BRN Discussion Ongoing

[Fullmoonfever]

I like that it's not just medical and flows into industrial mkts as well.

Tata signed a MOU earlier this to move into EV transportation with AI as well for things like fault prediction etc....something I believe we do well.

There is also the previously known link up between Renesas and Tata.

You'd think there's overlap discussions throughout with BRN, at least in research solution options?


Tata Elxsi’s partnership with BrainChip will be driving Akida™ technology into medical devices and industrial applications by leveraging BrainChip’s first-to-market, fully digital, neuromorphic technology to provide intelligent, low-power solutions to these demanding target markets.

IIT Guwahati collaborates with Tata Elxsi to foster EV Technologies

The Institute has signed an MoU with the Industry partner to work on the development and commercialization of products and solutions for EV Transportation

eduadvice.in

IIT Guwahati collaborates with Tata Elxsi to foster EV Technologies​

The Institute has signed an MoU with the Industry partner to work on the development and commercialization of products and solutions for EV Transportation

By : EduAdvice 2023-04-18 06:16:53

Excerpts:

The collaboration between IIT Guwahati and Tata Elxsi will bring together researchers and experts for advanced research in the fields of Material Science, Digital Twins, and Deep Artificial Intelligence and Machine Learning techniques.

One key area of work under this collaboration will be the digital analysis of electrical signature data for traction motors which underpins EV mobility across segments including Automotive and Rail. The solution will provide deep insights for pro-active fault prediction, maintenance schedule formulation, and traceability for design and manufacturing defects.

We already know about the Renesas / Tata partnership.

India roundup: IGSS looking to set up chip fab in southern India-DayStar Electric Technology 乾一科技

IGSS, an applicant for the US$10 billion semiconductor incentive scheme, is looking to set up its fab in southern India. Renesas, eyeing opportunities in India, has expanded its relationship with Tata Group. Singapore-based IGSS may set up semiconductor park in Tamil NaduAccording to The Hindu...

www.daystar-elec.com

View attachment 51831

Just an idea of some the key deals from the Tata Elxsi Q2 FY24 report.

Plenty of scope and exposure in there for Akida solutions imo.

Hope something decent comes out of the partnership sooner than later.

 

[Pom down under]

Day's not over yet....though I'm never a fan of aftermarket Ann's....more often than not meh

 

[Guzzi62]

Wow! STMicroelectronics on a big edge AI push!

Video posted a couple of days ago.

• 30 seconds

"This is AI directly at the edge on a miriad of tiny devices running innumerable applications. This is edge AI. And it's powered by a very different set of chips and software stack to what is used in the data centre today. We are litterally on the brink of this new era that will bring about a massive wave of smart devices representing a huge opportunity. In the coming years we see billions of microcontrollers and smart sensors shipping with AI functionality."

• 5.30 mins

Predicting and detecting faults in HVACs

• 17.43 mins

On-device learning?

• 22 mins

Two new products (STM32N6 & STM32) that integrate powerful neural acceleration cores that bring processing capabilities and algorithms that not so long ago were reserved for CPUs that are in the hands of selects customer now and are going into product development for launch next year.

• 23.21 mins

Real time object detection using STM32N6


View attachment 51813








View attachment 51807

STMicroelectronic is a really huge company with over 50.000 employees, +9000 are engineers.

https://www.st.com/content/st_com/en/about/st_company_information/who-we-are.html

On the bottom of above web page there is a list where they have facilities and they are all over the place.

It would be fantastic getting involved with them for sure.

 

[SERA2g]

Good evening Chippers ,

Couple of notes from past bought to the fore ,

Absolute monza ready to bear fruit ,
The executive suite have been fully engorging themselves in between times , actual shareholders about to, as well thay fricken well deserve.

Several notes & general ponderances to follow.

CRANK THE TUNES.



Regards,
Esq.

Hopefully Rob Telson documents our Partners and Ecosystems a little more digitally than this! Would hate for a birthday cake candle to be the result of years of effort turned to ash!

Love your work though Esq!

 

[TECH]

My ugly mug at Australia's Brainchip HQ taken back in September 2021....how time flies, no chance of sneaking into the office, 1 shot and
Akida has me busted !

