BRN Discussion Ongoing

[Bravo]

I did not request their White Paper which provides on the description a roadmap towards Ai at the Edge. It does by implication suggest that they are saying in 2022 that they are not yet where they were claiming to be in 2020.

I did not see anyone limping on the website but they could still be off undergoing rehab to learn how to walk with a hole in their foot.

My opinion only DYOR
FF

AKIDA BALLISTA

Here's something from Imec's Reading Room posted 31 May 2021. This includes a lot more technical information in which imec refer to adaptive neurons. Perhaps @Diogenese could take a look.




In April 2020, imec introduced the world’s first chip to process radar signals using a spiking recurrent neural network (SNN). Its flagship use-case? The creation of a smart, low-power multi-sensor perception system for drones that identifies obstacles in a matter of milliseconds.
Contrary to the artificial neural networks that are a key ingredient of today’s robotics perception systems, SNNs mimic the way groups of biological neurons operate – firing electrical pulses sparsely over time, and, in the case of biological sensory neurons, only when the sensory input changes. It is an approach that comes with important benefits: at the time of the announcement, imec’s SNN chip showed to consume up to a hundred times less power than traditional implementations while featuring a tenfold reduction in latency – enabling almost instantaneous decision-making.

In the following article, Ilja Ocket – program manager of neuromorphic sensing at imec – provides more insights into some of imec’s recent advances in this domain.

Optimizing and scaling up the original SNN chip​

In the last year, imec has been optimizing and scaling up its original SNN chip – the details of which were recently published in ‘Frontiers in Neuroscience’ – to host a variety of (IoT and autonomous robotics) use-cases. The chip builds on an entirely event-based digital architecture, and was implemented in low-cost 40nm CMOS technology. It supports event-driven processing and relies on local on-demand oscillators and a novel delay-cell to avoid the use of a global clock. Moreover, it does not exploit separate memory blocks; instead, memory and computation are co-localized in the IC area to avoid data access and energy overheads.

Imec’s SNN ranks amongst the top performers in terms of inference accuracy​

Meanwhile, research with the Dutch national research institute for mathematics and computer science (CWI), confirms that spiking neurons with adaptive thresholds can be trained to achieve top-notch inference accuracy. A comprehensive study conducted by imec and CWI aimed to benchmark SNNs using adaptive neurons against six other neural networks. To do so, eight different data sets were used – including Google’s radar (SoLi) and Google’s speech datasets. The study clearly pointed out that SNNs using neurons with adaptive thresholds can achieve a low energy consumption, but not at the expense of a decreased inference accuracy. On the contrary: for each of the major data sets used in the study, the imec SNN ranked amongst the top performers in terms of accuracy.

Imec’s adaptive neuron-based SNN (‘Adaptive SRNN’) was evaluated against six other neural networks – using eight different data sets including Google’s radar (SoLi) and Google’s speech datasets.
“SNN technology will find its way in a broad range of use-cases: from smart, self-learning Internet of Things (IoT) devices – such as wearables and brain-computer interface applications – to autonomous drones and robots. But each of those use-cases comes with its own set of requirements”, says Ilja Ocket. “While spiking neural networks for IoT applications should excel at operating within a very small power budget, autonomous drones demand a low-latency SNN that allows them to avoid obstacles quickly and effectively.”
“Addressing those requirements using a one-size-fits-all SNN architecture is extremely challenging. A delicate balance needs to be struck between energy consumption, latency, accuracy, cost (chip area) and scalability. For example, an SNN with the lowest possible energy consumption and latency typically results in an increased chip area – and vice versa. Finding that balance is one of imec’s SNN focus areas.”

Going forward: spiking all the way​

Drones are being used in an increasing number of application domains. Still, to improve their level of autonomy and to have them operate in more challenging environments (such as bad weather conditions), their sensing capabilities require yet another boost. According to Ilja Ocket, an end-to-end spiking approach – based on fused neuromorphic radar and camera inputs – might offer a way out.
Ilja Ocket: “This obviously makes for a highly energy-efficient and super low latency system. Today, however, in order to connect such cameras to the underlying AI, one still needs to translate their feed into frames – which significantly limits the efficiency gains. That is why we are investigating how the spiking concept can be implemented end-to-end: from the cameras and sensors to the AI engine. We are actually the first ones to do so, with very promising results so far. To that end, we are still looking for companies from across the drone industry – such as OEM drone builders – to join our program and experiment with this exciting technology.”

