BRN Discussion Ongoing

[manny100]

Manny to call this a "gaffe" is an understatement.

Should we not expect our Chairman, who was actually quoted in the announcement to know what he is talking about? Should we not expect accurate information?

This was an ASX released price sensitive announcement.

Personally, I like correct and factual information from our Execs and NEDS.

As already posted it speaks volumes that no-one from BrainChip through they should intervene to stop the train-wreck around the re-domicle questions...

Focus on the gaffes and you miss many big picture positives such as:
Around the 25.30 mark of the 'Tech Talk'. Use cases of AKIDA 3. He says discussions with DOD and a "very high probability of getting a very positive outcome." This is in connection with every soldier wearing a headset with cameras interpreting what is around them, eg recognising hand signals from someone behind them. Evidently the DOD reps were speechless on hearing about this as communicating effectively in battle conditions has been a huge problem.
There are so many positives from the tech talk and AGM.

 

[Diogenese]

Lumi still offer the roadmap presentation if you cant wait for the release on the website.​

BrainChip Technology Roadmap Presentation​

View attachment 84062

It seems like the 'engine bay' is NOW ready for customers to play with, tweek and test out our wares in relation to their products.
Availability of model support and simpler set up will facilitate faster processes for the end user.
We seem to have been feeding them fish until now, we are offering them to learn how to fish going forward. Less 'hand holding'.


9 million bookings this year for the CEO as a KPI will be a good thing to see.
One might think employees are set achievable targets some might receive stretch targets I hope this is the former.
One would think 9 million is small change for this kind of tech but any money entering might be the ignition source we need.
I'm looking forward to seeing the changes to the web site which were also mentioned.
From cold dead hands I remain

Thanks FK,

The roadmap is chock full of groundbreaking advances. I felt that question time could have been better utilized by addressing the new opportunities these advances provide.

 

[equanimous]

" Before our next AGM our technical teams will achieve a ground braking milestone: the launch of the industry's first AI accelerator for State-Space models (SSM)"
Leader of the pack.

 

[Kingkong2015]

Since Akida is adding SSMs support. Brainchip will have more use cases and clients in areas listed in below table

Top 20 Most Popular State Space / Sequential Models (Including LLMs & Modern Hybrids)​

Sorted by real-world usage, research relevance, and adoption in devices:

Rank	Model	Type	Use Cases
	Large Language Models (LLMs)	Deep Learning	Chatbots, agents, assistants (GPT, Gemini, Claude)
	Kalman Filter	Linear-Gaussian	AR/VR head tracking, IMU fusion, finance, GPS
	Hidden Markov Models (HMMs)	Probabilistic	Speech recognition, gesture tracking, NLP tagging
	Extended Kalman Filter (EKF)	Nonlinear	Drones, autonomous navigation, smartwatches
	Particle Filter	Nonlinear, Sampling	AR/VR tracking, robotics, IoT localization
	Unscented Kalman Filter (UKF)	Sigma-point	Automotive ADAS, wearables, inertial sensors
	Structural Time Series Models (STSMs)	Interpretable	Power grids, IoT energy sensors, economic forecasting
	Dynamic Linear Models (DLMs)	Bayesian	Sales forecasting, wearables, health analytics
	Switching State Space Models (SSSMs)	Regime-switching	Fault detection in IoT, market phase modeling
	Deep State Space Models (e.g., RNN-SSM)	Deep Probabilistic	AR gesture prediction, speech synthesis, biosignal modeling

Emerging or Specialized Models (Ranks 11–20)​

Rank	Model	Type	Use Cases
1	Neural State Space Models (NSSMs)	Deep Neural ODEs	Physics-informed wearables, prosthetic control
1	Variational State Space Models (VSSMs)	Bayesian Deep Learning	EEG/fMRI analysis, AR/VR cognitive load estimation
1	LSTM State Space Hybrids	Seq2Seq + State	Smartwatch motion prediction, anomaly detection
1	Transformer-based SSMs	Attention with dynamics	Real-time AR/VR captioning, gesture translation
1	Nonlinear Autoregressive Exogenous Models (NARX)	Time Series	IoT weather sensors, predictive maintenance
1	Bayesian Filters (non-Kalman)	Probabilistic	Smart meters, context-aware wearables
1	Time-Varying Coefficient Models (TVCMs)	Dynamic Regression	IoT sensor drift correction
1	Reservoir Computing (Echo State Networks)	RNN-like	Low-power IoT edge devices, wearables
1	DeepAR (Amazon)	RNN Forecasting	Smart energy usage forecasting
	Spatio-Temporal State Space Models	Multivariate	Environmental sensor networks, smart cities

