BRN Discussion Ongoing

[Neuromorphia]

3/17/2022 Press Release - BHTech wins Phase II SBIR Award for Implementing Neural Network Algorithms on Neuromorphic Processors

The generation of real-time insights for the warfighter is an increasingly important area of interest, especially due to the growth of Electronic Warfare challenges. These insights require faster processors and smarter models that can be deployed at the edge in low Size, Weight and Power (SWaP)...

xcelaero.com

used the wayback machine internet archive to find this.

3/17/2022 Press Release - BHTech wins Phase II SBIR Award for Implementing Neural Network Algorithms on Neuromorphic Processors

The generation of real-time insights for the warfighter is an increasingly important area of interest, especially due to the growth of Electronic Warfare challenges. These insights require faster processors and smarter models that can be deployed at the edge in low Size, Weight and Power (SWaP)...

web.archive.org

3/17/2022 Press Release – BHTech wins Phase II SBIR Award for Implementing Neural Network Algorithms on Neuromorphic Processors

The generation of real-time insights for the warfighter is an increasingly important area of interest, especially due to the growth of Electronic Warfare challenges. These insights require faster processors and smarter models that can be deployed at the edge in low Size, Weight and Power (SWaP) configurations. Traditional von-Neumann based computing architectures are challenged by the complex learning models, low power budget and real-time needs of the warfighter. To mitigate this limitation, BHTech has proposed to the United States Navy an implementation strategy using neuromorphic processors to accommodate modern SWaP and performance requirements of the warfighter.

Bascom Hunter Technologies has recently been awarded a Phase 2 Navy SBIR award for BHTech’s proposal on implementing neural network algorithms on neuromorphic processors. During phase 1, BHTech has demonstrated in the superior performance of photonic based neurons within Continuous Neuromorphic Computing architectures for both electronic and hybrid-photonic hardware. In Phase 2, we will extend that work to create designs for a Neuromorphic Toolbox of solutions providing Electronic, Spiking Electronic and Hybrid Photonic hardware for Neural Network topologies. The Phase 2 Option will develop these designs into benchtop prototypes. The Phase 2 Option will also include the development of a VPX Neuromorphic Hardware that is HOST compatible. In Phase 3 we will be looking at optimizing solutions for the Navy and creating deployable Neuromorphic Hardware. This will be based on the Neuromorphic Hardware Toolbox that was started in Phase 2 as well as the development of BASE (Bascom Hunter’s AI Software Environment), which will aid the rapid migration of machine learning algorithms from Desktop Computing Systems to Edge Computing modules.
Neuromorphic Processors provide a realistic solution to obtaining real-time insights for the warfighter by leveraging an architecture that more closely resembles the Human Brain and are better suited to run Neural Network models. Our toolbox approach allows the best hardware architectures to be matched with the best software solutions, enabling the rapid conversion of cutting-edge technology into ruggedized, modular hardware. Our Hardware and Software Toolboxes will bring immediate benefits to warfighters in the Navy and beyond by extracting actionable insights in real-time at the edge (eliminating the latency problem when processing in the cloud). One application is the real-time identification of Radio Frequency (RF) emitters using Neuromorphic processors operating via trained Neural Networks.
To learn more about Bascom Hunter Technologies’ neuromorphic processor design capabilities or our strategies to improve network throughput, latency, and power consumption, contact us at: Contact Us – Bascom Hunter

 

[Esq.111]

Morning Quatrojos,

Great find, should get tongues a wagging.

WooooHooo.

Regards,
Esq.

 

[Deleted member 118]

thats Gold!
View attachment 3216

High Dynamic Range, Low Noise Optical Link for Reduced SWaP | SBIR.gov

www.sbir.gov

HPSC-Compatible Neuromorphic Photonic Coprocessor | SBIR.gov

www.sbir.gov

Neuromorphic Processors for Next Generation Systems | SBIR.gov

www.sbir.gov

Massively Parallel Photonic Artificial Neural Network Accelerator | SBIR.gov

www.sbir.gov

Basic info into the technology they are using

Photonics for artificial intelligence and neuromorphic computing

Photonics for artificial intelligence and neuromorphic computing - Nature Photonics

Photonics offers an attractive platform for implementing neuromorphic computing due to its low latency, multiplexing capabilities and integrated on-chip technology.

www.nature.com

 

[Foxdog]

https://www.motor1.com/news/575973/mercedes-amg-autonomous-hot-laps/ Wow AMG

Would love to know if/how much of AKIDA is integrated into the autonomous tech.