Imec’s end-to-end spiking approach at work. Local feature detection forms the first layer for a more complex semantic build-up.

Ilja Ocket
Program Manager of Neuromorphic Sensing at imec

Ilja Ocket, Program Manager of Neuromorphic Sensing at imec, aims to develop technologies for autonomous robotics. His focus is on the intersection between advanced sensor developments and neuromorphic compute architectures.
More about these topics:
Artificial intelligence
Radar
Industry 4.0 & robotics
Published on:
31 May 2021
Share this article on
https://www.imec-int.com/en/articles/imecs-snn-chip-combines-low-latency-energy-consumption-high-inference-accuracy
https://www.imec-int.com/en/reading-room

 

[Diogenese]

Just to be clear it is EP3671748A1 IN-MEMORY COMPUTING FOR MACHINE LEARNING that has been abandoned.

Does that then mean IMEC only have as far as we know the original patent for an analog SNN?

Many thanks @Diogenese

My opinion only DYOR
FF

AKIDA BALLISTA

IMEC have about 60 patents which are related to NNs.

https://worldwide.espacenet.com/pat...A1?q=pa = "imec" AND nftxt = "neural network"

Many relate to analog NNs eg:

US2020210822A1 Multibit Neural Network
EP3671750A1 SYNAPSE CIRCUIT WITH MEMORY
EP3968208A1 ANALOG IN-MEMORY COMPUTING BASED INFERENCE ACCELERATOR
...

However IMEC does have other digital NNs, but they may be short of rare condiment.

EP3671568A1 BINARY RECURRENT NEURAL NETWORK INFERENCE TECHNIQUE

[006] ... They also propose binarization of the network activations (of inputs and hidden states) based on an equivalent formulation of the recurrences in the neural network. This results in reduced memory requirements for the learnt weights and the replacement of multiply-and-accumulate operations for the binarized activations and binarized hidden layer weights by simpler XNOR operations. Binarizing the activations, however, does not replace all the accumulate operations of the recurrent update equation by simpler XNOR operations. Binarizing the activations in a long short-term memory layer work is ambiguous, because it is not sure which outcome of a non-linear activation should be binarized. If this is applied to the non-linear activations of the cell states, the resulting hidden state vectors are non-binary and not suitable for an energy-efficient hardware implementation.

I haven't seen any reference to STDP.

EP3674982A1 HARDWARE ACCELERATOR ARCHITECTURE FOR CONVOLUTIONAL NEURAL NETWORK

A hardware accelerator architecture (10) for a convolutional neural network comprises a first memory (11) for storing NxM activation inputs of an input tensor; a plurality of processor units (12) each comprising a plurality of Multiply ACcumulate (MAC) arrays (13) and a filter weights memory (14) associated with and common to the plurality of MAC arrays of one processor unit (12). Each MAC array is adapted for receiving a predetermined fraction (FxF) of the NxM activation inputs from the first memory, and filter weights from the associated filter weights memory (14). Each MAC array is adapted for subsequently, during different cycles, computing and storing different partial sums, while reusing the received filter weights, such that every MAC array computes multiple parts of columns of an output tensor, multiplexed in time. Each MAC array further comprises a plurality of accumulators (18) for making a plurality of full sums from the partial sums made at subsequent cycles.

"during different cycles" implies synchronous operation. Akida is asynchronous.

The fact that EP3671748A1 IN-MEMORY COMPUTING FOR MACHINE LEARNING has been abandoned does not mean that IMEC are not using the system.

 

[Fact Finder]

Rodolphe Sepulchre, Professor of Engineering, Control Group, Department of Engineering​

Professor Rodolphe Sepulchre
Project: Spiking Control Systems: an algorithmic theory for control design of physical event-based systems (SpikyControl)

Overview: “Spikes and rhythms organise control and communication in the animal world, in contrast to the bits and clocks of digital technology,” says Sepulchre. “Spiking control systems aim at imitating the spiking nature of animal computation, combining the adaptation of analogue physical systems and the reliability of digital automata.

