BRN Discussion Ongoing

PvdM has been working on SNNs since at least 2008, so I suspect hat by 2019 he would have begun to get a glimmer of understanding of its capabilities.

https://brainchip.com/brainchip-releases-client-server-interface-tool-for-snap-technology/

BrainChip releases client server interface tool for snap technology 15.03.2016​

...
The SNAP neural network learns features that exist in the uploaded data, even when they are not distinguishable by human means. Autonomous machine learning has long been an elusive target in computer science. Recursive programs are cumbersome and take a long time to process. BrainChip has accomplished rapid autonomous machine learning in its patented hardware-only solution by replicating the learning ability of the brain, by re-engineering the way neural networks function, and by creating a new way of computing culminating in the SNAP technology.

It is possible to trace the development of Akida through the BrainChip patents, listed here:

https://worldwide.espacenet.com/patent/search/family/070458523/publication/US11468299B2?q=pa = "brainchip"

This is a US patent derived from PvdM's first NN patent application:

US10410117B2 Method and a system for creating dynamic neural function libraries: Priority 20080921

View attachment 20975

A method of creating a reusable dynamic neural function library for use in artificial intelligence, the method comprising the steps of:
sending a plurality of input pulses in form of stimuli to a first artificial intelligent device, where the first artificial intelligent device includes a hardware network of reconfigurable artificial neurons and synapses;
learning at least one task or a function autonomously from the plurality of input pulses, by the first artificial intelligent device;
generating and storing a set of control values, representing one learned function, in synaptic registers of the first artificial intelligent device;
altering and updating the control values in synaptic registers, based on a time interval and an intensity of the plurality of input pulses for autonomous learning of the functions, thereby creating the function that stores sets of control values, at the first artificial intelligent device; and
transferring and storing the function in the reusable dynamic neural function library, together with other functions derived from a plurality of artificial intelligent devices, allowing a second artificial intelligent device to reuse one or more of the functions learned by the first artificial intelligent device
.

... and this is the key patent which was granted recently:

US11468299B2 Spiking neural network: Priority 20181101

View attachment 20977

A system, method, and computer program product embodiments for an improved spiking neural network (SNN) configured to learn and perform unsupervised extraction of features from an input stream. An embodiment operates by receiving a set of spike bits corresponding to a set synapses associated with a spiking neuron circuit. The embodiment applies a first logical AND function to a first spike bit in the set of spike bits and a first synaptic weight of a first synapse in the set of synapses. The embodiment increments a membrane potential value associated with the spiking neuron circuit based on the applying. The embodiment determines that the membrane potential value associated with the spiking neuron circuit reached a learning threshold value. The embodiment then performs a Spike Time Dependent Plasticity (STDP) learning function based on the determination that the membrane potential value of the spiking neuron circuit reached the learning threshold value.

This one is for detecting partially obscured objects, quite handy in the real world:

US11151441B2 System and method for spontaneous machine learning and feature extraction: Priority 20170208

View attachment 20980

an artificial neural network system for improved machine learning, feature pattern extraction and output labeling. The system comprises a first spiking neural network and a second spiking neural network. The first spiking neural network is configured to spontaneously learn complex, temporally overlapping features arising in an input pattern stream. Competitive learning is implemented as Spike Timing Dependent Plasticity with lateral inhibition in the first spiking neural network. The second spiking neural network is connected with the first spiking neural network through dynamic synapses, and is trained to interpret and label the output data of the first spiking neural network. Additionally, the output of the second spiking neural network is transmitted to a computing device, such as a CPU for post processing.


Accurate detection of objects is a challenging task due to lighting changes, shadows, occlusions, noise and convoluted backgrounds. Principal computational approaches use either template matching with hand-designed features, reinforcement learning, or trained deep convolutional networks of artificial neurons and combinations thereof. Vector processing systems generate values, indicating color distribution, intensity and orientation from the image. These values are known as vectors and indicate the presence or absence of a defined object. Reinforcement learning networks learn by means of a reward or cost function. The reinforcement learning system is configured to either maximize the reward value or minimize the cost value and the performance of the system is highly dependent on the quality and conditions of these hand-crafted features.

