive project is supposed to be the company's 18A (1.8nm-class) technology, which is scheduled to become production-ready in "early 2025." Little is known about the company's plans beyond 18A, but now it says it will reveal its new roadmap in February.

Intel plans to host its IFS Direct Connect event on February 21, where Intel Foundry Services will discuss its roadmap beyond 5N4Y. Featured speakers at the event are Pat Gelsinger, Chief Executive of Intel; Stu Pann, General Manager of IFS; Keyvan Esfarjani, General Manager of Intel's Supply Chain and Operations, as well as Ann Kelleher, Executive Vice President responsible for Process Technology Development at Intel.

If you're interested in the process technologies that are set to come after 18A, Ann Kelleher's presentation is the one to watch. What to expect from Intel beyond 18A is up in the air, but we expect the company to continue building on its latest innovations. Intel's 20A introduces RibbonFET gate-all-around (GAA) transistors and PowerVia backside power delivery network (BSPDN), and 18A refines both technologies. At the recent IEDM event, the company outlined a further evolution of BSPDN, so expect one of Intel's process technologies after 18A to use this feature. GAA will obviously evolve as well, so we expect Intel to innovate in this realm, too.

Meanwhile, the disparity in the requirements of chips for different applications necessitates Intel to specialize in various process technologies, something that Intel does already. For example, Intel 3 offered a denser high-performance library and increased drive current, which is just what the doctor ordered for data center-class processors. Whether this approach will be extended and Intel will offer other specialized nodes remains open to question.

Intel describes the IFS Direct event as follows:

"Hear from Intel leaders, technologists, and partners as they share details of our strategy, process technology, advanced packaging, and ecosystem. Learn how Intel Foundry Services can help you build your silicon designs leveraging Intel’s resilient, security, and sustainably oriented, source of supply."

The career profiles of the event speakers indicate that Intel plans to disclose both the technical and executive directions of Intel and IFS. However, the nature of the event implies that its focus will be squarely on Intel Foundry Services operations."
 
Last edited:
  • Like
  • Love
  • Fire
Reactions: 34 users
I had a cursory look. Maybe it's because they're presenting their new roadmap and Brainchip will be part of it?

View attachment 57231

"IFS Direct Connect
Intel will disclose further manufacturing plans


On February 21, Intel will host IFS Direct Connect in San Jose . This will be a conference where Intel will continue to execute on its Intel Foundry Services (IFS) strategy and possibly announce additional customers and partnerships. In addition to Intel, companies such as Synopsys, Cadence, Siemens, Ansys will be on site.

One of the presentations will be given by Dr. Ann Kelleher, Head of the Development Department. Her presentation is entitled "Unveiling Our Roadmap Beyond 5N4Y" – i.e. the announcement of the roadmap that is to come into force after the current period of the "Five Nodes in Four Years" strategy (5N4Y). So far, Intel hasn't commented on what's coming after Intel 18A. So this will now happen on February 21st.
View attachment 57233
At IEDM 2023 , Intel showcased some technological approaches to scaling manufacturing . Here, after Intel 18A, everything was still referred to as "Intel Next". Also at the IEDM (IEEE International Electron Devices Meeting), TSMC talked about its plans going beyond N2 . Here, too, the corresponding designations A14 and A10 are chosen for the Ångström era."


"Intel to reveal its roadmap beyond the 18A (1.8nm) process node in a few weeks — the company will share its post-5N4Y plans during February event​

We'll get to see Intel's post-5N4Y roadmap soon.

Along with introducing its IDM 2.0 paradigm in 2021, which involves using both internal and external production capacities, Intel also outlined its impressive plan for 'five nodes in four years,' now dubbed '5N4Y.' The culmination of that impressive project is supposed to be the company's 18A (1.8nm-class) technology, which is scheduled to become production-ready in "early 2025." Little is known about the company's plans beyond 18A, but now it says it will reveal its new roadmap in February.

Intel plans to host its IFS Direct Connect event on February 21, where Intel Foundry Services will discuss its roadmap beyond 5N4Y. Featured speakers at the event are Pat Gelsinger, Chief Executive of Intel; Stu Pann, General Manager of IFS; Keyvan Esfarjani, General Manager of Intel's Supply Chain and Operations, as well as Ann Kelleher, Executive Vice President responsible for Process Technology Development at Intel.

If you're interested in the process technologies that are set to come after 18A, Ann Kelleher's presentation is the one to watch. What to expect from Intel beyond 18A is up in the air, but we expect the company to continue building on its latest innovations. Intel's 20A introduces RibbonFET gate-all-around (GAA) transistors and PowerVia backside power delivery network (BSPDN), and 18A refines both technologies. At the recent IEDM event, the company outlined a further evolution of BSPDN, so expect one of Intel's process technologies after 18A to use this feature. GAA will obviously evolve as well, so we expect Intel to innovate in this realm, too.

Meanwhile, the disparity in the requirements of chips for different applications necessitates Intel to specialize in various process technologies, something that Intel does already. For example, Intel 3 offered a denser high-performance library and increased drive current, which is just what the doctor ordered for data center-class processors. Whether this approach will be extended and Intel will offer other specialized nodes remains open to question.

Intel describes the IFS Direct event as follows:

"Hear from Intel leaders, technologists, and partners as they share details of our strategy, process technology, advanced packaging, and ecosystem. Learn how Intel Foundry Services can help you build your silicon designs leveraging Intel’s resilient, security, and sustainably oriented, source of supply."

The career profiles of the event speakers indicate that Intel plans to disclose both the technical and executive directions of Intel and IFS. However, the nature of the event implies that its focus will be squarely on Intel Foundry Services operations."
Interesting..


An excerpt..

"Nvidia's H100 GPU, for example, is close to the reticle limit at 814mm2. These large-area chips likely have glum yields since you can only pack so many onto a wafer and some will be defective one way or another"

"This is why chip designers are increasingly relying on advanced packaging to combine multiple smaller chiplets into one big CPU or GPU within a processor package. AMD's Zen family and Intel's GPU Max cards are prime examples of what's possible using advanced packaging"


And the conclusion..

"While advances in process tech remain important, factors like packaging, power delivery, and signaling are arguably as important, and as time goes on will arguably become more so. So, unless someone stumbles upon some miracle solution for continuing Moore's Law, chip manufacturing is going to be awfully or perhaps delightfully weird over the next decade"

Intel and all chip manufacturers, are trying various things, to keep tech moving forward, as the old doors, begin to close..
 
  • Like
  • Fire
Reactions: 10 users

cosors

👀
Interesting..

Moore's Law, chip manufacturing is going to be awfully or perhaps delightfully weird over the next decade"

Intel and all chip manufacturers, are trying various things, to keep tech moving forward, as the old doors, begin to close..
I can be even crazier, right down to the aluminium hat. What if Intel not just knew what they will announcing, obvious, but had used the last few days to pick up a few dozen million shares, then they would have done everything right. I'd better keep quiet now...

Screenshot_2024-02-19-18-07-27-32_40deb401b9ffe8e1df2f1cc5ba480b12.jpg


"APPROACHING THE VON NEUMANN BOTTLENECK: NEUROMORPHIC COMPUTING & BEYOND​

...Moore’s law states that..."

😁😅🤭
 
Last edited:
  • Like
  • Fire
  • Wow
Reactions: 29 users
Top Bottom