“The project will explore novel control strategies to interconnect event-based sensors and actuators and will test them both in electrophysiological and electronic environments. Spiking control systems could enable an entirely novel generation of brain-inspired functionalities in machine intelligence and in neural interfaces.”

---

“ERC is unique in encouraging researchers to venture into unchartered territories. I feel privileged that it will fund my research for the next five years.”​

Professor Rodolphe Sepulchre

Nine Cambridge academics have won Advanced Grants awarded by the European Research Council (ERC). This is the greatest number of grants won by a UK institution in the 2021 round of funding.​

Advanced Grants are awarded to leading researchers who are established in their field and have a recognised track record of achievements. The Cambridge grantees are Professor Anuj Dawar, Professor Vikram Deshpande, Professor Paul Dupree, Professor Matthew Gaunt, Dr Florian Markowetz, Professor Pierre Raphael, Professor Erwin Reisner, Professor Rodolphe Sepulchre and Professor Ivan Smith.

“I’d like to offer my congratulations to our nine grantees,” says Professor Anne Ferguson-Smith, Pro-Vice-Chancellor for Research. “Each of the awardees has made outstanding contributions to their field and the ERC funding they have secured is testament to this.

“This funding will allow our grantees to pursue innovative ambitious research projects at the cutting edge of their disciplines and their success reminds us of the greatly valued contribution of ERC funding programmes to our research environment.”

The ERC is the premier European funding organisation for excellent frontier research. The 2021 Advanced Grants competition will see funding worth €624 million going to 253 leading researchers across Europe. This year, the UK has received grants for 45 projects, Germany 61, the Netherlands 27 and France 26. The overall ERC budget from 2021 to 2027 is more than €16 billion, as part of the Horizon Europe programme

 

[Fact Finder]

Rodolphe Sepulchre, Professor of Engineering, Control Group, Department of Engineering​

Professor Rodolphe Sepulchre
Project: Spiking Control Systems: an algorithmic theory for control design of physical event-based systems (SpikyControl)

Overview: “Spikes and rhythms organise control and communication in the animal world, in contrast to the bits and clocks of digital technology,” says Sepulchre. “Spiking control systems aim at imitating the spiking nature of animal computation, combining the adaptation of analogue physical systems and the reliability of digital automata.

“The project will explore novel control strategies to interconnect event-based sensors and actuators and will test them both in electrophysiological and electronic environments. Spiking control systems could enable an entirely novel generation of brain-inspired functionalities in machine intelligence and in neural interfaces.”

---

“ERC is unique in encouraging researchers to venture into unchartered territories. I feel privileged that it will fund my research for the next five years.”​

Professor Rodolphe Sepulchre

Nine Cambridge academics have won Advanced Grants awarded by the European Research Council (ERC). This is the greatest number of grants won by a UK institution in the 2021 round of funding.​

Advanced Grants are awarded to leading researchers who are established in their field and have a recognised track record of achievements. The Cambridge grantees are Professor Anuj Dawar, Professor Vikram Deshpande, Professor Paul Dupree, Professor Matthew Gaunt, Dr Florian Markowetz, Professor Pierre Raphael, Professor Erwin Reisner, Professor Rodolphe Sepulchre and Professor Ivan Smith.

“I’d like to offer my congratulations to our nine grantees,” says Professor Anne Ferguson-Smith, Pro-Vice-Chancellor for Research. “Each of the awardees has made outstanding contributions to their field and the ERC funding they have secured is testament to this.

“This funding will allow our grantees to pursue innovative ambitious research projects at the cutting edge of their disciplines and their success reminds us of the greatly valued contribution of ERC funding programmes to our research environment.”

The ERC is the premier European funding organisation for excellent frontier research. The 2021 Advanced Grants competition will see funding worth €624 million going to 253 leading researchers across Europe. This year, the UK has received grants for 45 projects, Germany 61, the Netherlands 27 and France 26. The overall ERC budget from 2021 to 2027 is more than €16 billion, as part of the Horizon Europe programme

Not sure why but it would not let me add my text to the above post.

Anyway it seems to me that they are funding Professor Sepluchre to look at how to process the spikes from an event based sensor. He is very pleased to have the next five years to work on the problem.

I seem to recall that Anil Mankar showed in 2020 AKIDA processing spikes from a Samsung DVS camera.

If I understand what the good professor is going to work on correctly Peter van der Made and Anil Mankar seem to have a bit of a head start.