Deep convolutional neural networks learn by means of a technique called back-propagation, in which errors between expected output values for a known and defined input, and actual output values, are propagated back to the network by means of an algorithm that updates synaptic weights with the intent to minimize the error.

The Deep Learning method requires millions of labelled input training models, resulting in long training times, and clear definition of known output values.

However, these methods are not useful when dealing with previously unknown features or in the case whereby templates are rapidly changing or where the features are flexible. The field of neural networks is aimed at developing intelligent learning machines that are based on mechanisms which are assumed to be related to brain function. U.S. Pat. No. 8,250,011 [BrainChip] describes a system based on artificial neural network learning. The system comprises a dynamic artificial neural computing device that is capable of approximation, autonomous learning and strengthening of formerly learned input patterns. The device can be trained and can learn autonomously owing to the artificial spiking neural network that is intended to simulate or extend the functions of a biological nervous system. Since, the artificial spiking neural network simulates the functioning of the human brain; it becomes easier for the artificial neural network to solve computational problems.

[0003] US20100081958 (Lapsed) [Florida Uni] describes a more advanced version of machine learning and automated feature extraction using neural network. US20100081958 is related to pulse-based feature extraction for neural recordings using a neural acquisition system. The neural acquisition system includes the neural encoder for temporal-based pulse coding of a neural signal, and a spike sorter for sorting spikes encoded in the temporal-based pulse coding. The neural encoder generates a temporal-based pulse coded representation of spikes in the neural signal based on integrate-and-fire coding of the received neural signal and can include spike detection and encode features of the spikes as timing between pulses such that the timing between pulses represents features of the spikes.

[0004] However, the prior art do not disclose any system or method which can implement machine learning or training algorithm and can autonomously extract features and label them as an output without implementing lengthy training cycles. In view of the aforementioned reasons, there is therefore a need for improved techniques in spontaneous machine learning, eliminating the need for hand-crafted features or lengthy training cycles. Spontaneous Dynamic Learning differs from supervised learning in that known input and output sets are not presented, but instead the system learns from repeating patterns (features) in the input stream
.

US2010081958A1 PULSE-BASED FEATURE EXTRACTION FOR NEURAL RECORDINGS relates to neurophysiology, I guess it's to do with those skull cap neuron detectors, which shows the depth of PvdM's research.



It is interesting that US20100081958 (Lapsed) [Florida Uni] is cited for its discussion of spike sorting because BrainChip's US11468299B2 Spiking neural network also has a spike sorting system:


View attachment 20982

It doesn't look like the Florida Uni document discloses anything like PvdM's spike sorter.

View attachment 20985


Sorry, I seem to have wandered down a different rabbit hole from the one I started in ...


... oh yes, does PvdM know the capabilities of Akida?

I think even he will be astonished when he gets the cortex sorted out and produces AGI, or maybe, justly hugely proud of his achievements.
Great expert witnesses make average lawyers look good.
Thanks for all you do for shareholders @Diogenese

Highest regards
FF

AKIDA BALLISTA
 
  • Like
  • Love
  • Fire
Reactions: 36 users

Sirod69

bavarian girl ;-)
PvdM has been working on SNNs since at least 2008, so I suspect hat by 2019 he would have begun to get a glimmer of understanding of its capabilities.

https://brainchip.com/brainchip-releases-client-server-interface-tool-for-snap-technology/

BrainChip releases client server interface tool for snap technology 15.03.2016​

...
The SNAP neural network learns features that exist in the uploaded data, even when they are not distinguishable by human means. Autonomous machine learning has long been an elusive target in computer science. Recursive programs are cumbersome and take a long time to process. BrainChip has accomplished rapid autonomous machine learning in its patented hardware-only solution by replicating the learning ability of the brain, by re-engineering the way neural networks function, and by creating a new way of computing culminating in the SNAP technology.

