BRN Discussion Ongoing

This is well worth watching.

They say they are working with luxury car brands..

Thought some of the proposed applications of the tech, are a bit funny though..
Like putting on various types of music, if the car senses tension, or boredom?..

So you're having a major spit with your partner and it starts playing..



Or it senses you're bored and puts your seat into a more sporty driving position and starts playing..




The companion robot, that they are working on with Panasonic, could be Big.

They have expanded the modalities of their tech, beyond just vision now too..

It's crystal clear, what's given them those options.

Talked me into buying another 10k parcel you

1723876050090.gif



Wife won’t be happy but I wish her the best in her new life 😂
 
Last edited:
  • Haha
Reactions: 12 users

IloveLamp

Top 20


1000017742.jpg
1000017740.jpg
 
Last edited:
  • Like
  • Love
  • Fire
Reactions: 35 users
Talked me into buying another 10k parcel now you

View attachment 68124


Wife won’t be happy but I wish her the best in her new life 😂
Good to hear you made the right decision 😉

I'll be buying a few more next week, but not that many, until I can sell more things..

I have "enough"... Perhaps.. But am a buyer while it's still up to and under 25 cents.

Almost everything I look at at the moment, I think "That's worth X amount of BRN shares"..

It's similar, for something I may want to buy..
"You know that's X amount of BRN shares, don't you?"..

Maybe I'm just MAD!...
I guess we'll see..
 
  • Like
  • Love
  • Haha
Reactions: 20 users
Good to hear you made the right decision 😉

I'll be buying a few more next week, but not that many, until I can sell more things..

I have "enough"... Perhaps.. But am a buyer while it's still up to and under 25 cents.

Almost everything I look at at the moment, I think "That's worth X amount of BRN shares"..

It's similar, for something I may want to buy..
"You know that's X amount of BRN shares, don't you?"..

Maybe I'm just MAD!...
I guess we'll see..
Will have to catch up for a beer if it ever makes $1 again lol
 
  • Like
Reactions: 5 users

schuey

Regular
Who remembers Mercedes say that they will announce later this year who they are working with? Are we still a hope? GOD I HOPE SO....
 
  • Like
  • Fire
  • Thinking
Reactions: 14 users

Dallas

Regular
  • Like
  • Thinking
Reactions: 5 users
Will have to catch up for a beer if it ever makes $1 again lol
Sure thing 👍

Screenshot_20240817-183934_Firefox.jpg


They say, where there's smoke, there's fire and we're seeing plenty of smoke.

Unless it's smoke and mirrors 🤔...
 
  • Like
Reactions: 5 users
Who remembers Mercedes say that they will announce later this year who they are working with? Are we still a hope? GOD I HOPE SO....
Hope went out the window ages ago

1723892589128.gif
 
  • Haha
  • Love
Reactions: 4 users

Dallas

Regular
  • Like
  • Love
  • Thinking
Reactions: 10 users

manny100

Top 20
Will have to catch up for a beer if it ever makes $1 again lol
IMO there is a fair chance that the patent portfolio alone is worth more than that.
 
  • Like
  • Fire
Reactions: 10 users
They have an idea, but yet to materialise it, by the looks of things..


Main guy is a young gun..

"Founded in 2022 by 28-year-old artificial intelligence PhD, Walter Goodwin, Fractile s building its first new AI chip, capable of running state-of-the-art AI models up to 100x faster and 10x cheaper than existing hardware"
 
  • Like
  • Fire
Reactions: 6 users

Dallas

Regular
  • Like
  • Fire
Reactions: 7 users

Diogenese

Top 20
They have an idea, but yet to materialise it, by the looks of things..


Main guy is a young gun..

"Founded in 2022 by 28-year-old artificial intelligence PhD, Walter Goodwin, Fractile s building its first new AI chip, capable of running state-of-the-art AI models up to 100x faster and 10x cheaper than existing hardware"

GB2625821A Analog neural network = WO2024141751A1 ANALOG NEURAL NETWORK 20221229

GOODWIN WALTER THOMAS ROMBOLD [GB]

NEU EDGE LTD [GB]

1723901849557.png



An analog neural network is described comprising: a plurality of layers connected to form an electrical circuit having an input and an output, the input suitable for receiving an electrical signal corresponding to an input example and the output corresponding to an output of the neural network. Each layer comprises elements connected together, where the elements comprise: at least one programmable electronic element representing a weight of the neural network; at least one non-linear element; at least one amplifier block; an error element. Each layer also comprises a measurement element for measuring a change in an electrical signal across the error element.
 