 

[Taproot]

Someone call the fire brigade, you all on fire this morning.
Bascom Hunter - Paul Prucnal out of Princeton was one of the original founders, seems pretty switched on guy.
That Merc hot lap was crazy.

 

[Fact Finder]

3/17/2022 Press Release - BHTech wins Phase II SBIR Award for Implementing Neural Network Algorithms on Neuromorphic Processors

The generation of real-time insights for the warfighter is an increasingly important area of interest, especially due to the growth of Electronic Warfare challenges. These insights require faster processors and smarter models that can be deployed at the edge in low Size, Weight and Power (SWaP)...

xcelaero.com

I was digging into their web site. I am not sure how Brainchip fits in to their NASA application but I found the following which given Rob Telson's sudden interest in monitoring fans is interesting to ponder:

High Performance Fans & Air Movers

SMALLER, LIGHTER AND MORE FLOW

Smaller, Lighter, More flow. The demanding requirements of A&D systems require high flow rates, high-pressure, high efficiency, and low noise. Xcelaero provides solutions for these applications with standard and custom vane axial, mixed flow, and centrifugal fans. Xcelaero has 4 series of fans that are available in different diameters and motor types:

Flow: Xcelaero’s Flow series of fans are axial and vane axial fans designed to be robust, light weight, and compact, and have been optimized for low pressure applications in the aerospace and defense market. The fans in the Flow series can provide between 25 cfm and 5,000 cfm of flow. The fans are available with a variety of motors and can run off AC or DC power. If an existing fan does not meet your requirements, Xcelaero can design a custom fan for your application.

Force: Xcelaero’s Force series of fans are optimized for cost and performance. The Force fans are vane axial fans designed to be robust, light weight, compact and low noise for the aerospace and defense market. The fans in this series can provide between 150 cfm and 2,400 cfm of flow. The fans are available with a variety of motors and can run off AC or DC power. If an existing fan does not meet your requirements, Xcelaero can design a custom fan for your application.

Galeforce: Xcelaero’s Galeforce series of fans are optimized for high performance, high efficiency, and low weight. The Galeforce fans are high-performance vane axial fans designed to be robust, light weight, compact, and low noise for the aerospace and defense market. Galeforce fans utilize 5 axis machined impellers and guide vanes to maximize performance. The fans in this series can provide between 200 cfm and 20,500 cfm of flow. The fans are available with a variety of motors and can run off AC or DC power. If an existing fan does not meet your requirements, Xcelaero can design a custom fan for your application.

Helios: Xcelaero’s Helios series of fans are optimized for high pressure applications. The Helios fans are high-performance centrifugal fans designed to be robust, light weight, compact and low noise for the aerospace and defense market. The fans in this series can provide between 50 cfm and 9,000 cfm of flow. If an existing fan does not meet your requirements, Xcelaero can design a custom fan for your application.

Markets

bascomhunter.com

My opinion only DYOR
FF

AKIDA BALLISTA

 

[Fact Finder]

High Dynamic Range, Low Noise Optical Link for Reduced SWaP | SBIR.gov

www.sbir.gov

HPSC-Compatible Neuromorphic Photonic Coprocessor | SBIR.gov

www.sbir.gov

Neuromorphic Processors for Next Generation Systems | SBIR.gov

www.sbir.gov

Massively Parallel Photonic Artificial Neural Network Accelerator | SBIR.gov

www.sbir.gov

Basic info into the technology they are using

Photonics for artificial intelligence and neuromorphic computing

Photonics for artificial intelligence and neuromorphic computing - Nature Photonics