It is possible to trace the development of Akida through the BrainChip patents, listed here:

https://worldwide.espacenet.com/patent/search/family/070458523/publication/US11468299B2?q=pa = "brainchip"

This is a US patent derived from PvdM's first NN patent application:

US10410117B2 Method and a system for creating dynamic neural function libraries: Priority 20080921

View attachment 20975

A method of creating a reusable dynamic neural function library for use in artificial intelligence, the method comprising the steps of:
sending a plurality of input pulses in form of stimuli to a first artificial intelligent device, where the first artificial intelligent device includes a hardware network of reconfigurable artificial neurons and synapses;
learning at least one task or a function autonomously from the plurality of input pulses, by the first artificial intelligent device;
generating and storing a set of control values, representing one learned function, in synaptic registers of the first artificial intelligent device;
altering and updating the control values in synaptic registers, based on a time interval and an intensity of the plurality of input pulses for autonomous learning of the functions, thereby creating the function that stores sets of control values, at the first artificial intelligent device; and
transferring and storing the function in the reusable dynamic neural function library, together with other functions derived from a plurality of artificial intelligent devices, allowing a second artificial intelligent device to reuse one or more of the functions learned by the first artificial intelligent device
.

... and this is the key patent which was granted recently:

US11468299B2 Spiking neural network: Priority 20181101

View attachment 20977

A system, method, and computer program product embodiments for an improved spiking neural network (SNN) configured to learn and perform unsupervised extraction of features from an input stream. An embodiment operates by receiving a set of spike bits corresponding to a set synapses associated with a spiking neuron circuit. The embodiment applies a first logical AND function to a first spike bit in the set of spike bits and a first synaptic weight of a first synapse in the set of synapses. The embodiment increments a membrane potential value associated with the spiking neuron circuit based on the applying. The embodiment determines that the membrane potential value associated with the spiking neuron circuit reached a learning threshold value. The embodiment then performs a Spike Time Dependent Plasticity (STDP) learning function based on the determination that the membrane potential value of the spiking neuron circuit reached the learning threshold value.

This one is for detecting partially obscured objects, quite handy in the real world:

US11151441B2 System and method for spontaneous machine learning and feature extraction: Priority 20170208

View attachment 20980

an artificial neural network system for improved machine learning, feature pattern extraction and output labeling. The system comprises a first spiking neural network and a second spiking neural network. The first spiking neural network is configured to spontaneously learn complex, temporally overlapping features arising in an input pattern stream. Competitive learning is implemented as Spike Timing Dependent Plasticity with lateral inhibition in the first spiking neural network. The second spiking neural network is connected with the first spiking neural network through dynamic synapses, and is trained to interpret and label the output data of the first spiking neural network. Additionally, the output of the second spiking neural network is transmitted to a computing device, such as a CPU for post processing.


Accurate detection of objects is a challenging task due to lighting changes, shadows, occlusions, noise and convoluted backgrounds. Principal computational approaches use either template matching with hand-designed features, reinforcement learning, or trained deep convolutional networks of artificial neurons and combinations thereof. Vector processing systems generate values, indicating color distribution, intensity and orientation from the image. These values are known as vectors and indicate the presence or absence of a defined object. Reinforcement learning networks learn by means of a reward or cost function. The reinforcement learning system is configured to either maximize the reward value or minimize the cost value and the performance of the system is highly dependent on the quality and conditions of these hand-crafted features.

Deep convolutional neural networks learn by means of a technique called back-propagation, in which errors between expected output values for a known and defined input, and actual output values, are propagated back to the network by means of an algorithm that updates synaptic weights with the intent to minimize the error.

The Deep Learning method requires millions of labelled input training models, resulting in long training times, and clear definition of known output values.

