BRN Discussion Ongoing

A company similar to Prophesee is iniVation with their neuromorphic vision systems.


iniVation partnered with SynSense in 2019 to develop Speck which is a low power smart vision sensor for mobile & IoT devices.


Speck™ is a fully event-driven neuromorphic vision SoC. Speck™ is able to support large-scale spiking convolutional neural network (sCNN) with a fully asynchronous chip architecture. Speck™ is fully configurable with the spiking neuron capacity of 320K. Furthermore, it integrates the state-of-art dynamic vision sensor (DVS) that enables fully event-driven based, real-time, highly integrated solution for varies dynamic visual scene. For classical applications, Speck™ can provide intelligence upon the scene at only mWs with a response latency in few ms.

Prophesee partnered with SynSense in 2021 to develop a one chip event based smart sensing solution for low power edge AI.

Prophesee partnered with BrainChip in 2022 to optimize computer vision AI performance & efficiency.

Prophesee CEO has mentioned BrainChip is a perfect fit for their event based camera vision sensor.

Qualcomm have recently partnered with Prophesee which has been working with Snapdragon processors since 2018.

Qualcomm mentioned Prophesee event based cameras will be launched this year in their recent presentation, however, there was no mention of SynSense's Speck.

It's a puzzle this one. Unless Qualcomm will use Prophesee's metavision event based sensor only with their own processor suitable for neuromorphic SNN if they have one.

I am intrigued because the smartphone market dominated by Qualcomm will result in big revenue for BRN if Akida IP is embedded in their chip for Prophesee's event based camera. It took ARM nearly 10 years from when they started to get into smartphones.


Hi @Steve10

A few of us have latched onto that idea with great excitement and I hope Qualcomm does look to include Brainchip in the future for its science fiction qualities. However it was identified via @Bravo and debunked by @Diogenese as NOT being the case currently.

Qualcomm were working with Icatch and another company whose name escapes me to provide it’s AI needs. N

EDIT: the links below discusses Qualcomm‘s tech and although they look the same have different conten:





It is however highly likely Brainchip could improve performance but given there has been no announcement re partnership/agreements I don’t think it’s the case as the moment!


On the flip side if another phone company wants to match or beat Qualcomm current technology then a Prophesee/Brainchip event camera in their phone would be a good fix so fingers crossed Apple, Pixel, Nokia etc are developing that.

:)
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 33 users

KMuzza

Mad Scientist
Hi- Something worth watching again - especially with the AKIDA-1500 "launching" soon

Watch from 06.25 min - 08.00 min mark. (the whole clip gives little nuggets that now fall into place)



Cheers
AKIDA BALLISTA UBQTS
 
  • Like
  • Fire
  • Love
Reactions: 29 users

Jasonk

Regular
Seems like Open Ai has changed tack for CHAT Gpt4
I know they talk of their partnership with Cerebras, ................. BUT


Is it just me , or , does anybody else find themselves saying,

"hey, thats what Akida can do/make better " ................... :sneaky:

Its the newest version of CHAT Gpt ( 4 )

IE ............ SPARSITY = less computational power consumption
............. MULTIMODAL LANGUAGE MODEL = RTs continual emphasise on multi modalities
..............ADVANTAGE OF FASTER CHIPS OR HARDWARE = have they found a better way to reduce the computational power issues?
...............SELF HEALING SENSORS = Brainchips catchcry ........... making sensors smart
................ARTIFICIAL INTELIGENCE ON EDGE DEVICES = eliminating the need for large cloud servers
.................RESOURCE CONSTRAINED ENVIROMENTS = low power consumption, ? 6mths on a ÄAA" battery
.................BIOLOGICAL BRAINS ABLE TO LEARN = one shot learning

Check out this video if interested




Just wondering whether Elon has taken onboard my numerous emails to him ...................:unsure:

AKIDA ( G iveit Patience Time ) BALLISTA

Open AI produced its own chip technology for ChatGPT based on RISC-V open source architecture I believe. Main keywords they use to describe it are similar to akida. You can speak to the bot in a certain way and it will disclose some information about it creation.