Photonics offers an attractive platform for implementing neuromorphic computing due to its low latency, multiplexing capabilities and integrated on-chip technology.

www.nature.com

Over on the other place I used harp on about how the term "real time" processing had a specific meaning in the world of semiconductors and that AKIDA technology processes in real time and faster than the human brain. I have extracted the following from the application Rocket posts above and leave it to you to consider the implications:

"The TPU classification engine can process 280,000 inferences per second, but the response time remains around 10 ms. Defense applications requiring real-time processing, such as GPS-less navigation in the jammed battlefield. With digital electronics, such as TPU, the first issue is the processing latency. Real-time feedback based on such a latency (i.e. ~10 ms) would limit the processing bandwidth of only 100 Hz. Hypersonic aircraft and missile tracking, for example, requires feedback loop latency of under 1 ms.The second issue is the bandwidth of each data channel. For example, command of the radio spectrum requires real-time processing of many GHz signals, e.g. suppressing jamming and interference in adversarial environments. This is only made possible with reconfigurable hardware that does not depend on synchronous clocks. The third issue is, defense applications need edge devices with predominantly low size, weight and power (SWaP)."

My opinion only DYOR
FF

AKIDA BALLISTA

 

[Neuromorphia]

3/17/2022 Press Release - BHTech wins Phase II SBIR Award for Implementing Neural Network Algorithms on Neuromorphic Processors

The generation of real-time insights for the warfighter is an increasingly important area of interest, especially due to the growth of Electronic Warfare challenges. These insights require faster processors and smarter models that can be deployed at the edge in low Size, Weight and Power (SWaP)...

xcelaero.com

BHTech has proposed to the United States Navy an implementation strategy using neuromorphic processors to accommodate modern SWaP and performance requirements of the warfighter

SWaP explained

What is Low-SWaP?

The prominence of the acronym has been primarily driven by military requirements and industry trends toward smaller more powerful devices.

www.redcom.com

 

[Bravo]

Any thoughts on quantum AKIDA?

Artificial neurons go quantum with photonic circuits

Quantum memristor as missing link between artificial intelligence and quantum computing.

www.nanowerk.com

Mar 24, 2022

Artificial neurons go quantum with photonic circuits​ (Nanowerk News) In recent years, artificial intelligence has become ubiquitous, with applications such as speech interpretation, image recognition, medical diagnosis, and many more. At the same time, quantum technology has been proven capable of computational power well beyond the reach of even the world’s largest supercomputer.

Physicists at the University of Vienna have now demonstrated a new device, called quantum memristor, which may allow to combine these two worlds, thus unlocking unprecedented capabilities. The experiment, carried out in collaboration with the National Research Council (CNR) and the Politecnico di Milano in Italy, has been realized on an integrated quantum processor operating on single photons.

The work is published in the current issue of the journal Nature Photonics ("Experimental quantum memristor").

At the heart of all artificial intelligence applications are mathematical models called neural networks. These models are inspired by the biological structure of the human brain, made of interconnected nodes.

Just like our brain learns by constantly rearranging the connections between neurons, neural networks can be mathematically trained by tuning their internal structure until they become capable of human-level tasks: recognizing our face, interpreting medical images for diagnosis, even driving our cars.

Having integrated devices capable of performing the computations involved in neural networks quickly and efficiently has thus become a major research focus, both academic and industrial.

One of the major game changers in the field was the discovery of the memristor, made in 2008. This device changes its resistance depending on a memory of the past current, hence the name memory-resistor, or memristor. Immediately after its discovery, scientists realized that (among many other applications) the peculiar behavior of memristors was surprisingly similar to that of neural synapses. The memristor has thus become a fundamental building block of neuromorphic architectures.

A group of experimental physicists from the University of Vienna, the National Research Council (CNR) and the Politecnico di Milano led by Prof. Philip Walther and Dr. Roberto Osellame, have now demonstrated that it is possible to engineer a device that has the same behavior as a memristor, while acting on quantum states and being able to encode and transmit quantum information.

In other words, a quantum memristor. Realizing such device is challenging because the dynamics of a memristor tends to contradict the typical quantum behavior.