However, these methods are not useful when dealing with previously unknown features or in the case whereby templates are rapidly changing or where the features are flexible. The field of neural networks is aimed at developing intelligent learning machines that are based on mechanisms which are assumed to be related to brain function. U.S. Pat. No. 8,250,011 [BrainChip] describes a system based on artificial neural network learning. The system comprises a dynamic artificial neural computing device that is capable of approximation, autonomous learning and strengthening of formerly learned input patterns. The device can be trained and can learn autonomously owing to the artificial spiking neural network that is intended to simulate or extend the functions of a biological nervous system. Since, the artificial spiking neural network simulates the functioning of the human brain; it becomes easier for the artificial neural network to solve computational problems.

[0003] US20100081958 (Lapsed) [Florida Uni] describes a more advanced version of machine learning and automated feature extraction using neural network. US20100081958 is related to pulse-based feature extraction for neural recordings using a neural acquisition system. The neural acquisition system includes the neural encoder for temporal-based pulse coding of a neural signal, and a spike sorter for sorting spikes encoded in the temporal-based pulse coding. The neural encoder generates a temporal-based pulse coded representation of spikes in the neural signal based on integrate-and-fire coding of the received neural signal and can include spike detection and encode features of the spikes as timing between pulses such that the timing between pulses represents features of the spikes.

[0004] However, the prior art do not disclose any system or method which can implement machine learning or training algorithm and can autonomously extract features and label them as an output without implementing lengthy training cycles. In view of the aforementioned reasons, there is therefore a need for improved techniques in spontaneous machine learning, eliminating the need for hand-crafted features or lengthy training cycles. Spontaneous Dynamic Learning differs from supervised learning in that known input and output sets are not presented, but instead the system learns from repeating patterns (features) in the input stream
.

US2010081958A1 PULSBASIERTE MERKMALEXTRAKTION FÜR NEURALAUFZEICHNUNGEN bezieht sich auf die Neurophysiologie, ich denke, es hat mit diesen Schädelkappen-Neuronendetektoren zu tun, was die Tiefe der Forschung von PvdM zeigt.



Es ist interessant, dass US20100081958 (Lapsed) [Florida Uni] für seine Erörterung der Spike-Sortierung zitiert wird, da BrainChips US11468299B2 Spiking Neural Network auch ein Spike-Sortiersystem hat:


View attachment 20982

Es sieht nicht so aus, als würde das Dokument der Florida Uni irgendetwas wie den Spike-Sortierer von PvdM offenbaren.

View attachment 20985


Entschuldigung, ich scheine in ein anderes Kaninchenloch gewandert zu sein als in das, in dem ich angefangen habe ...


... ach ja, kennt PvdM die Fähigkeiten von Akida?

Ich denke, selbst er wird erstaunt sein, wenn er den Kortex aussortiert und AGI produziert, oder vielleicht zu Recht sehr stolz auf seine Errungenschaften sein.
thank you so much
 
  • Like
  • Love
Reactions: 6 users

JK200SX

Regular
  • Like
Reactions: 1 users

Slade

Top 20
  • Like
  • Fire
  • Love
Reactions: 14 users

Slade

Top 20
  • Like
  • Fire
Reactions: 4 users

Diogenese

Top 20

View attachment 20966

Looks to be CNN, not SNN. Not us?

Also, nobody from Brainchip has "liked" it yet.
looked at Quadric a few months ago. From recall, they use ALUs.

https://worldwide.espacenet.com/pat...pa = "quadric" AND nftxt = "machine learning"


US10474398B2 Machine perception and dense algorithm integrated circuit

1667357280713.png



1667357406135.png



[0035] An array core 110 preferably functions as a data or signal processing node (e.g., a small microprocessor) or processing circuit and preferably, includes a register file 112 having a large data storage capacity (e.g., 4 kilobyte (KB) or greater, etc.) and an arithmetic logic unit (ALU) 118 or any suitable digital electronic circuit that performs arithmetic and bitwise operations on integer binary numbers. In a preferred embodiment, the register file 112 of an array core 110 may be the only memory element that the processing circuits of an array core no may have direct access to. An array core no may have indirect access to memory outside of the array core and/or the integrated circuit array 105 (i.e., core mesh) defined by the plurality of border cores 120 and the plurality of array cores 110 .