If it was the Stawell Gift I know who I would bet on. The runner starting off 119 metres only has to fall over to win.

My opinion only DYOR
FF

AKIDA BALLISTA

 

[Fact Finder]

IMEC have about 60 patents which are related to NNs.

https://worldwide.espacenet.com/patent/search/family/070189674/publication/EP3889900A1?q=pa = "imec" AND nftxt = "neural network"

Many relate to analog NNs eg:

US2020210822A1 Multibit Neural Network
EP3671750A1 SYNAPSE CIRCUIT WITH MEMORY
EP3968208A1 ANALOG IN-MEMORY COMPUTING BASED INFERENCE ACCELERATOR
...

However IMEC does have other digital NNs, but they may be short of rare condiment.

EP3671568A1 BINARY RECURRENT NEURAL NETWORK INFERENCE TECHNIQUE

[006] ... They also propose binarization of the network activations (of inputs and hidden states) based on an equivalent formulation of the recurrences in the neural network. This results in reduced memory requirements for the learnt weights and the replacement of multiply-and-accumulate operations for the binarized activations and binarized hidden layer weights by simpler XNOR operations. Binarizing the activations, however, does not replace all the accumulate operations of the recurrent update equation by simpler XNOR operations. Binarizing the activations in a long short-term memory layer work is ambiguous, because it is not sure which outcome of a non-linear activation should be binarized. If this is applied to the non-linear activations of the cell states, the resulting hidden state vectors are non-binary and not suitable for an energy-efficient hardware implementation.

I haven't seen any reference to STDP.

EP3674982A1 HARDWARE ACCELERATOR ARCHITECTURE FOR CONVOLUTIONAL NEURAL NETWORK

A hardware accelerator architecture (10) for a convolutional neural network comprises a first memory (11) for storing NxM activation inputs of an input tensor; a plurality of processor units (12) each comprising a plurality of Multiply ACcumulate (MAC) arrays (13) and a filter weights memory (14) associated with and common to the plurality of MAC arrays of one processor unit (12). Each MAC array is adapted for receiving a predetermined fraction (FxF) of the NxM activation inputs from the first memory, and filter weights from the associated filter weights memory (14). Each MAC array is adapted for subsequently, during different cycles, computing and storing different partial sums, while reusing the received filter weights, such that every MAC array computes multiple parts of columns of an output tensor, multiplexed in time. Each MAC array further comprises a plurality of accumulators (18) for making a plurality of full sums from the partial sums made at subsequent cycles.

"during different cycles" implies synchronous operation. Akida is asynchronous.

The fact that EP3671748A1 IN-MEMORY COMPUTING FOR MACHINE LEARNING has been abandoned does not mean that IMEC are not using the system.

I think they need to read some of the papers coming out of China as they all seem to understand the need to use STDP to create an efficient SNN.

Not being hamstrung by a Western outdated sense of ethics and rule of law as IMEC is certainly has its advantages.

Mind you they are academic papers not patents so there is no suggestion they will lead to anything other than knowledge which is a more than worthy goal of which I approve.

My opinion only DYOR
FF

AKIDA BALLISTA

 

[Bravo]

Here's something from Imec's Reading Room posted 31 May 2021. This includes a lot more technical information in which imec refer to adaptive neurons. Perhaps @Diogenese could take a look.




In April 2020, imec introduced the world’s first chip to process radar signals using a spiking recurrent neural network (SNN). Its flagship use-case? The creation of a smart, low-power multi-sensor perception system for drones that identifies obstacles in a matter of milliseconds.
Contrary to the artificial neural networks that are a key ingredient of today’s robotics perception systems, SNNs mimic the way groups of biological neurons operate – firing electrical pulses sparsely over time, and, in the case of biological sensory neurons, only when the sensory input changes. It is an approach that comes with important benefits: at the time of the announcement, imec’s SNN chip showed to consume up to a hundred times less power than traditional implementations while featuring a tenfold reduction in latency – enabling almost instantaneous decision-making.

In the following article, Ilja Ocket – program manager of neuromorphic sensing at imec – provides more insights into some of imec’s recent advances in this domain.