By using single photons, i.e. single quantum particles of lights, and exploiting their unique ability to propagate simultaneously in a superposition of two or more paths, the physicists have overcome the challenge.

In their experiment, single photons propagate along waveguides laser-written on a glass substrate and are guided on a superposition of several paths. One of these paths is used to measure the flux of photons going through the device and this quantity, through a complex electronic feedback scheme, modulates the transmission on the other output, thus achieving the desired memristive behavior.

Besides demonstrating the quantum memristor, the researchers have provided simulations showing that optical networks with quantum memristor can be used to learn on both classical and quantum tasks, hinting at the fact that the quantum memristor may be the missing link between artificial intelligence and quantum computing.

“Unlocking the full potential of quantum resources within artificial intelligence is one of the greatest challenges of the current research in quantum physics and computer science”, says Michele Spagnolo, who is first author of the publication in the journal Nature Photonics.

The group of Philip Walther of the University of Vienna has also recently demonstrated that robots can learn faster when using quantum resources and borrowing schemes from quantum computation. This new achievement represents one more step towards a future where quantum artificial intelligence become reality.

Source: University of Vienna

 

[Deleted member 118]

Over on the other place I used harp on about how the term "real time" processing had a specific meaning in the world of semiconductors and that AKIDA technology processes in real time and faster than the human brain. I have extracted the following from the application Rocket posts above and leave it to you to consider the implications:

"The TPU classification engine can process 280,000 inferences per second, but the response time remains around 10 ms. Defense applications requiring real-time processing, such as GPS-less navigation in the jammed battlefield. With digital electronics, such as TPU, the first issue is the processing latency. Real-time feedback based on such a latency (i.e. ~10 ms) would limit the processing bandwidth of only 100 Hz. Hypersonic aircraft and missile tracking, for example, requires feedback loop latency of under 1 ms.The second issue is the bandwidth of each data channel. For example, command of the radio spectrum requires real-time processing of many GHz signals, e.g. suppressing jamming and interference in adversarial environments. This is only made possible with reconfigurable hardware that does not depend on synchronous clocks. The third issue is, defense applications need edge devices with predominantly low size, weight and power (SWaP)."

My opinion only DYOR
FF

AKIDA BALLISTA

https://arxiv.org/pdf/2202.08897.pdf

 

[Fact Finder]

BHTech has proposed to the United States Navy an implementation strategy using neuromorphic processors to accommodate modern SWaP and performance requirements of the warfighter

SWaP explained

What is Low-SWaP?

The prominence of the acronym has been primarily driven by military requirements and industry trends toward smaller more powerful devices.

www.redcom.com

The other important criteria that goes hand in hand with SWaP is COTS. When Tensor Innovation Partners were first identified by @uiux back in 2020 the fact of AKIDA being COTS was a great asset to its adoption by NASA and this became clear as NASA/DARPA acquisition policies were found and revealed by the 1,000 Eyes and Vorago was revealed as an EAP.

The dots are looking quite large and very dark on this one.

My opinion only DYOR
FF

AKIDA BALLISTA

 

[Potato]

Essentially, the chips can be used in anything. It's more about which industry wants it the most.
I would have thought that the Car Industry would be at the forefront of BRN's mind. Assuming it is and with the world's fast tracked change to a more clean energy/efficient mode of transportation, i would think we are on the verge of signing something very good.

I would have thought the money was in the car industry, not the mobile industry.

 

[Potato]

With the combined experience of Sean and Viana in this industry, i would say (IMO) that we are not too far off a deal.

 

[Fact Finder]

Essentially, the chips can be used in anything. It's more about which industry wants it the most.
I would have thought that the Car Industry would be at the forefront of BRN's mind. Assuming it is and with the world's fast tracked change to a more clean energy/efficient mode of transportation, i would think we are on the verge of signing something very good.

I would have thought the money was in the car industry, not the mobile industry.