Last edited:
  • Like
  • Fire
Reactions: 6 users

Diogenese

Top 20
GB2625821A Analog neural network = WO2024141751A1 ANALOG NEURAL NETWORK 20221229

GOODWIN WALTER THOMAS ROMBOLD [GB]

NEU EDGE LTD [GB]

View attachment 68143


An analog neural network is described comprising: a plurality of layers connected to form an electrical circuit having an input and an output, the input suitable for receiving an electrical signal corresponding to an input example and the output corresponding to an output of the neural network. Each layer comprises elements connected together, where the elements comprise: at least one programmable electronic element representing a weight of the neural network; at least one non-linear element; at least one amplifier block; an error element. Each layer also comprises a measurement element for measuring a change in an electrical signal across the error element.
Oh dear!

https://fortune.com/2024/07/26/fractile-ai-chip-startup-nvidia-15-million-funding-seed-round/


Startup with ‘radical’ concept for AI chips emerges from stealth with $15 million to try to challenge Nvidia​

BYJeremy Kahn
July 26, 2024 at 4:00 PM

...

Fractile was founded in 2022, but has been operating for two years in “stealth mode,” while working on its chip designs. The company has secured its investment seed round from Kindred Capital, the innovation fund of the defense alliance NATO, and Oxford Science Enterprises, which led the funding. Also participating are Cocoa and Innovia Capital, as well as prominent angel investors and alumni of AI and semiconductor companies.

...

AI startup Groq, which already has its chips in production and offers them through its own cloud-based AI computing service, is following a somewhat similar approach, moving the system’s memory closer to where the processing takes place. Groq uses SRAM (static random access memory) components co-located them on the chip, rather than off-chip DRAM to do this. But Goodwin says Fractile is going a step further and combining memory and processing into a single component, which should mean Fractile’s chips are even faster.

So far, though, Fractile has only tested its designs in computer simulations and has yet to manufacture test chips. But Goodwin said Fractile is convinced from these simulations that it can run a large language model, the kind of AI models that power today’s consumer chatbots and form the foundation of most generative AI applications, 100 times faster and 10 times cheaper than Nividia’s GPU
s.
 
  • Like
  • Fire
  • Haha
Reactions: 8 users

Diogenese

Top 20
Very interesting listen, especially after 38.30 onwards.

Georges Massing’s official title has clearly escaped the attention of his company’s marketing team: “Vice President MBOS Automated Driving, Powernet & Integration E/E”. We like to say that he is the global leader of autonomy and cabin technologies (amongst a few other things) for Mercedes-Benz AG, a brand known for safety, reliability, and luxury. Georges is part of the generation of Mercedes managers who will translate those values into a future where vehicle electronics increasingly define the driver experience and sense of value.

“We have two visions that are driving us. One: vision zero, so safety, zero accidents. The second vision that is driving us is how can we give back time to customer?" Georges Massing

Giving time back to the customer means automated driving, and in this regard, Georges’ team leads the world: S-class sedans are the only passenger vehicle in the world certified for Level 3 driving with a system the company calls “Drive Pilot.” This means the driver, while needing to remain available to take control, is free to engage in non-driving tasks while Drive Pilot is active. This ability to leave drivers out of the loop is a critical differentiator with all other systems.

“No matter how good an assisted system is, you as a driver are still responsible and have to control the whole vehicle. As soon as we move to an automated system, now you as a driver, you give control back to the car and you can do way much more.” Georges Massing

To maintain the brand’s focus on safety, Georges emphasizes the need for redundancy in sensing and equipment packages on the vehicle. While pushing new technologies such as end-to-end neural networks, the company is highly sensitive to being able to formally verify the safety and adaptability of advances.

Currently, Drive Pilot limits itself to favorable conditions: clear lane markings on approved freeways, moderate to heavy traffic with speeds under 40 MPH, daytime lighting and clear weather, with the driver visible to a camera located above the driver's display, and no construction zone present. Clearly, the future is about relaxing these conditions, with a relaxation of the speed limit a likely event in the near future.


“Drive Pilot is just the beginning of what can be done." Georges Massing

TT
Hi TT,

"end-to-end neural networks" bodes well for BRN - and redundancy means two of everything!

Mercedes has previously mentioned that it places emphasis on standardization, so that may mean they will use the same tech for all sensors.

So far as we know, they are not using Akida silicon yet, but are doing signal processing in software, but, if the software is Akida/TeNNs simulation software, it will still beat the socks of the competition.
 