Needless to say akida could be used in conjunction with its in-house design for GPT4 but I'm confident it's not part of previous versions.

Happy for others to chip in here.

In a previous post I mentioned I found it interesting that intel ditched a billion dollars of investment into RISC-V at the same time it incorporated brainchip into its programs and intel diverted the billion dollars of funding to this program.

I'd generally say that it's a very good sign but RISC-v is competition to x86 which is licensed by intel. So it's probable intel may have other forces pushing it arm for switching.
 
  • Like
  • Fire
Reactions: 10 users

equanimous

Norse clairvoyant shapeshifter goddess
Seems like Open Ai has changed tack for CHAT Gpt4
I know they talk of their partnership with Cerebras, ................. BUT


Is it just me , or , does anybody else find themselves saying,

"hey, thats what Akida can do/make better " ................... :sneaky:

Its the newest version of CHAT Gpt ( 4 )

IE ............ SPARSITY = less computational power consumption
............. MULTIMODAL LANGUAGE MODEL = RTs continual emphasise on multi modalities
..............ADVANTAGE OF FASTER CHIPS OR HARDWARE = have they found a better way to reduce the computational power issues?
...............SELF HEALING SENSORS = Brainchips catchcry ........... making sensors smart
................ARTIFICIAL INTELIGENCE ON EDGE DEVICES = eliminating the need for large cloud servers
.................RESOURCE CONSTRAINED ENVIROMENTS = low power consumption, ? 6mths on a ÄAA" battery
.................BIOLOGICAL BRAINS ABLE TO LEARN = one shot learning

Check out this video if interested




Just wondering whether Elon has taken onboard my numerous emails to him ...................:unsure:

AKIDA ( G iveit Patience Time ) BALLISTA

There is already political biases in CHATGPT and the question is what information is also manipulated?

“And mark my words, AI is far more dangerous than nukes. Far. So why do we have no regulatory oversight? This is insane.” Elon Musk, SXSW 2018

 
  • Like
Reactions: 9 users

Crestman

Regular
Today I did a google search that Stuart888 has put up a few times and looking in the last week only.


If you go to tools and choose only the last week, it will give you a link to a NASA document dated 13th March 2023.

There are numerous scopes in here that relate to Akida such as:

Neuromorphic Software for Cognition and Learning for Space Missions

Extreme Radiation Hard Neuromorphic Hardware

Radiation Tolerant Neuromorphic Learning Hardware


Akida is mentioned in the document.

Someone else might be able to shed more light on this document as it has many pages.

Apologies if already posted, I cant keep up with all the posts and gifs sometimes!
 
  • Like
  • Fire
  • Love
Reactions: 28 users
Just had a visit from a mate who I convinced to buy brainchip a while back 😔
He's cool but I still feel like shit.
I should add he did say he should have been buying now, so he still has confidence in the company. But hindsight regarding share price is whole different 🍪
And I got him into Dre @ 3 cents so he's going easy on me 😂
 
  • Like
  • Haha
Reactions: 6 users

TasTroy77

Founding Member
This looks great thanks MC

Screenshot_20230219-120737_Messenger.jpg
 
  • Like
  • Fire
  • Love
Reactions: 20 users

TasTroy77

Founding Member
Screenshot_20230219-120806_Messenger.jpg
 
  • Like
  • Fire
  • Love
Reactions: 47 users

equanimous

Norse clairvoyant shapeshifter goddess
  • Haha
  • Like
  • Thinking
Reactions: 7 users
  • Like
  • Fire
  • Love
Reactions: 31 users

Sirod69

bavarian girl ;-)
Last edited:
  • Like
  • Fire
  • Thinking
Reactions: 10 users
  • Like
Reactions: 4 users

TECH

Regular
Following on from yesterday, below is yet another great paper that is written up by 3 known names on this site, we partnered with Tata Consultancy Services back in 2019 from memory when we jointly conducted our demo's in Vancouver showing hand gesture technology, linking to robotics.