Summary​

• AR/VR and smartwear absolutely use SSMs, especially Kalman, UKF, and Particle Filters — just often embedded and not advertised.
• IoT devices use lightweight or approximate SSMs to balance performance and battery life.
• New deep learning hybrids (like Transformer + SSM or LLM + Sensor fusion) are emerging, especially with edge AI chips

SSMs are actually already used in these domains, but they’re often:

• Embedded inside sensor fusion or signal processing algorithms.
• Not marketed as “state space models” in commercial AR/VR/IoT products.
• Hidden behind layers of software (e.g., SLAM systems, Kalman-based IMU fusion).

For instance:

• AR headsets use Kalman/UKF to track user head/eye positions.
• Smartwatches use EKF/Particle Filters to smooth noisy biometric data.
• IoT sensors apply SSMs for anomaly detection or sensor calibration.

 

[Slade]

A new website will be unveiled shortly. " This will be followed by launch of a dedicated, developer focused companion site later this year"
"
This should expand our developer eco system.

I think they realize that Edge Impulse is no longer going to support them and they need their own developer platform.

 

[Fullmoonfever]

Appears in a recent preprint, that Basharat Ali has been running Akida, with others, as part of his / her work on cybersecurity.

Akida gives some pretty good results.

Kinda craps on NVIDiA.


Neuromorphic Quantum Adversarial Learning
(NQAL): A Bio-Inspired Paradigm for DNS over HTTPS Threat Detection
Basharat Ali
Nanjing University
Research Article
Keywords: Network Security, NQAL in Network Security, Network Protocols, Enhancing Network Security,
Enhancing DoH Protocol Security, Threats Detection in Encrypted Network, Cyber Attacks Detections
Posted Date: April 30th, 2025


Abstract Excerpt:

To overcome these complex issues, this work proposes a new architecture—Neuromorphic Quantum Adversarial Learning (NQAL)—a bio-inspired, zero-knowledge-supported detection
mechanism combining spiking neural networks (SNNs), quantum noise injection (QNI), and federated swarm intelligence to immunize, rather than detect, DoH-based attacks.

The method relies on a neuromorphic model employing Dynamic Spiking Graph Attention (DSGAT) and Spike-Timing-Dependent Plasticity (STDP) to encode encrypted traffic as dynamic spike trains to enable ultra-fast, energy-efficient inference on processors such as Intel Loihi and BrainChip Akida

Experiment set up Except:

Experiments were carried out on neuromorphic hardware platforms such as Intel Loihi 2 and BrainChip Akida that provide sub-millisecond latency with low-power event-driven processing characteristics.

Akida results related Excerpt:

Table 5: Hardware Deployment Metrics
Platform Accuracy Latency Power Throughput
GPU (NVIDIA V100) 89.2% 3.1 ms 45 W 1,200 QPS
TPUv4 91.5% 2.8 ms 32 W 1,500 QPS
Loihi 2 98.7% 0.9 ms 4 W 9,800 QPS
Akida 99.1% 0.7 ms 3 W 12,400 QPS

Outcome of Table 5:

Hardware Installation Metrics presents the excellent performance of our neuromorphic hardware solutions towards accomplishing peak performance for DoH security systems. When comparing Loihi 2 and Akaida to GPU platforms and TPU platforms depicts easily how changing towards neuromorphic chips invokes important boosts in terms of both accuracy and efficiency. Both the GPU (NVIDIA V100) and TPUv4 initiated with low performance at 89.2% and 91.5% accuracy, respectively, but when executed on Loihi 2, accuracy jumped dramatically to 98.7%, and a further improved 99.1% on Akida.

This increase in accuracy is accompanied by a drastic reduction in latency, from 3.1 ms for GPU to 0.7 ms for Akida, illustrating the real-time processing capability of the neuromorphic hardware.