[0039] An array core 110 may, additionally or alternatively, include a plurality of multiplier (multiply) accumulators (MACs) 114 or any suitable logic devices or digital circuits that may be capable of performing multiply and summation functions.
[0040] Accordingly, each of the plurality of MACs 114 positioned within an array core 110 may function to have direct communication capabilities with neighboring cores (e.g., array cores, border cores, etc.) within the integrated circuit 100 . The plurality of MACs 114 may additionally function to execute computations using data (e.g., operands) sourced from the large register file 112 of an array core no. However, the plurality of MACs 114 preferably function to source data for executing computations from one or more of their respective neighboring core(s) and/or a weights or coefficients (constants) bus 116 that functions to transfer coefficient or weight inputs of one or more algorithms (including machine learning algorithms) from one or more memory elements (e.g., main memory 160 or the like) or one or more input sources.


1667357354436.png



[0049] The dispatcher 130 preferably includes processing circuitry (e.g., microprocessor or the like) that function to create instructions that include scheduled computations or executions to be performed by various circuits and/or components (e.g., array core computations) of the integrated circuit 100 and further, create instructions that enable a control a flow of input data through the integrated circuit 100 . In some embodiments, the dispatcher 130 may function to execute part of the instructions and load another part of the instructions into the integrated circuit array 105 . In general, the dispatcher 130 may function as a primary controller of the integrated circuit 100 that controls and manages access to or a flow (movement) of data from memory to the one or more other storage and/or processing circuits of the integrated circuit 100 (and vice versa). Additionally, the dispatcher 130 may function control execution operations of the various sub-controllers (e.g., periphery controllers, etc.) and the plurality of array cores no.

Pretty ugly really ...
 
  • Like
  • Haha
  • Love
Reactions: 11 users

jk6199

Regular
I just had an order filled at .645 thinking it wouldn't drop that low again.

I am now really looking to couch surf lol.

At least (I hope), my returns will be multiple of this in the future!
 
  • Like
  • Haha
  • Fire
Reactions: 13 users

Diogenese

Top 20
Hi Bravo
Love your work but remember as Brainchip states "We don't make sensors we make them smart." AKIDA is a processor. A GPU is a processor. A CPU is a processor. None of them are sensors but sensors need something to process what they sense and make it intelligible to humans.

Now you can use multiple GPU's or multiple CPU's to process the data coming from five sensors or more and send it somewhere else to be fused into a meaningful action or you can use something that takes in multiple streams of different sensory data and fuses that data on chip and gives you the meaningful action close to the sensors.

By coincidence this ability to take multiple sensor imputes and fuse them on chip close to the sensor and produce meaningful action is something AKIDA technology IP provides. AKIDA IP however will not be the sensor itself.

Remember the Luca Verre CEO of Propehesee interview where he described building their event based sensor but knowing that it was only half the story unless they could find someone with an event based processor.

Intel did not have it.

SynSense did not have it.

But then,

'One enchanted evening,
Then Luca found AKIDA,
And somehow he knew,
With AKIDA he'd be sensing,
And he made it his own'.

(sung to the tune Some Enchanted Evening from South Pacific)

My opinion only DYOR
FF

AKIDA BALLISTA
Was that the fish chorus line song "Salmon chanted evening"?
 
  • Haha
  • Like
Reactions: 8 users

Newk R

Regular
Hi Bravo
Love your work but remember as Brainchip states "We don't make sensors we make them smart." AKIDA is a processor. A GPU is a processor. A CPU is a processor. None of them are sensors but sensors need something to process what they sense and make it intelligible to humans.

Now you can use multiple GPU's or multiple CPU's to process the data coming from five sensors or more and send it somewhere else to be fused into a meaningful action or you can use something that takes in multiple streams of different sensory data and fuses that data on chip and gives you the meaningful action close to the sensors.