Most certainly there is money in automotive for Brainchip but remember the acting CEO Peter van der Made, the then VP of Sales and Marketing Rob Telson put forward last year that they were going to saturate the Edge market. Not we are going to saturate an Edge market. They also used the word ubiquitous to describe what they had planned for AKIDA and did not qualify it as just being the automotive market where this was going to happen. The new CEO Sean Hehir has not stated otherwise than his one comment about focus.

Then we have both Renesas and MegaChips who cover more than just automotive and MegaChips actually list mobile phones as a potential use case for AKIDA technology.

Then there is the Nanose SniffPhone idea which clearly needs a mobile phone to fulfil the description.

There are so many other Smart Health applications which can be processed through mobile phones but if they cause the phone to need a recharge every 30 minutes are likely not going to be picked up but a 3 to 5 day phone life they become the marketing edge for a phone company.

I was reading an article yesterday probably posted here by someone but it was basically saying that do not expect your new phone to be much more revolutionary than the last one because battery life was greatly restricting added innovations.

I am not saying Brainchip is in bed with a mobile phone company but I am saying it cannot be discounted on the basis of known facts.

Also on the Mercedes EQXX front remember the concept also includes turning it into a technology hub linked to your Smartphone, your Smartoffice, your Smarthome it could be argued that just this one known fact makes it more likely than not that phones using AKIDA technology are already on the table.

My opinion only DYOR
FF

AKIDA BALLISTA

 

[Fact Finder]

I was very taken with the Chief Financial Officer's statement in his presentation to German investors that AKIDA technology was going to disrupt industries that did not exist yet. It is very hard to imagine an industry that does not exist yet without thinking you are as was said in the Castle 'dreaming'.

Occasionally though I come across things that are far from dreaming and just now I found this article covering a recently released patent from Suzuki and as the article states there is no one yet manufacturing boots and pants containing the sensors necessary to make it work. Wearable sensors now where have I heard that mentioned recently?

Not mentioned in the article but a boot sensor could monitor your pulse which might be useful to emergency responders.

MSN

My opinion only DYOR
FF

AKIDA BALLISTA

 

[Potato]

Most certainly there is money in automotive for Brainchip but remember the acting CEO Peter van der Made, the then VP of Sales and Marketing Rob Telson put forward last year that they were going to saturate the Edge market. Not we are going to saturate an Edge market. They also used the word ubiquitous to describe what they had planned for AKIDA and did not qualify it as just being the automotive market where this was going to happen. The new CEO Sean Hehir has not stated otherwise than his one comment about focus.

Then we have both Renesas and MegaChips who cover more than just automotive and MegaChips actually list mobile phones as a potential use case for AKIDA technology.

Then there is the Nanose SniffPhone idea which clearly needs a mobile phone to fulfil the description.

There are so many other Smart Health applications which can be processed through mobile phones but if they cause the phone to need a recharge every 30 minutes are likely not going to be picked up but a 3 to 5 day phone life they become the marketing edge for a phone company.

I was reading an article yesterday probably posted here by someone but it was basically saying that do not expect your new phone to be much more revolutionary than the last one because battery life was greatly restricting added innovations.

I am not saying Brainchip is in bed with a mobile phone company but I am saying it cannot be discounted on the basis of known facts.

Also on the Mercedes EQXX front remember the concept also includes turning it into a technology hub linked to your Smartphone, your Smartoffice, your Smarthome it could be argued that just this one known fact makes it more likely than not that phones using AKIDA technology are already on the table.

My opinion only DYOR
FF

AKIDA BALLISTA

well said FF.


AKIDA BALLISTA EVERYONEE

 

[Quatrojos]

Asynchronous Neuromorphic Digital Readout Circuit for Infrared Cameras for Autonomous Target Acquisition and Autonomous Vehicles – Army SBIR|STTR Program

...
4) A. Vanarse, et al, “A Review of Current Neuromorphic Approaches for Vision Auditory and Olfactory Sensors,” Frontiers in Neuroscience, vol. 10, Article 115, Mar. 2016

Akida is becoming embedded in the zeitgeist of AI...