Besides this, the power usage of the
Loihi 2 and Akida platforms—4 W and 3 W respectively—is a brilliant power efficiency against traditional GPU-based systems consuming 45 W. Throughput is also dramatically increased, with Akida being able to support 12,400 QPS, in strong contrast to the GPU’s 1,200 QPS.

Such results justify the single value of neuromorphic hardware as an approach for energy-efficient high-performance DoH anomaly detection and prove how
our new approach beats current systems and becomes the future standard for real-time system encrypted traffic protection[14].

Full paper HERE

 

[IloveLamp]

Semitech Semiconductor | Smart Grid & IoT Solutions

Discover Semitech Semiconductor's leading-edge solutions for smart grids and IoT, enabling robust and efficient communication technologies.

semitechsemi.com

#electronex #electronicdesign #powerlinecommunication | Semitech Semiconductor

What a great week at ElectroneX in Melbourne! We had many insightful conversations about the use of our PLC technology in a variety of industrial and transportation applications. We are looking forward to engaging with more Australian customers and partners. Thanks to the team for a job well...

www.linkedin.com

In the latest episode of our video series, Syntiant’s CEO Kurt Busch and Federal GM Ethan Wais share updates on our AI work for government, including a DIU success memo validating our tech in… | Syntiant Corp.

In the latest episode of our video series, Syntiant’s CEO Kurt Busch and Federal GM Ethan Wais share updates on our AI work for government, including a DIU success memo validating our tech in real-world military use. Highlights include: ✅ Warfighters can now run compact, efficient AI models...

www.linkedin.com

 

[IloveLamp]

💖Save the Date for 2025 Andes RISC-V CON Hsinchu- RePioneering the Future🎯 | Andes Technology

💖Save the Date for 2025 Andes RISC-V CON Hsinchu- RePioneering the Future🎯 📆Date: June 10 2025 🕛Time: 13:30-17:00 (GMT+8) 📍Venue: Sheraton Hsinchu Hotel, Taiwan 🌟Join us to discover the latest #RISCV trends, explore Andes’ innovations in #AI, #automotive, application processors, and...

www.linkedin.com

 

[IloveLamp]

💖Save the Date for 2025 Andes RISC-V CON Hsinchu- RePioneering the Future🎯 | Andes Technology

💖Save the Date for 2025 Andes RISC-V CON Hsinchu- RePioneering the Future🎯 📆Date: June 10 2025 🕛Time: 13:30-17:00 (GMT+8) 📍Venue: Sheraton Hsinchu Hotel, Taiwan 🌟Join us to discover the latest #RISCV trends, explore Andes’ innovations in #AI, #automotive, application processors, and...

www.linkedin.com

 

[TECH]

Good morning,

Look, some criticism is justified in my opinion during different stages of our development, from poor communication, poor management of
our funds, poor business planning, as in, not addressing traction issues early enough, while funds kept being pumped into sales teams who
clearly couldn't sell the idea, which I believe was a management issue myself, and possibly internal staff accountability issues etc.... but I
would suggest that many young start-ups battle similar growing pains.

I have been onboard for just shy of 10 years, and currently have a sense of calm surrounding this investment, are we in the best position
we have been in for years? yes, I believe so, a lot has been to do with education, not only of the semi-conductor industry or companies
actually, genuinely wanting to understand the real benefits of SNN technologies, but also our company as a whole, it's been a real learning
experience, which all groups appear to be coming out the other side of into clear air.

Peter's years of hard work and knock backs clearly show just how far advanced his research was, hence, we appear to be coming to that
inflection point, the bridge that was once too far, feels like that same bridge is close to completion as we as a company claim our share
of this new frontier, there's plenty to share around, our share of the pie will be huge moving forward I'm convinced of that, my opening
paragraph was fair I believe, but I, like many long termers have moved on, learnt from those early errors (growing pains) and can finally
see a horizon with a bright light emerging, our day is closing in, Brainchip will be successful, stay the journey with me and many others,
we all deserve to rise up as one!

Love our company.... Tech.

 

[FJ-215]

A short interview with ARM CEO Rene Haas. Worth a look as we are copying their business model.

 

[FJ-215]

Whoops, take 2.

Interview with ARM CEO Rene Haas.