By coincidence this ability to take multiple sensor imputes and fuse them on chip close to the sensor and produce meaningful action is something AKIDA technology IP provides. AKIDA IP however will not be the sensor itself.

Remember the Luca Verre CEO of Propehesee interview where he described building their event based sensor but knowing that it was only half the story unless they could find someone with an event based processor.

Intel did not have it.

SynSense did not have it.

But then,

'One enchanted evening,
Then Luca found AKIDA,
And somehow he knew,
With AKIDA he'd be sensing,
And he made it his own'.

(sung to the tune Some Enchanted Evening from South Pacific)

My opinion only DYOR
FF

AKIDA BALLISTA
That's funny. I had dinner with a couple of my brothers last night an we reminisced about when our Uncle Harry sang Some Enchanted Evening at my wedding
 
  • Love
  • Like
Reactions: 4 users
Have you ever wondered why she covers her ears?
So she heard no evil when she worked for and was in a relationship with a proven corrupt union official. Back then she even wore opaque glasses so she could see no evil on the documents she drafted. A future Prime Minister cannot be too careful these sorts of things can come back to bite.

The golden days of Australian politics when both the Prime Minister and Leader of the Opposition where both born and raised for some time in a foreign country before being dragged to Australia by their migrating parents.

When I look at the state of UK politics would the UK have been better of if they had stayed and entered politics in their country of birth.

One of life’s many unknowable unknowns.

My opinion only DYOR
FF

AKIDA BALLISTA
 
  • Like
Reactions: 5 users

Newk R

Regular
Was that the fish chorus line song "Salmon chanted evening"?
Knock Knock
Who's there?
Sam and Janet
Sam and Janet who?
Sam and Janet evening😂
 
  • Haha
  • Like
Reactions: 6 users

KKFoo

Regular
I tend to think that inflationary pressures suppressing industry and the demise of Argo may well play into BRNs hands in the longer run. I see an opportunity for the right technology in the right place at the right time. And Akida is the right technology imo, it’s cheap and scales well as IP, it’s the only real edge choice atm and I think with a suppressed market and the need to keep moving ADAS and level 3 automation ahead, that industry will gravitate towards a modular autonomous solution of necessary components making up what is required. I think this has happened with software in the past (many times) and now it will be forced upon software defined car manufacturers to reduce the amount of reinventing in development they do in favour of purchasing more generic modular solutions - to speed up adoption. I think Akida will be part of this why? Not because I’m a biased shareholder but because Akida scales and will be cheaper and faster to implement. I think that eventually there will be maybe 2 or 3 major autonomous vehicle platforms adopted by the whole of industry and each will utilise Akida technology - fulfilling the companies ambition for Akida to be the defacto standard for car edge AI. AIMO.
My take is once Akida is used in Mercedes, the rest of the makers will follow..
 
  • Like
  • Love
Reactions: 13 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
  • Like
  • Fire
  • Love
Reactions: 56 users
My take is once Akida is used in Mercedes, the rest of the makers will follow..
Would still really love some clarity at some point on that relationship and how / where we fit given no NDA.

Good coin per car according to Qualcomm.




Chipmaker Qualcomm says automotive future business expands to $30 bln​

OCTOBER 21, 2022
U.S. chip designer Qualcomm (QCOM.O) on Thursday said its automotive business “pipeline” increased to $30 billion, up more than $10 billion since its third quarter results were announced in late July.

The jump in future business was thanks to its Snapdragon Digital Chassis product used by car makers and their suppliers, Qualcomm said at its Automotive Investor Day. The Snapdragon Digital Chassis can provide assisted and autonomous driving technology, as well as in-car infotainment and cloud connectivity.

With electric vehicles and increasing autonomous features in cars, the number of chips used by automakers is surging and the automotive market has been a key growth area for chipmakers.