  • Like
  • Love
  • Fire
Reactions: 40 users
Oh dear!

https://fortune.com/2024/07/26/fractile-ai-chip-startup-nvidia-15-million-funding-seed-round/


Startup with ‘radical’ concept for AI chips emerges from stealth with $15 million to try to challenge Nvidia​

BYJeremy Kahn
July 26, 2024 at 4:00 PM

...

Fractile was founded in 2022, but has been operating for two years in “stealth mode,” while working on its chip designs. The company has secured its investment seed round from Kindred Capital, the innovation fund of the defense alliance NATO, and Oxford Science Enterprises, which led the funding. Also participating are Cocoa and Innovia Capital, as well as prominent angel investors and alumni of AI and semiconductor companies.

...

AI startup Groq, which already has its chips in production and offers them through its own cloud-based AI computing service, is following a somewhat similar approach, moving the system’s memory closer to where the processing takes place. Groq uses SRAM (static random access memory) components co-located them on the chip, rather than off-chip DRAM to do this. But Goodwin says Fractile is going a step further and combining memory and processing into a single component, which should mean Fractile’s chips are even faster.

So far, though, Fractile has only tested its designs in computer simulations and has yet to manufacture test chips. But Goodwin said Fractile is convinced from these simulations that it can run a large language model, the kind of AI models that power today’s consumer chatbots and form the foundation of most generative AI applications, 100 times faster and 10 times cheaper than Nividia’s GPU
s.
Your "Oh dear!" Doesn't indicate a great deal of concern @Diogenese 😛

Is it the fact they are playing with analog, basing results off of simulations of analog, or something else?

They seem a way off down the track, but could probably have their first Engineering Samples, within the next 6 months, to a year?..

How does TENNs compare, with what they are trying to do for LLMs, in your opinion?
 
Last edited:
  • Like
  • Fire
Reactions: 5 users

Diogenese

Top 20
Your "Oh dear!" Doesn't indicate a great deal of concern @Diogenese 😛

Is it that fact they are playing with analog, basing results off of simulations of analog, or something else?

They seem a way off down the track, but could probably have their first Engineering Samples, within the next 6 months, to a year?..

How does TENNs compare, with what they are trying to do for LLMs, in your opinion?

Raising 15 million pounds on the suggestion that analog is a radical concept is a bit of a stretch.

Their patent talks about clamping the input and output signal levels of the neurons, which they do using digital-to-analog and analog-to-digital converters. They also use error-correction.

In addition, they have only run simulation software. I wonder how much this software takes account of actual silicon manufacturing variations.

Astonishingly the international patent search only found one relevant prior art document. The patent examiner must be living in the Tardus, or maybe they used ChatGPT.

While analog does have theoretical benefits in simplicity, the need for the ADC & DAC for each neuron militates against these advantages..

As to TeNNs, it really is a radical concept on top of the radical concept of digital SNNs, but a technical comparison without any Fractile benchmarking is beyond my pay grade.
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 25 users
  • Haha
Reactions: 2 users
Raising 15 million pounds on the suggestion that analog is a radical concept is a bit of a stretch.

Their patent talks about clamping the input and output signal levels of the neurons, which they do using digital-to-analog and analog-to-digital converters. They also use error-correction.

In addition, they have only run simulation software. I wonder how much this software takes account of actual silicon manufacturing variations.

Astonishingly the international patent search only found one relevant prior art document. The patent examiner must be living in the Tardus, or maybe they used ChatGPT.

While analog does have theoretical benefits in simplicity, the need for the ADC & DAC for each neuron militates against these advantages..

As to TeNNs, it really is a radical concept on top of the radical concept of digital SNNs, but a technical comparison without any Fractile benchmarking is beyond my pay grade.
"Astonishingly the international patent search only found one relevant prior art document. The patent examiner must be living in the Tardus, or maybe they used ChatGPT"

Yeah, I imagined them "beating a path" through a seemingly "undiscovered" area, only to find that path, had just been partially overgrown and wasn't actually new ground..

But figured, it was just my lack of understanding..
 
  • Like
  • Fire
Reactions: 3 users

mrgds

Regular
hi @Diogenese .................. like to ask you if you would agree that SNR (signal to noise ratio) could be seen as the same principals as SNNs ?
And would the use of SNNs give a higher SNR?
Appreciate your thoughts.
Cheers
 
  • Like
Reactions: 1 users
Top Bottom