Arm CEO Says AI Is 'Not a Bubble'

Arm CEO Rene Haas discusses the chipmaker’s outlook following a strong first quarter earnings report. Haas also comments on tariffs, artificial intelligence demand and growing the businesses with Caroline Hyde and Vonnie Quinn on Bloomberg Television. (Source: Bloomberg)

www.bloomberg.com

 

[manny100]

Good morning,

Look, some criticism is justified in my opinion during different stages of our development, from poor communication, poor management of
our funds, poor business planning, as in, not addressing traction issues early enough, while funds kept being pumped into sales teams who
clearly couldn't sell the idea, which I believe was a management issue myself, and possibly internal staff accountability issues etc.... but I
would suggest that many young start-ups battle similar growing pains.

I have been onboard for just shy of 10 years, and currently have a sense of calm surrounding this investment, are we in the best position
we have been in for years? yes, I believe so, a lot has been to do with education, not only of the semi-conductor industry or companies
actually, genuinely wanting to understand the real benefits of SNN technologies, but also our company as a whole, it's been a real learning
experience, which all groups appear to be coming out the other side of into clear air.

Peter's years of hard work and knock backs clearly show just how far advanced his research was, hence, we appear to be coming to that
inflection point, the bridge that was once too far, feels like that same bridge is close to completion as we as a company claim our share
of this new frontier, there's plenty to share around, our share of the pie will be huge moving forward I'm convinced of that, my opening
paragraph was fair I believe, but I, like many long termers have moved on, learnt from those early errors (growing pains) and can finally
see a horizon with a bright light emerging, our day is closing in, Brainchip will be successful, stay the journey with me and many others,
we all deserve to rise up as one!

Love our company.... Tech.

Thanks Tech, my take below,
I think a 'prime' reason was that PVM's Neuromorphic invention was way ahead of its time. There were no products it could slip into.
No one had any use for it at all. So it was never going to sell.
Late 2021 Sean who had a mountain of experience was employed to commercialise the product. The ASX announcement that we were full on commercial was issued in Jan'22.
He had a 5 year plan approved by the BOD - 18 months shy of expiring.
An eco system has been built and it's a living system given its always growing. It's based on the premise that in the semi conductor industry 'no one stands alone' - if you do you perish and die. So well done.
I have no doubt that even the experienced Sean and the BOD were surprised at the time it has taken for industry to take up neuromorphic AI at the Edge for which we are the standout leader. The latest tech road map shows that we will remain the leader.
Humans change slowly unless it becomes necessary. The conflict in Europe and ME and loose war talk has defense build ups world wide.
That deemed necessary urgent DOD beef up is our opportunity.
Sean mentioned at the AGM that we are submitting proposals every month to the DOD. US AFRL, Navy transition to the Edge via Bascom Hunter.
Industry will start to full on follow the DOS and of course space program public useful tech.
IMO we get judged from here. The past has passed.
Times 'they are a changing' and we must take full advantage.

 

[White Horse]

Appears in a recent preprint, that Basharat Ali has been running Akida, with others, as part of his / her work on cybersecurity.

Akida gives some pretty good results.

Kinda craps on NVIDiA.


Neuromorphic Quantum Adversarial Learning
(NQAL): A Bio-Inspired Paradigm for DNS over HTTPS Threat Detection
Basharat Ali
Nanjing University
Research Article
Keywords: Network Security, NQAL in Network Security, Network Protocols, Enhancing Network Security,
Enhancing DoH Protocol Security, Threats Detection in Encrypted Network, Cyber Attacks Detections
Posted Date: April 30th, 2025


Abstract Excerpt:

To overcome these complex issues, this work proposes a new architecture—Neuromorphic Quantum Adversarial Learning (NQAL)—a bio-inspired, zero-knowledge-supported detection
mechanism combining spiking neural networks (SNNs), quantum noise injection (QNI), and federated swarm intelligence to immunize, rather than detect, DoH-based attacks.

The method relies on a neuromorphic model employing Dynamic Spiking Graph Attention (DSGAT) and Spike-Timing-Dependent Plasticity (STDP) to encode encrypted traffic as dynamic spike trains to enable ultra-fast, energy-efficient inference on processors such as Intel Loihi and BrainChip Akida

Experiment set up Except:

Experiments were carried out on neuromorphic hardware platforms such as Intel Loihi 2 and BrainChip Akida that provide sub-millisecond latency with low-power event-driven processing characteristics.