Anyway, we already know that this relationship has and is ongoing, which will deliver massive inroads into robotics in my own opinion, amongst other technologies yet to be revealed, but this company is massive, Indian, and just another link to our ever expanding network.

It may have been posted awhile ago, I just can't remember, have a read and try to absorb some more info.

Sundays question: Why are companies being attracted to us, and I'm not referring to dots?



Here's to a positive week ahead, starting with tomorrows Podcast at 10am AEDT 7am AWST

Tech ;)
 
  • Like
  • Fire
  • Love
Reactions: 38 users

Diogenese

Top 20
A company similar to Prophesee is iniVation with their neuromorphic vision systems.


iniVation partnered with SynSense in 2019 to develop Speck which is a low power smart vision sensor for mobile & IoT devices.


Speck™ is a fully event-driven neuromorphic vision SoC. Speck™ is able to support large-scale spiking convolutional neural network (sCNN) with a fully asynchronous chip architecture. Speck™ is fully configurable with the spiking neuron capacity of 320K. Furthermore, it integrates the state-of-art dynamic vision sensor (DVS) that enables fully event-driven based, real-time, highly integrated solution for varies dynamic visual scene. For classical applications, Speck™ can provide intelligence upon the scene at only mWs with a response latency in few ms.

Prophesee partnered with SynSense in 2021 to develop a one chip event based smart sensing solution for low power edge AI.

Prophesee partnered with BrainChip in 2022 to optimize computer vision AI performance & efficiency.

Prophesee CEO has mentioned BrainChip is a perfect fit for their event based camera vision sensor.

Qualcomm have recently partnered with Prophesee which has been working with Snapdragon processors since 2018.

Qualcomm mentioned Prophesee event based cameras will be launched this year in their recent presentation, however, there was no mention of SynSense's Speck.

It's a puzzle this one. Unless Qualcomm will use Prophesee's metavision event based sensor only with their own processor suitable for neuromorphic SNN if they have one.

I am intrigued because the smartphone market dominated by Qualcomm will result in big revenue for BRN if Akida IP is embedded in their chip for Prophesee's event based camera. It took ARM nearly 10 years from when they started to get into smartphones.
Synsense uses analog SNNs:

WO2023284142A1 SIGNAL PROCESSING METHOD FOR NEURON IN SPIKING NEURAL NETWORK AND METHOD FOR TRAINING SAID NETWORK

1676771117945.png

A signal processing method for a neuron in a spiking neural network, and a method for training said network. Unlike a single spike mechanism that is presently commonly used, same is designed as a multi-spike mechanism. The signal processing method for a neuron comprises: a reception step: at least one neuron receives at least one input spike train; an accumulation step: a membrane voltage is obtained on the basis of a weighted sum of the at least one input spike train; an activation step: once the membrane voltage exceeds a threshold, the amplitude of a spike fired by a neuron is determined on the basis of a ratio of the membrane voltage and the threshold. In order to solve the problems of a training algorithm being inefficient and time-consuming due to an ever-increasing configuration parameter scale, the present network training method achieves highly efficient training of a spiking neural network by means of a multi-spike mechanism, a periodic exponential function surrogate gradient, and addition and suppression of a neuron activity level as loss, low power consumption of neuromorphic hardware can be sustained, and precision and convergence speed are also improved.

Luca Verre has stated that Prophesee do not have Akida in a product (yet!).

Qualcomm Snapdragon 8.2 uses their in-house hexagon AI processor.
 
  • Like
  • Fire
Reactions: 16 users

Sirod69

bavarian girl ;-)
  • Like
Reactions: 1 users
Well if it's Aussie time that's in a couple hours for me😅
@Sirod69
 
  • Haha
  • Like
Reactions: 3 users

Tothemoon24

Top 20
Sounds interesting.
Have we uncovered any links here in the pass ?

 
  • Like
Reactions: 1 users

Sirod69

bavarian girl ;-)
  • Like
  • Love
Reactions: 2 users

Labsy

Regular
  • Like
  • Fire
Reactions: 2 users
Top Bottom