 

[Taproot]

Asynchronous Neuromorphic Digital Readout Circuit for Infrared Cameras for Autonomous Target Acquisition and Autonomous Vehicles – Army SBIR|STTR Program

...
4) A. Vanarse, et al, “A Review of Current Neuromorphic Approaches for Vision Auditory and Olfactory Sensors,” Frontiers in Neuroscience, vol. 10, Article 115, Mar. 2016

Akida is becoming embedded in the zeitgeist of AI...

Link did not work, so have just reposted with a little context for any new comers who may not know who Anup is.

Asynchronous Neuromorphic Digital Readout Circuit for Infrared Cameras for Autonomous Target Acquisition and Autonomous Vehicles – Army SBIR|STTR Program

Frontiers | A Review of Current Neuromorphic Approaches for Vision, Auditory, and Olfactory Sensors

Conventional vision, auditory, and olfactory sensors generate large volumes of redundant data and as a result tend to consume excessive power. To address the...

www.frontiersin.org

https://www.linkedin.com/in/anup-vanarse/?originalSubdomain=au

 

[Bravo]

Sandia Labs' latest news release from the 10th March 2022.

The researchers used the 50-million-chip Loihi platform that Sandia received approximately a year and a half ago from Intel Corp. And the article states "The next version of Loihi, said Sandia researcher Craig Vineyard, will increase its current chip scale from 128,000 neurons per chip to up to one million."

Imagine then what Akida could do with its 1.2 million virtual neurons and 10 billion virtual synapses? Interestingly enough Sandia have been aware of BrainChip for quite a while as this slide from a presentation of theirs in 2017 shows.

Extract

The findings, detailed in a recent article in the journal Nature Electronics, show that neuromorphic simulations using the statistical method called random walks can track X-rays passing through bone and soft tissue, disease passing through a population, information flowing through social networks and the movements of financial markets, among other uses, said Sandia theoretical neuroscientist and lead researcher James Bradley Aimone.

“Basically, we have shown that neuromorphic hardware can yield computational advantages relevant to many applications, not just artificial intelligence to which it’s obviously kin,” said Aimone. “Newly discovered applications range from radiation transport and molecular simulations to computational finance, biology modeling and particle physics.”

Neuromorphic computing widely applicable, Sandia researchers show

ALBUQUERQUE, N.M. — With the insertion of a little math, Sandia National Laboratories researchers have shown that neuromorphic computers, which synthetically replicate the brain’s logic, can solve more complex problems than those posed by artificial intelligence and may …

newsreleases.sandia.gov

Sandia Labs ? Neural Sommelier. (Conference) | OSTI.GOV

The U.S. Department of Energy's Office of Scientific and Technical Information

www.osti.gov

 

[Taproot]

Link did not work, so have just reposted with a little context for any new comers who may not know who Anup is.

Asynchronous Neuromorphic Digital Readout Circuit for Infrared Cameras for Autonomous Target Acquisition and Autonomous Vehicles – Army SBIR|STTR Program

Frontiers | A Review of Current Neuromorphic Approaches for Vision, Auditory, and Olfactory Sensors

Conventional vision, auditory, and olfactory sensors generate large volumes of redundant data and as a result tend to consume excessive power. To address the...

www.frontiersin.org

https://www.linkedin.com/in/anup-vanarse/?originalSubdomain=au

OK, link still did not work, but will if you copy and paste into your browser

Release Date: 11/16/2021​

Open Date: 11/30/2021​

Application Due Date: 01/04/2022​

Close Date: 01/04/2022​

Solicitation: 21.4​

Topic Number: A214-051​

Duration: Up to 6 months​

Amount Up To: $250K​

Most military scenarios consist of highly cluttered and dynamic scenes. Asynchronous on chip smart event cameras can eliminate cluttered scenarios with a much-reduced latency, power, and would be able to hand off images of interest to imbedded autonomous target algorithms. Development of a smart digital readout circuit, with embedded processing, containing this capability would significantly enhance infrared cameras for use in autonomous detection. The objective of this topic is to take this new technology and apply it to the 3GEN FLIR program and all other systems that use or will use 3GEN FLIR Cameras.