Optimizing and scaling up the original SNN chip​

In the last year, imec has been optimizing and scaling up its original SNN chip – the details of which were recently published in ‘Frontiers in Neuroscience’ – to host a variety of (IoT and autonomous robotics) use-cases. The chip builds on an entirely event-based digital architecture, and was implemented in low-cost 40nm CMOS technology. It supports event-driven processing and relies on local on-demand oscillators and a novel delay-cell to avoid the use of a global clock. Moreover, it does not exploit separate memory blocks; instead, memory and computation are co-localized in the IC area to avoid data access and energy overheads.

Imec’s SNN ranks amongst the top performers in terms of inference accuracy​

Meanwhile, research with the Dutch national research institute for mathematics and computer science (CWI), confirms that spiking neurons with adaptive thresholds can be trained to achieve top-notch inference accuracy. A comprehensive study conducted by imec and CWI aimed to benchmark SNNs using adaptive neurons against six other neural networks. To do so, eight different data sets were used – including Google’s radar (SoLi) and Google’s speech datasets. The study clearly pointed out that SNNs using neurons with adaptive thresholds can achieve a low energy consumption, but not at the expense of a decreased inference accuracy. On the contrary: for each of the major data sets used in the study, the imec SNN ranked amongst the top performers in terms of accuracy.

Imec’s adaptive neuron-based SNN (‘Adaptive SRNN’) was evaluated against six other neural networks – using eight different data sets including Google’s radar (SoLi) and Google’s speech datasets.
“SNN technology will find its way in a broad range of use-cases: from smart, self-learning Internet of Things (IoT) devices – such as wearables and brain-computer interface applications – to autonomous drones and robots. But each of those use-cases comes with its own set of requirements”, says Ilja Ocket. “While spiking neural networks for IoT applications should excel at operating within a very small power budget, autonomous drones demand a low-latency SNN that allows them to avoid obstacles quickly and effectively.”
“Addressing those requirements using a one-size-fits-all SNN architecture is extremely challenging. A delicate balance needs to be struck between energy consumption, latency, accuracy, cost (chip area) and scalability. For example, an SNN with the lowest possible energy consumption and latency typically results in an increased chip area – and vice versa. Finding that balance is one of imec’s SNN focus areas.”

Going forward: spiking all the way​

Drones are being used in an increasing number of application domains. Still, to improve their level of autonomy and to have them operate in more challenging environments (such as bad weather conditions), their sensing capabilities require yet another boost. According to Ilja Ocket, an end-to-end spiking approach – based on fused neuromorphic radar and camera inputs – might offer a way out.
Ilja Ocket: “This obviously makes for a highly energy-efficient and super low latency system. Today, however, in order to connect such cameras to the underlying AI, one still needs to translate their feed into frames – which significantly limits the efficiency gains. That is why we are investigating how the spiking concept can be implemented end-to-end: from the cameras and sensors to the AI engine. We are actually the first ones to do so, with very promising results so far. To that end, we are still looking for companies from across the drone industry – such as OEM drone builders – to join our program and experiment with this exciting technology.”

Imec’s end-to-end spiking approach at work. Local feature detection forms the first layer for a more complex semantic build-up.

Ilja Ocket
Program Manager of Neuromorphic Sensing at imec

Ilja Ocket, Program Manager of Neuromorphic Sensing at imec, aims to develop technologies for autonomous robotics. His focus is on the intersection between advanced sensor developments and neuromorphic compute architectures.
More about these topics:
Artificial intelligence
Radar
Industry 4.0 & robotics
Published on:
31 May 2021
Share this article on
https://www.imec-int.com/en/articles/imecs-snn-chip-combines-low-latency-energy-consumption-high-inference-accuracy
https://www.imec-int.com/en/reading-room

I found the 'Frontiers in Neuroscience' paper that they refer to above. Amongst other things it states "In terms of sensor data processing, a major current challenge is to develop spike neural network learning principles, concurrently advancing both the algorithms and hardware, to enable the disparate sensor data fusion inherent to biological sensing."

Here's the part that refers to imec.

(Extract 1)

Another neuromorphic approach to active sensing, includes the world’s first spiking neural network-based chip that was announced recently for radar signal processing. The first application was reported to encompass the creation of a low-power smart anti-collision radar system for drone collision avoidance; future plans are to process a variety of active sensor data including electrocardiogram, speech, sonar, radar and LIDAR streams (Liu, 2020). Reportedly, the chip consumes 100 times less power than traditional implementations and provides 10X reduction in latency.


