BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Fullmoonfever
Top 20
Latest Accenture Report came out towards the end of Nov.
Unleashing the full potential of AI
Not a bad read for a general overview on their assessment of AI and Semi Industry.
Quite liked this image they used which appears borrowed from a 2015 paper.
www.osti.gov
A table I also found interesting was the costs.
On their web I found a small research section where they did their own POC voice control in 2021:
NEUROMORPHIC COMPUTING: ENERGY-EFFICIENT SMART CARS WITH ADVANCED VOICE CONTROL
Was based on Intel but hey, I don't mind if they blaze away generating industry interest for us to swoop in as the best available for immediate uptake
Speaker 1: Tim Shea, a research scientist at
Accenture Labs, has been working with an
automotive client on prototyping the use of
neuromorphic computing to help people interact
with smart vehicles.
Speaker 2: Consumer demand for AI driven
experiences is increasing rapidly, especially in
the automotive industry. Customers expect
responsive voice, gesture, and contextual
intelligence from their vehicles. But current AI
hardware is too power hungry, which can impact
vehicle performance and limit the possible
applications. Smart vehicles need more efficient
edge AI devices to meet the demand.
Using edge AI devices to compliment cloud
based AI could also increase responsiveness
and improve reliability when connectivity is poor.
So we've built a proof of concept system with
one of our major automotive partners to
demonstrate that neuromorphic computing can
make cars smarter without draining the
batteries. We're using Intel's Kapoho Bay to
recognize voice commands that an owner would
give to their vehicle. The Kapoho Bay is a
portable and extremely efficient neuromorphic
research device for AI at the edge.
We're comparing that proof of concept system
against a standard approach using a GPU. To
build the system, we trained spiking neural
networks to differentiate between command
phrases. Then we ran the trains networks on
the Kapoho Bay. We connected the Kapoho
Bay to a microphone and a controller similar to
the electronic control units that operate various
functions of a smart vehicle.
We're targeting commands that reflect features
that can be accessed from outside a smart
vehicle, such as park here, or unlock passenger
door. These functions also need to be energy
efficient, so the vehicle can remain responsive
even when parked for long stretches of time.
As a first step, we trained the system to
recognize simple commands, such as lights on
and lights off, open door, close door, or start
engine. Using a combination of open source
voice recordings and a smaller sample of
specific commands, we can approximate the
kinds of voice processing needed for smart
vehicles. We tested this approach by comparing
our train spiking neural networks running on
Intel's neuromorphic research cloud against a
convolutional neural network, running on a
GPU.
Both systems achieved acceptable accuracy
recognizing our voice commands, but we found
that the neuromorphic system was up to a
thousand times more efficient than the standard
AI system with a GPU. This is extremely
impressive and it's consistent with the results
from other labs, as Intel will show further in their
session on benchmarking the Intel OAE.
The neuromorphic system also responded up to
200 milliseconds faster than the GPU. This
dramatic improvement in energy efficiency for
our task comes from the fact that computation
in Loihi is extremely sparse. While the GPU
performs billions of computations per second,
every second, the neuromorphic chip only
processes changes in the audio signal and
neuron cores inside low Loihi communicate
efficiently with spikes.
This project demonstrates that neuromorphic
systems can prove more efficient and more
responsive than conventional solutions for AI in
smart vehicles. This research is helping our
partners in the automotive industry understand
how Intel's neuromorphic systems might impact
their next-generation products. And it helps us
develop a roadmap for future neuromorphic
applications.
Copyright © 2021 Accenture
All rights reserved.
Accenture, its logo, and High
Performance Delivered are
trademarks of Accenture
Unleashing the full potential of AI
Unleashing the full potential of AI
The semiconductor industry is key to unlocking the full potential of #AI. Semiconductor manufacturers have the opportunity to play a leading role in driving the next wave of computing. See how:
www.accenture.com
Not a bad read for a general overview on their assessment of AI and Semi Industry.
Quite liked this image they used which appears borrowed from a 2015 paper.
Computing beyond Moore's Law (Journal Article) | OSTI.GOV
The U.S. Department of Energy's Office of Scientific and Technical Information
www.osti.gov
A table I also found interesting was the costs.