Akida results related Excerpt:

Table 5: Hardware Deployment Metrics
Platform Accuracy Latency Power Throughput
GPU (NVIDIA V100) 89.2% 3.1 ms 45 W 1,200 QPS
TPUv4 91.5% 2.8 ms 32 W 1,500 QPS
Loihi 2 98.7% 0.9 ms 4 W 9,800 QPS
Akida 99.1% 0.7 ms 3 W 12,400 QPS

Outcome of Table 5:

Hardware Installation Metrics presents the excellent performance of our neuromorphic hardware solutions towards accomplishing peak performance for DoH security systems. When comparing Loihi 2 and Akaida to GPU platforms and TPU platforms depicts easily how changing towards neuromorphic chips invokes important boosts in terms of both accuracy and efficiency. Both the GPU (NVIDIA V100) and TPUv4 initiated with low performance at 89.2% and 91.5% accuracy, respectively, but when executed on Loihi 2, accuracy jumped dramatically to 98.7%, and a further improved 99.1% on Akida.

This increase in accuracy is accompanied by a drastic reduction in latency, from 3.1 ms for GPU to 0.7 ms for Akida, illustrating the real-time processing capability of the neuromorphic hardware.

Besides this, the power usage of the
Loihi 2 and Akida platforms—4 W and 3 W respectively—is a brilliant power efficiency against traditional GPU-based systems consuming 45 W. Throughput is also dramatically increased, with Akida being able to support 12,400 QPS, in strong contrast to the GPU’s 1,200 QPS.

Such results justify the single value of neuromorphic hardware as an approach for energy-efficient high-performance DoH anomaly detection and prove how
our new approach beats current systems and becomes the future standard for real-time system encrypted traffic protection[14].

Full paper HERE

BrainChip is doing business in Korea, Japan and Taiwan. We have been working with international companies like Renesas. It is hard to imagine that China hasn’t had a good look at Akida. Being an Australian company we are not restricted in dealing directly with China by US sanctions. If we have stepped back from dealing with China to please the US then I hope it proves worth it.

Hi Slade, remember this from 2022.
https://www.ex3.simula.no/resources

Posted by FMF.
https://thestockexchange.com.au/thr...rver-kunpeng-920-processor-using-akida.29899/

Well, if anybody was doubting interest from China.
I'd say the answer is YES.!!!

 

[Bravo]

Lockheed Martin! Cybersecurity!

Let's get a wriggle on and get this CyberNeuro-RT technology out into the market!

Blog published 3 days ago.



Pioneering Innovation:

How Lockheed Martin is using AI to transform cybersecurity​

May 05, 2025



In the unseen battlespaces of the digital age, where cyber threats hide around every corner, the U.S. military and its allies are in an unrelenting battle to safeguard their most critical assets: the networks, systems, and secrets that power national defense.
As the cyber landscape rapidly evolves, industry leaders like Lockheed Martin are driving an unprecedented shift in operations by incorporating artificial intelligence (AI) and machine learning (ML) to jump ahead of emerging cyber threats.

Advancing Cybersecurity​

When looking at the future of defense, cyber capabilities are at the frontlines. It is where conflict starts and deterrence is tested. With modern military operations relying heavily on software and data, cyber-attacks can have devastating effects. With networks down, you cannot operate, communicate, or make informed decisions. Because of this, increasing the cyber security and resiliency is a critical aspect of Lockheed Martin's operations. The Lockheed Martin Artificial Intelligence Center (LAIC) is at the heart of this innovation, driving the development and implementation of cutting-edge AI and ML solutions to enhance cyber defenses for the warfighter.
“The current pace of change in AI research and the ever-increasing level of investments means that the state of the art (SOTA) AI five years ago is commonplace now,” explained Dan Reese, Lockheed Martin Associate Fellow. “Lockheed Martin continues to mature and invest in cyber advancements and new capabilities using AI/ML that will allow our customers to maintain an edge on the battlefield."