The algorithmic and hardware transitions to EB sensing platforms are driven by the desire to reduce latency, to achieve orders of magnitude improvement in energy efficiency, dynamic range, and sensitivity, to solve complex control problems with limited computing resources and to attain autonomous system’s capability of adapting to operation in unpredictable dynamic environments. Hence recently, they have been applied successfully in space surveillance applications (Roffe et al., 2021) and for controlled landing of micro-air vehicles (Dupeyroux et al., 2020). However, despite the progress achieved in the last decade by state-of-the-art neuromorphic sensors, there are several fundamental barriers separating them from real life applications. For example, visual EB sensors have limited ability to handle high focal plane array utilization due to complex illumination or clutter as well as pixel response inhomogeneity. In terms of sensor data processing, a major current challenge is to develop spike neural network learning principles, concurrently advancing both the algorithms and hardware, to enable the disparate sensor data fusion inherent to biological sensing.


The paper concludes with a long term goal which is detailed below.

(Extract 2)

We have identified a clear need to enhance understanding of neurosensory systems in nature’s flying creatures, which shall result in new and better mathematical models needed for autonomous flying vehicles, see Figure 1. The long-term goal is hardware and software design and prototyping for interacting autonomous vehicles. Our target is neuromorphic hardware that aims at mimicking the functions of neural cells in custom synthetic hardware that is analog, digital, and asynchronous in its nature of information processing and is vastly more energy-efficient and lighter than classical silicon circuitry. It is expected that such a neuromorphic technology will disrupt existing solutions and be a key enabler for real-time processing of different sensor modalities by lower cost, lower energy consumption, lower weight, adaptable to changing missions, while providing enhanced and resilient performance and saving human lives.

Autonomous Flying With Neuromorphic Sensing

Autonomous flight for large aircraft appears to be within our reach. However, launching autonomous systems for everyday missions still requires an immense interdisciplinary research effort supported by pointed policies and funding. We believe that concerted endeavors in the fields of...

www.frontiersin.org

 

[Fact Finder]

I found the 'Frontiers in Neuroscience' paper that they refer to above. Amongst other things it states "In terms of sensor data processing, a major current challenge is to develop spike neural network learning principles, concurrently advancing both the algorithms and hardware, to enable the disparate sensor data fusion inherent to biological sensing."

Here's the part that refers to imec.

(Extract 1)

Another neuromorphic approach to active sensing, includes the world’s first spiking neural network-based chip that was announced recently for radar signal processing. The first application was reported to encompass the creation of a low-power smart anti-collision radar system for drone collision avoidance; future plans are to process a variety of active sensor data including electrocardiogram, speech, sonar, radar and LIDAR streams (Liu, 2020). Reportedly, the chip consumes 100 times less power than traditional implementations and provides 10X reduction in latency.


The algorithmic and hardware transitions to EB sensing platforms are driven by the desire to reduce latency, to achieve orders of magnitude improvement in energy efficiency, dynamic range, and sensitivity, to solve complex control problems with limited computing resources and to attain autonomous system’s capability of adapting to operation in unpredictable dynamic environments. Hence recently, they have been applied successfully in space surveillance applications (Roffe et al., 2021) and for controlled landing of micro-air vehicles (Dupeyroux et al., 2020). However, despite the progress achieved in the last decade by state-of-the-art neuromorphic sensors, there are several fundamental barriers separating them from real life applications. For example, visual EB sensors have limited ability to handle high focal plane array utilization due to complex illumination or clutter as well as pixel response inhomogeneity. In terms of sensor data processing, a major current challenge is to develop spike neural network learning principles, concurrently advancing both the algorithms and hardware, to enable the disparate sensor data fusion inherent to biological sensing.


The paper concludes with a long term goal which is detailed below.

(Extract 2)

We have identified a clear need to enhance understanding of neurosensory systems in nature’s flying creatures, which shall result in new and better mathematical models needed for autonomous flying vehicles, see Figure 1. The long-term goal is hardware and software design and prototyping for interacting autonomous vehicles. Our target is neuromorphic hardware that aims at mimicking the functions of neural cells in custom synthetic hardware that is analog, digital, and asynchronous in its nature of information processing and is vastly more energy-efficient and lighter than classical silicon circuitry. It is expected that such a neuromorphic technology will disrupt existing solutions and be a key enabler for real-time processing of different sensor modalities by lower cost, lower energy consumption, lower weight, adaptable to changing missions, while providing enhanced and resilient performance and saving human lives.