Looking forward to coming home in May 2024 and hopefully catch up with the gang for a tea/coffee or beer...trust in our company, I know
it's hard for many holders to keep believing, but the way I see it is, if our team can't deliver with Neuromorphic Computing, well how the hell
are the rest going to manage it....we lead......the mob follow, roll on January 2025

Regards....Tech (NZ)

 

[Humble Genius]

View attachment 51841

My ugly mug at Australia's Brainchip HQ taken back in September 2021....how time flies, no chance of sneaking into the office, 1 shot and
Akida has me busted !

Looking forward to coming home in May 2024 and hopefully catch up with the gang for a tea/coffee or beer...trust in our company, I know
it's hard for many holders to keep believing, but the way I see it is, if our team can't deliver with Neuromorphic Computing, well how the hell
are the rest going to manage it....we lead......the mob follow, roll on January 2025

Regards....Tech (NZ)

Hope you mean roll on 2024?

 

[Humble Genius]

A year on, reading the comments in the thread below is both painful and funny

BRN price prediction Xmas 2023

Happy new year fellow brainers and as I was well off this years price prediction I recon next Xmas will be $879.34

thestockexchange.com.au

 

[ENZee2]

View attachment 51841

My ugly mug at Australia's Brainchip HQ taken back in September 2021....how time flies, no chance of sneaking into the office, 1 shot and
Akida has me busted !

Looking forward to coming home in May 2024 and hopefully catch up with the gang for a tea/coffee or beer...trust in our company, I know
it's hard for many holders to keep believing, but the way I see it is, if our team can't deliver with Neuromorphic Computing, well how the hell
are the rest going to manage it....we lead......the mob follow, roll on January 2025

Regards....Tech (NZ)

Hi Chris
I don't post here much, but do a lot of reading and I do like your input so
If you passing through Warkworth anytime, would be great to have a chat over any of those beverages.
I heading to Vegas on 29th for couple weeks so before xmass would work.
Cheers

 

[Diogenese]

Below is the second STMicroelectronic's video on their Edge AI Summit (published a couple of days ago) with a presentation by Deepu Talla from NVDIA. You can see here at 17.45 a screenshot of the TAO Ecosystem. Deepu mentions in the video that Nvidia design environment is also supported on the Edge Impulse platform.

I've circled Arm, STSTMicroelectronics and Edge Impulse.

View attachment 51830


So this reminded me of what @chapman89 posted on Rob Telson's thoughts on Edge Impulse and TAO, and I thought perhaps a similar situation might prevail in relation to STMicro's customers who might then choose to incorporate BrainChip's IP.





View attachment 51828

Hi Bravo,

We know that, from day 1, Akida has been "processor agnostic".

We know that Akida is even more agnosticker where ARM is concerned, compatibility with all ARM processors having been proven.

ARM produces CPU IP. Nvidia produces GPU and, in 2013, Nvidia announced that it would license its GPU IP.

https://www.anandtech.com/show/7083/nvidia-to-license-kepler-and-future-gpu-ip-to-3rd-parties

NVIDIA to License Kepler and Future GPU IP to 3rd Parties​

by Anand Lal Shimpion June 18, 2013

Processor agnostic should mean that Akida works with Nvidia GPUs, so has there been anything published to show Akida is also agnosticker with Nvidia?

CPUs basically work by performing processes in series. GPUs get their processing power from parallel processing.
Akida is designed for asynchronous operation and has a basically parallel architecture, so I would guess that Akida can be adapted to operate with GPUs.

The main interactions between Akida 1 and an associated processor are that the processor is used to configure the NN nodes/layers and allocate the weights. The processor played no part in the operation of the NN in carrying out its classification/inferencing tasks. The results of the NNs operation would then be sent to the processor to use in its specific tasks.

Akida 2, with its TeNNs/ViT does require some limited interaction between the NN and the processor in implementing these advanced features. There must be some fiddling around to enable the NN and the processor to implement these advanced features. Clearly this fiddling about has been successfully implemented with ARM. It would be nice to have some affirmation that the fiddling around has also been implemented with GPUs, and this is implicit in Rob's response to Chapman.

 

[David holland]

STMicroelectronic is a really huge company with over 50.000 employees, +9000 are engineers.

https://www.st.com/content/st_com/en/about/st_company_information/who-we-are.html

On the bottom of above web page there is a list where they have facilities and they are all over the place.

It would be fantastic getting involved with them for sure.

Bring on a IP, Pressure on Sean to deliver, I think he needs the old Billybaroo

 

[wilzy123]

 

[Diogenese]

Hi @Bravo,

I’m trying to work out the context of the word ”Proprietary” in the article you via posted:

“Unlike other STM32 MCU, the STM32N6 includes a proprietary NPU and an ARM Cortex core.