On their web I found a small research section where they did their own POC voice control in 2021:
NEUROMORPHIC COMPUTING: ENERGY-EFFICIENT SMART CARS WITH ADVANCED VOICE CONTROL
Was based on Intel but hey, I don't mind if they blaze away generating industry interest for us to swoop in as the best available for immediate uptake
Neuromorphic Computing | Accenture
Every organization needs to shape its computational variety strategy to meet growing demands from consumers. Learn how to stay ahead of increasing competition.
www.accenture.com
Speaker 1: Tim Shea, a research scientist at
Accenture Labs, has been working with an
automotive client on prototyping the use of
neuromorphic computing to help people interact
with smart vehicles.
Speaker 2: Consumer demand for AI driven
experiences is increasing rapidly, especially in
the automotive industry. Customers expect
responsive voice, gesture, and contextual
intelligence from their vehicles. But current AI
hardware is too power hungry, which can impact
vehicle performance and limit the possible
applications. Smart vehicles need more efficient
edge AI devices to meet the demand.
Using edge AI devices to compliment cloud
based AI could also increase responsiveness
and improve reliability when connectivity is poor.
So we've built a proof of concept system with
one of our major automotive partners to
demonstrate that neuromorphic computing can
make cars smarter without draining the
batteries. We're using Intel's Kapoho Bay to
recognize voice commands that an owner would
give to their vehicle. The Kapoho Bay is a
portable and extremely efficient neuromorphic
research device for AI at the edge.
We're comparing that proof of concept system
against a standard approach using a GPU. To
build the system, we trained spiking neural
networks to differentiate between command
phrases. Then we ran the trains networks on
the Kapoho Bay. We connected the Kapoho
Bay to a microphone and a controller similar to
the electronic control units that operate various
functions of a smart vehicle.
We're targeting commands that reflect features
that can be accessed from outside a smart
vehicle, such as park here, or unlock passenger
door. These functions also need to be energy
efficient, so the vehicle can remain responsive
even when parked for long stretches of time.
As a first step, we trained the system to
recognize simple commands, such as lights on
and lights off, open door, close door, or start
engine. Using a combination of open source
voice recordings and a smaller sample of
specific commands, we can approximate the
kinds of voice processing needed for smart
vehicles. We tested this approach by comparing
our train spiking neural networks running on
Intel's neuromorphic research cloud against a
convolutional neural network, running on a
GPU.
Both systems achieved acceptable accuracy
recognizing our voice commands, but we found
that the neuromorphic system was up to a
thousand times more efficient than the standard
AI system with a GPU. This is extremely
impressive and it's consistent with the results
from other labs, as Intel will show further in their
session on benchmarking the Intel OAE.
The neuromorphic system also responded up to
200 milliseconds faster than the GPU. This
dramatic improvement in energy efficiency for
our task comes from the fact that computation
in Loihi is extremely sparse. While the GPU
performs billions of computations per second,
every second, the neuromorphic chip only
processes changes in the audio signal and
neuron cores inside low Loihi communicate
efficiently with spikes.
This project demonstrates that neuromorphic
systems can prove more efficient and more
responsive than conventional solutions for AI in
smart vehicles. This research is helping our
partners in the automotive industry understand
how Intel's neuromorphic systems might impact
their next-generation products. And it helps us
develop a roadmap for future neuromorphic
applications.
Copyright © 2021 Accenture
All rights reserved.
Accenture, its logo, and High
Performance Delivered are
trademarks of Accenture
Dhm
Regular
I agree that this podcast wasn’t quite as uplifting as previous. Sally’s job is to report factually on many companies and the products they are marketing. She fired off quite a list of innovative categories and products in her journalistic universe; and ours, whilst novel and ground breaking, has no direct connection to her, other than to report about, unlike the Arm and Prophesee podcasts, which demonstrated strong disruption.
FJ-215
Regular
If we are going a bit of Peter Sellers, maybe "The mouse that roared" would be a good fit for BRN.
We will move up the food chain next year.
The Renesas tap out news from the other day is great. It’s given me the goal of holding tight for the next 6 to 12 months. Who knows what other great news we will get in the meantime. I’m not too worried, for me, I’m gonna wait to see what happens when Renesas release the new Akida powered chips to their customers.