When you think about a per car basis, a lower tier car, we have an opportunity of approximately $200 stretching all the way to $3,000 at the high tier,” said Akash Palkhiwala, Qualcomm’s CFO.
“Going forward the mix will continue to shift towards the high end so the opportunity will keep expanding.”

Qualcomm said the automotive market size it is targeting could grow to as large as $100 billion by 2030.

In fiscal year 2022, it estimates its automotive business revenue will be about $1.3 billion, from $975 million the previous year. By fiscal year 2026, it estimates that to rise to over $4 billion and in fiscal year 2031 to over $9 billion.

Qualcomm also announced an expanded partnership with Mercedes Benz AG (MBGn.DE) which will be using the Snapdragon Cockpit for its in-car infotainment system from 2023.

Qualcomm also has many automotive customers in China. Asked about the impact of broader U.S. export regulations, CEO Cristiano Amon said “strong win-win partnerships between the U.S. enterprises and the China enterprises will always be a force of stability”.
“But we’ll see what the future holds,”
he added.

Earlier this week, chipmaker Nvidia (NVDA.O) unveiled a new automotive central computer called drive thor to provide autonomous and assisted driving as well as in-car digital entertainment and services.
 
  • Like
  • Fire
Reactions: 20 users
  • Like
  • Fire
  • Love
Reactions: 18 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
Anyone heard of this group CREOIR? Half way down it says "Embedded: ARM Cortex @1GHZ, 256MB RAM, 2GB file system".

It also states "Creoir brought voice control into Nokia conscious factory to validate the voice user interface in a factory environment. The Smart Factory Voice Assistant enables a hands-free voice user interface to access Nokia factory data and is now in use at the Nokia conscious factory control corner to provide an easy way of getting quality data of the ongoing production."


Nokia...telecommunications company....non-typical application...maybe....maybe not...

Creoir Offline Voice Solution


FLEXIBLE WAY FOR VOICE INTERACTION ON-THE-EDGE​


Creoir Offline Voice Solution SDK has been developed for products and applications that require private and local voice control without Internet connectivity. The software stack includes Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) provided by Cerence and Natural Language Understanding (NLU) system developed by Creoir. In addition to creating a custom voice UI design, Creoir OVS SDK offers a simple and robust interface towards the customer application.

icon-high-accuracy.png

HIGH ACCURACY​

  • Proven speech technologies from Cerence
  • End-to-end voice performance guaranteed with Speech Signal Enhancement

icon-privacy.png

PRIVACY​

  • The user data stays on the device or on a local network
  • No audio data sent to the cloud or a 3rd party

icon-easy-integration.png

EASY INTEGRATION​

  • Fast development using SDK with built-in APIs
  • Contains tools, libraries and step-by-step instructions

icon-on-the-edge.png

ON-THE-EDGE​

  • Easy set-up and reliable operation without Internet connection
  • Use anytime, anywhere. Perpetual license available for manufacturers.

FEATURES AND BENEFITS​

icon-check.png

Enables fast development cycle to create custom embedded Voice User Interface (VUI) for devices and applications
icon-check.png

Supports programming language independent action code implementation (Python, C, C++, ReactJS, etc.)
icon-check.png

Offers a simple-to-use interface towards customer application with MQTT / Intent-API
icon-check.png

SDK contains tools, libraries, and step-by-step instructions for speaker-independent Natural Language Understanding (NLU)
icon-check.png

Wide language support - 39 languages for Automatic Speech Recognition, 65 languages for Text-to-Speech
icon-check.png

Comes with high-performing Cerence™ speech technologies, shipped in more than 400 million cars already

SUPPORTED PLATFORMS​

supported-platforms.png


SYSTEM REQUIREMENTS​

Embedded: ARM Cortex @1GHZ, 256MB RAM, 2GB file system
PC (Linux, Windows): X86-64, SSE2, AVX2
Mobile: Android 8 (API level 26)

cerence-logo.png


About Cerence: Cerence is the global industry leader in creating unique, moving experiences for the automotive world. As an innovation partner to the world’s leading automakers, it is helping transform how a car feels, responds and learns. Its track record is built on more than 20 years of knowledge and almost 325 million cars on the road today. Whether it’s connected cars, autonomous driving or e-vehicles, Cerence is mapping the road ahead. For more information, visit www.cerence.com.
Creoir uses Cerence CSDK with AI-powered speech recognition and proven acoustic modeling technology to bring great voice experiences for numerous product categories.