I’ve listed a few examples of the meaning of “Proprietary” but still not sure it helps make their sentence any clearer.

So I don’t know if the NPU is: theirs, e.g. unique to them or a trade secret?

Fingers crossed it’s Brainchips NPU and their trade secret they’re using it!




What does proprietary mean for a product?

A Proprietary Product refers to a product produced under a legally protected proprietary process or a brand name. With the legally backed propriety rights, others cannot replicate the process or the product.

Does proprietary mean secret?

Proprietary information, also known as a trade secret, is information a company wishes to keep confidential. Proprietary information can include secret formulas, processes, and methods used in production.


What is an example of proprietary in business?

Proprietary information is any information that deals with the activities, business or products of a company. More specifically, some things that commonly fall under this umbrella include trade secrets, financial data, product research and development, computer software, business processes and marketing strategies.

Hi @Bravo ,

Just to drive a stake through the heart of the garlic-allergic monster, this is a very recent application by STM for a Frankenstein in-memory compute chip.

STM use a capacitor to sum currents to perform the analog equivalent of digital MAC (multiply accumulate).


US2023386565A1 IN-MEMORY COMPUTATION CIRCUIT USING STATIC RANDOM ACCESS MEMORY (SRAM) ARRAY SEGMENTATION AND LOCAL COMPUTE TILE READ BASED ON WEIGHTED CURRENT 20230419

An in-memory computation circuit includes a memory array including sub-arrays of with SRAM cells connected in rows by word lines and in columns by bit lines. A row controller circuit selectively actuates word lines across the sub-arrays for an in-memory compute operation. A computation tile circuit for each sub-array includes a column compute circuit for each bit line. Each column compute circuit includes a switched timing circuit that is actuated in response to weight data on the bit line for a duration of time set by an in-memory compute operation enable signal. A current digital-to-analog converter powered by the switched timing circuit operates to generate a drain current having a magnitude controlled by bits of feature data for the in-memory compute operation. The drain current is integrated to generate an output voltage.

[004] … A column processing circuit 20 senses the analog current signals on the pairs of complementary bit lines BLT and BLC (and/or on the read bit line BLR) for the M columns and generates a decision output for the in-memory compute operation from those analog current signals. The column processing circuit 20 can be implemented to support processing where the analog current signals on the columns are first processed individually and then followed by a recombination of multiple column outputs.

[0006] The row controller circuit 18 receives the feature data for the in-memory compute operation and in response thereto performs the function of selecting which ones of the word lines WL<0> to WL<N−1> are to be simultaneously accessed (or actuated) in parallel during an in-memory compute operation, and further functions to control application of pulsed signals to the word lines in accordance with that in-memory compute operation. FIG. 1 illustrates, by way of example only, the simultaneous actuation of all N word lines with the pulsed word line signals, it being understood that in-memory compute operations may instead utilize a simultaneous actuation of fewer than all rows of the SRAM array. The analog signals on a given pair of complementary bit lines BLT and BLC (or on the read bit line RBL in the 8T-type implementation) are dependent on the logic state of the bits of the computational weight stored in the memory cells 14 of the corresponding column and the width(s) of the pulsed word line signals applied to those memory cells 14 .

[0007] The implementation illustrated in FIG. 1 shows an example in the form of a pulse width modulation (PWM) for the applied word line signals for the in-memory compute operation dependent on the received feature data. The use of PWM or period pulse modulation (PTM) for the applied word line signals is a common technique used for the in-memory compute operation based on the linearity of the vector for the multiply-accumulation (MAC) operation. The pulsed word line signal format can be further evolved as an encoded pulse train to manage block sparsity of the feature data of the in-memory compute operation. It is accordingly recognized that an arbitrary set of encoding schemes for the applied word line signals can be used when simultaneously driving multiple word lines. Furthermore, in a simpler implementation, it will be understood that all applied word line signals in the simultaneous actuation may instead have a same pulse width.

 

[IloveLamp]

We've all been told....... BUCKLE UP

Anierroodh Raammie on LinkedIn: #randstaddigital #valeo #partnership

Randstad Digital is excited to share the news of our recent partnership 🤝with Valeo in the realm of Software Defined Vehicles. Together, we’re set to drive…

www.linkedin.com

 

[Mt09]

We've all been told....... BUCKLE UP

Anierroodh Raammie on LinkedIn: #randstaddigital #valeo #partnership

Randstad Digital is excited to share the news of our recent partnership 🤝with Valeo in the realm of Software Defined Vehicles. Together, we’re set to drive…

www.linkedin.com

View attachment 51854

Anything Brainchip related?