Izzzzzzzzzzy
Regular
What’s on linkedin?
Mccabe84
Regular
I agree. It’s probably the best news we have had all year ( unless of forgotten something), hopefully megachips are not to far behind them. I’m still thinking we won’t see any real revenue until mid to late next year
DollazAndSense
Regular
If you were a first time listener to Brainchip's podcasts, and this is the first one you tuned into, I don't think you would walk away with the most positive impression of Brainchip. As these podcasts are one of the few times we hear from the company per year (with tiny snippets of progression generally mentioned), I think we could have done without this one. I just don't see the benefit.
I mentioned Sally's use of the word 'niche' in my previous post. Rob Telson played it off well but I could tell he shares my sentiment that niche is a little condescending - note when he said he prefers the term specialty technology. Trivial? Yes. But that was the gist of a lot of the podcast for me though - quasi downplaying our potential to be a game changer.
Dhm
Regular
What we need is revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue revenue
Then we will be $10 per share and going skyward!!
Mugen74
Regular
I will have to listen to it again,as my first impression/lasting take away so far was it seemed to me that she was almost subtely thumbing her nose at Brainchip/Rob (not actually sure what triggered this feeling/impression?) and only really there to plug ee times.?? Anyhow not to worry good things come to those who can wait.
Maybe Anastasi wiuld have been a better fit
Last edited:
thelittleshort
Top Bloke
My money riding the BRN carousel lol
Fact Finder
Top 20
My final thought on the podcast became clear when she was given the opportunity to promote the EE Times conference and then it became clear to me as her effect stood in stark contrast to her articles when she has written about Brainchip.
What she was doing in a rather clumsy fashion was playing to the sensitivities of the conference participants by appearing to be independent of Brainchip.
She and EE Times are like all organisers of these conferences chasing advertising and sponsorship dollars.
I think Rob Telson was aware of what she was doing and this is why he fed us the nugget about Transformers and what his gut was telling him. Rob Telson knows AKIDA 2.0 with Transformers and LSTM is close to being revealed and he wanted to give a heads up to his loyal listeners and shareholders.
My opinion only DYOR
FF
AKIDA BALLISTA
Mugen74
Regular
Aha ok that makes sense cheers FF
Boab
I wish I could paint like Vincent
Fact Finder
Top 20
For those who do not know what Kaphoo Bay from Intel was it was a USB stick made up of one or two 14nm Loihi 1 chips. Loihi 2 is 7nm and still runs at 1.5 to 3 watts.
en.wikichip.org
From my reading early on while Kaphoo Bay could be just one Loihi 1 chip it was generally 2 Loihi 1 chips.
If you want to sit down and do all the calculations using the chart in @Fullmoonfever ’s above post you will see the amazing price and power advantage one first generation Commercial AKD1000 or AKIDA 1.0 chip has over the Loihi 1 and Loihi 2 research chips.
In the above link it explains that the term RESEARCH CHIP is used to convey to the user that performance and reliability cannot be guaranteed.
My opinion only DYOR
FF
AKIDA BALLISTA
Loihi - Intel - WikiChip
Loihi (pronounced low-ee-hee) is a neuromorphic research test chip designed by Intel Labs that uses an asynchronous spiking neural network (SNN) to implement adaptive self-modifying event-driven fine-grained parallel computations used to implement learning and inference with high efficiency. The...
From my reading early on while Kaphoo Bay could be just one Loihi 1 chip it was generally 2 Loihi 1 chips.
If you want to sit down and do all the calculations using the chart in @Fullmoonfever ’s above post you will see the amazing price and power advantage one first generation Commercial AKD1000 or AKIDA 1.0 chip has over the Loihi 1 and Loihi 2 research chips.
In the above link it explains that the term RESEARCH CHIP is used to convey to the user that performance and reliability cannot be guaranteed.
My opinion only DYOR
FF
AKIDA BALLISTA
Izzzzzzzzzzy
Regular
Bro what about the decepticons?
Kachoo
Regular
Comments about Sean dumping shares.
Similar threads