Autonomous Flying With Neuromorphic Sensing

Autonomous flight for large aircraft appears to be within our reach. However, launching autonomous systems for everyday missions still requires an immense interdisciplinary research effort supported by pointed policies and funding. We believe that concerted endeavors in the fields of...

www.frontiersin.org

Thanks for this @Bravo. Perhaps we should send them an email telling them not to fear because Professor Sepulchre is working on their problem and could have an answer in five years. That should take the pressure off and they can go and get a coffee.

My opinion only DYOR
FF

AKIDA BALLISTA

 

[Bravo]

Thanks for this @Bravo. Perhaps we should send them an email telling them not to fear because Professor Sepulchre is working on their problem and could have an answer in five years. That should take the pressure off and they can go and get a coffee.

My opinion only DYOR
FF

AKIDA BALLISTA

I'm pretty sure @Dhm would be happy to write to them. He-he-he!

 

[Dhm]

I'm pretty sure @Dhm would be happy to write to them. He-he-he!

Sorry, it's my day off!

 

[Fact Finder]

Having had red herring for breakfast I thought we should stick with the theme and have something European for lunch:

“A real hot stock is BrainChip. Partners like Mercedes show that the Australians are on the right track."
https://www.inv3st.de/kommentare/ch...ercedes-partner-brainchip-nvidia-und-infineon

It is actually more than noteworthy that despite IMEC’s obvious status in Europe and their various claims to firsts in the SNN space particularly with radar that the quintessential European Brand Mercedes’ Benz is running with AKIDA technology and the main NATO player the USA’s own Airforce is funding ISL & Brainchip to develop a system which IMEC claimed to have mastered.

My opinion only DYOR
FF

AKIDA BALLISTA

 

[Bravo]

Morning TFM,

Cheers, just added.

Esq.

Fantastic list Esq! So handy since there's SOOO much going on!

Could you please add TC Sessions: Mobility 2022 May 18 and May 19? Herbert Diess (CEO Volkswagen) will be joining for an online portion of the event during which is going to talk about the company’s pursuits in EVs and autonomous vehicle technology, to his thoughts on the newer competitors like Tesla and how it has affected VW Group, to plans for the future. Might be worth listening to him talk about software and future technology.

TIA

https://techcrunch.com/events/tc-sessions-mobility-2022/

 

[Bravo]

I just saw this video on the Vinfast Futuristic VF8 on Cerence's twitter. Check out the INCREDIBLY INTELLIGENT and intuitive voice assistant!

At 5.50 It has a little camera that has face recogniiton and set's everything to your profile (moves your seat, etc).

At 6.20 She discusses how she doesn't have a car where the voice activation works this well.

At 7.30 It has a smart home services function to connect to smart home devices. Tallks about how they are all currently working out the contracts so can't mention all of the partners until these contracts have been fanalised.


Spoiler Alert: It looks like they're not using Akida, since it's integrated with Alexa.

VINFAST AND AMAZON ANNOUNCE PLANS TO INTEGRATE ALEXA VOICE AI INTO VF 8 AND VF 9 ELECTRIC VEHICLE MODELS

/PRNewswire/ -- VinFast, a global electric vehicle manufacturer, today announced plans to integrate the Amazon Alexa voice experience into its vehicles...

www.prnewswire.com

https://twitter.com/cerenceinc

 

[Proga]

Having had red herring for breakfast I thought we should stick with the theme and have something European for lunch:

“A real hot stock is BrainChip. Partners like Mercedes show that the Australians are on the right track."
https://www.inv3st.de/kommentare/ch...ercedes-partner-brainchip-nvidia-und-infineon

It is actually more than noteworthy that despite IMEC’s obvious status in Europe and their various claims to firsts in the SNN space particularly with radar that the quintessential European Brand Mercedes’ Benz is running with AKIDA technology and the main NATO player the USA’s own Airforce is funding ISL & Brainchip to develop a system which IMEC claimed to have mastered.