Nope.

 

[Tothemoon24]

PROPHESEE on LinkedIn: #ar #vr #edgecomputing #iot #smartdevices #visionsensing #eventsensor #ebv…

📣 Have you heard? Our latest GenX320 Metavision® sensor is making waves in the vision-sensing world! 📰 The smallest and most power-efficient event-based…

www.linkedin.com

Have you heard? Our latest GenX320 Metavision® sensor is making waves in the vision-sensing world!

The smallest and most power-efficient event-based vision sensor to date, the GenX320, has captured the attention of industry enthusiasts and experts alike

Explore the buzz with these insightful articles:

Imaging and Machine Vision Europe: Prophesee unveils event-based sensor for ultra-low power Edge AI Devices

LinkedIn

This link will take you to a page that’s not on LinkedIn

lnkd.in

EE Times | Electronic Engineering Times: Prophesee Reinvents DVS Camera For AIoT Applications (Sally Ward-Foxton)

LinkedIn

This link will take you to a page that’s not on LinkedIn

lnkd.in

BFMTV: Prophesee dévoile son nouveau capteur GenX320, capteur neuromorphique le plus petit et le plus économe

https://lnkd.in/dTcGx2cS

Fierce Electronics: Prophesee unveils latest sensor, aimed at consumer products, IoT (Dan O'Shea)

https://lnkd.in/d8DTVUAU

EE Journal: Prophesee’s 5th generation sensors detect motion instead of images for industrial, robotic and consumer applications (Steve Leibson)

https://lnkd.in/g9XngTRn

Vision Systems Design: Prophesee Launches Event-Based Vision Sensor (Linda Wilson)

https://lnkd.in/dNHaYrCH

L'Usine Nouvelle: Prophesee part à la conquête de l’IoT et de la réalité immersive avec son nouveau capteur événementiel GenX320 (Frédéric Monflier)

https://lnkd.in/dwKeVa7s

eeNews Europe: Event-based sensor for ‘always-on’ video, low-power apps (Peter Clarke)

https://lnkd.in/dkfrpTGF

The Ojo-Yoshida Report: Prophesee Emboldens Its Mass Consumer Outreach (Junko Yoshida)

https://lnkd.in/dmNwj4JV

New Electronics: Prophesee launches event-based vision sensor for consumer Edge-AI devices

https://lnkd.in/drMJEub7


Thank you to these esteemed publications and journalists for covering our latest innovation!

Stay tuned for more exciting updates!

 

[thelittleshort]

https://x.com/brainchip_inc/status/1734294479459246098?s=46&t=QTEd-sj4ml4B_yEc2g-tKw

 

[IloveLamp]

Anything Brainchip related?





Nope.

 

[IloveLamp]

Innovation Drives Change by Socionext • A podcast on Spotify for Creators

Welcome to "Innovation Drives Change!" Our name, Socionext, says everything about us: SOC stands for System-on-Chip, IO for input and output and NEXT represents our forward-thinking approach with a continuous focus on innovation. Here we will discuss as many of our technologies as possible.

podcasters.spotify.com

Socionext Europe on LinkedIn: #socionext #soc #radar #automotive #nca #radarsensor #safety

𝗦𝗢𝗖𝗜𝗢𝗡𝗘𝗫𝗧 𝗜𝗡𝗧𝗥𝗢𝗗𝗨𝗖𝗘𝗦 𝗣𝗢𝗗𝗖𝗔𝗦𝗧 𝗦𝗘𝗥𝗩𝗜𝗖𝗘 Socionext are delighted to unveil our brand-new Podcast Service, geared to keep you…

www.linkedin.com

 

[supersonic001]

At the Hackster.io Summit 2023, BrainChip and AI Put the “Ability” in… | BrainChip

New Video - Todd Vierra - @hacksterio Summit. “Sustainable Cities Using Smart Efficient AI” BrainChip has found methods to boost computational speed, accuracy,…

www.linkedin.com

 

[IloveLamp]

MediaTek's AI-Powered Chips Aim to Make Your Next Phone Very Personal

At the MediaTek Summit, the chipmaker announced new phone chips that use generative AI, new Redcap 5G modems and teased a new augmented reality chip.

www.cnet.com