CASE STUDY: VOICE ASSISTANCE MAKES FACTORIES SMARTER​


Creoir OVS SDK has been used in various projects. One example is the Smart Factory Voice Assistant PoC developed for Nokia factory.
creoir1_Nokia_Smartfactory.jpg

At the factory, the challenge is that operators and workers need to interrupt the current tasks at hand and free their hands to access data or control computers and machines. But what if they did not have to interrupt what they were doing in the first place? Instead, they could use voice to get access to instructions and manufacturing data or even control computers and machines.
Creoir brought voice control into Nokia conscious factory to validate the voice user interface in a factory environment. The Smart Factory Voice Assistant enables a hands-free voice user interface to access Nokia factory data and is now in use at the Nokia conscious factory control corner to provide an easy way of getting quality data of the ongoing production.
To learn more about the project, see the Reboot IoT Factory blog!

LET’S ADD VOICE TO YOUR PRODUCT!​

CONTACT US TO LEARN MORE

 
  • Like
  • Fire
  • Thinking
Reactions: 22 users

Diogenese

Top 20
@Diogenese and anyone else that can read tech specs, I would be interested in what you think.

Hi Slade,

There are several Maxim Integrated patents:

https://worldwide.espacenet.com/pat...im integrated" AND nftxt = "machine learning"

After close perusal of these documents, this seems to be the most relevant:

US2022334634A1 SYSTEMS AND METHODS FOR REDUCING POWER CONSUMPTION IN EMBEDDED MACHINE LEARNING ACCELERATORS

1667360877101.png


[0051] As previously mentioned, the architecture of hardware accelerator 508 may be different from that of memory 504 or the CPU that memory 504 is embedded in. For example, the bus word size of hardware accelerator 508 may be different from the typical 32-bit or 64-bit bus word size of the CPU or memory 504 . Instead, the architecture of hardware accelerator 508 may be optimized to efficiently perform computations on various sizes of data that do not nicely align with the sizes found in common memory devices.

The MAX7800 data sheet mentions 1, 2, 4, 8 bits:
https://datasheets.maximintegrated.com/en/ds/MAX78000.pdf
442k 8-Bit Weight Capacity with 1,2,4,8-Bit Weights


1667360733657.png


[0013] FIG. 8 depicts a simplified block diagram of a computing device/information handling system, in accordance with embodiments of the present disclosure.

The data sheet does not talk about spikes (except in the context of interference), but it looks like they are running 1, 2, 4, or 8 bits on CPU/GPU.
 

Attachments

  • 1667360802578.png
    1667360802578.png
    71.7 KB · Views: 58
  • Like
  • Love
  • Fire
Reactions: 17 users
Has anyone else received an anomalous trade settlement message on their phone from Comsec?
They are saying I need to deposit funds, for a trade I didn't do?
I'm currently calling them, but am on hold, but wondering, whether their system has been hacked?

The message came through on a number, that they have previously sent me genuine notifications..
 
  • Wow
  • Thinking
  • Sad
Reactions: 15 users

alwaysgreen

Top 20
Has anyone else received an anomalous trade settlement message on their phone from Comsec?
They are saying I need to deposit funds, for a trade I didn't do?
I'm currently calling them, but am on hold, but wondering, whether their system has been hacked?

The message came through on a number, that they have previously sent me genuine notifications..
Sounds like they've been hacked.

Is it for shares in a Nigerian mine?
 
  • Haha
  • Like
Reactions: 14 users
Top Bottom