My opinion only DYOR
FF

AKIDA BALLISTA

I liked this bit FF. As we both know it will take time to bring the applications to market. More importantly, they're the first possible.

BrainChip recently reported a cooperation with nViso SA. According to the Swiss company, the technology is the only one capable of analyzing signals of human behavior such as facial expressions, emotions, identity, head position, looks, gestures, activities and objects with which users interact. In robotics and automotive applications, human behavior analysis recognizes the emotional state of the user to provide customized, adaptive, interactive, and safe devices and systems. This technology is to be integrated into BrainChip's Akida processors. The partners see the first possible applications in the field of robots and monitoring systems.

 

[Diogenese]

Having had red herring for breakfast I thought we should stick with the theme and have something European for lunch:

“A real hot stock is BrainChip. Partners like Mercedes show that the Australians are on the right track."
https://www.inv3st.de/kommentare/ch...ercedes-partner-brainchip-nvidia-und-infineon

It is actually more than noteworthy that despite IMEC’s obvious status in Europe and their various claims to firsts in the SNN space particularly with radar that the quintessential European Brand Mercedes’ Benz is running with AKIDA technology and the main NATO player the USA’s own Airforce is funding ISL & Brainchip to develop a system which IMEC claimed to have mastered.

My opinion only DYOR
FF

AKIDA BALLISTA

Red herring, 'umble pie and a bottle of shampain - Diogenese regular diet.

 

[Fact Finder]

For a more intellectual read head over to @IloveLamp post on the Nviso thread.

(My secret pleasure is the little dig the author has at Intel & IBM.)

My opinion only DYOR
FF

AKIDA BALLISTA

 

[Fact Finder]

For a more intellectual read head over to @IloveLamp post on the Nviso thread.

(My secret pleasure is the little dig the author has at Intel & IBM.)

My opinion only DYOR
FF

AKIDA BALLISTA

I just had to steal this quote:

“[Today’s DVS] sensors are extremely fast, super low bandwidth, and have a high dynamic range so you can see indoors and outdoors,” Benosman said. “It’s the future. Will it take off? Absolutely!”
“Whoever can put the processor out there and offer the full stack will win, because it’ll be unbeatable,” he added.
— Professor Ryad Benosman will give the keynote address at the Embedded Vision Summitin Santa Clara, Calif. on May 17.

 

[Proga]

Wowsers! I just saw this video on the Vinfast Futuristic VF8 on Cerence's twitter. Check out the INCREDIBLY INTELLIGENT and intuitive voice assistant!

At 5.50 It has a little camera that has face recogniiton and set's everything to your profile (moves your seat, etc).

At 6.20 She discusses how she doesn't have a car where the voice activation works this well.

https://twitter.com/cerenceinc

View attachment 5323

Hey Bravo,

If they used Akida, I gather the latency when she asks to open or close the sunroof will disappear because with SoC it will be already programmed on the chip?

 

[Bravo]

Hey Bravo,

If they used Akida, I gather the latency when she asks to open or close the sunroof will disappear because with SoC it will be already programmed on the chip?

Hey Proga,

I'm not sure they're using Akida since it's integrated with Alexa. I just updated my original post.

https://www.prnewswire.com/news-rel...d-vf-9-electric-vehicle-models-301525843.html

 

[Esq.111]

Fantastic list Esq! So handy since there's SOOO much going on!

Could you please add TC Sessions: Mobility 2022 May 18 and May 19? Herbert Diess (CEO Volkswagen) will be joining for an online portion of the event during which is going to talk about the company’s pursuits in EVs and autonomous vehicle technology, to his thoughts on the newer competitors like Tesla and how it has affected VW Group, to plans for the future. Might be worth listening to him talk about software and future technology.

TIA

https://techcrunch.com/events/tc-sessions-mobility-2022/

Afternoon Bravo,

I have only included events which we know Brainchip are part of , or exclusively Brainchip .

Great work with all the finds, the mind boggles.

Regards,
Esq.

 

[Fact Finder]

Hey Proga,

I'm not sure they're using Akida since it's integrated with Alexa. I just updated my original post.

https://www.prnewswire.com/news-rel...d-vf-9-electric-vehicle-models-301525843.html

Why does Rob Telson keep referencing Alexa when he talks about AKIDA advantages???

My opinion only DYOR
FF

AKIDA BALLISTA