Here are three ways it’s being done:​

Threat Detection ___
The LAIC is developing AI-powered threat detection systems that can identify and respond to emerging threats in real-time, reducing the risk of cyber-attacks and data breaches before they occur.
These systems use advanced analytics and ML algorithms to analyze network traffic and system data to identify patterns and anomalies that may indicate a potential threat. This in turn enables swift and effective response, reducing the risk of cyber-attacks, protecting critical systems and infrastructure.
Vulnerability Assessment ___
Lockheed Martin has developed a new approach to identifying cyber vulnerabilities, exposing exploits and potential attack vectors. By leveraging a multi-agent reinforcement learning (MARL) framework, cyber-attack sequences can be prioritized based on adversarial mission objectives. By understanding how adversaries can potentially compromise our mission systems/platforms, our defenders can now develop countermeasures and effective mitigation techniques with AI at a fraction of the previous cost.
Cloud Transformation ___
To further enhance cybersecurity, Lockheed Martin is leading the way in cloud transformation, recognizing the immense benefits it offers in terms of scalability, flexibility, and cost savings. By migrating its systems and applications to the cloud, the company is able to enhance cybersecurity, reduce latency, and improve data processing speeds. The LAIC is playing a critical role in this effort, leveraging its expertise in AI and ML to develop cloud-based solutions that enable real-time data analysis, predictive maintenance, and advanced threat detection.
One notable example of Lockheed Martin's cloud transformation is its work on the Department of Defense's (DoD) Joint All-Domain Command and Control (JADC2) program. The LAIC is collaborating with the DoD to develop a cloud-based architecture that enables seamless communication and data sharing across different domains, including air, land, sea, space, and cyber. This innovative approach will enhance situational awareness, improve decision-making, and increase the speed of response to emerging threats.

Warfighting Solutions​

By embracing cloud computing and AI/ML technologies, Lockheed Martin is enhancing cybersecurity, improving efficiency, and unlocking new insights and capabilities. These new cutting-edge technologies are also increasing the effectiveness of military operations, and drive the development of a more agile, adaptive, and responsive military force, capable of addressing the complex and evolving threats of the modern battlefield.
“What's exciting about AI is its ability to transform not only how we do work within Lockheed, but ultimately how we transform and provide new capabilities to the warfighter,” stated Greg Forrest, AI Foundations Director. “At the end of the day, that's why we're here. We're here to support our customers. We're here to support our service members. And I think there's tremendous opportunity to utilize AI across the board to enable a more safe, secure world for our warfighters.”

Artificial Intelligence and Machine Learning

Lockheed Martin pioneers in AI-driven advancements. With a commitment to ethical AI, we enhance decision-making and deliver actionable intelligence.

www.lockheedmartin.com

 

[manny100]

Lockheed Martin! Cybersecurity!

Let's get a wriggle on and get this CyberNeuro-RT technology out into the market!

Blog published 3 days ago.



Pioneering Innovation:

How Lockheed Martin is using AI to transform cybersecurity​

May 05, 2025



In the unseen battlespaces of the digital age, where cyber threats hide around every corner, the U.S. military and its allies are in an unrelenting battle to safeguard their most critical assets: the networks, systems, and secrets that power national defense.
As the cyber landscape rapidly evolves, industry leaders like Lockheed Martin are driving an unprecedented shift in operations by incorporating artificial intelligence (AI) and machine learning (ML) to jump ahead of emerging cyber threats.

Advancing Cybersecurity​

When looking at the future of defense, cyber capabilities are at the frontlines. It is where conflict starts and deterrence is tested. With modern military operations relying heavily on software and data, cyber-attacks can have devastating effects. With networks down, you cannot operate, communicate, or make informed decisions. Because of this, increasing the cyber security and resiliency is a critical aspect of Lockheed Martin's operations. The Lockheed Martin Artificial Intelligence Center (LAIC) is at the heart of this innovation, driving the development and implementation of cutting-edge AI and ML solutions to enhance cyber defenses for the warfighter.
“The current pace of change in AI research and the ever-increasing level of investments means that the state of the art (SOTA) AI five years ago is commonplace now,” explained Dan Reese, Lockheed Martin Associate Fellow. “Lockheed Martin continues to mature and invest in cyber advancements and new capabilities using AI/ML that will allow our customers to maintain an edge on the battlefield."

Here are three ways it’s being done:​

Threat Detection ___
The LAIC is developing AI-powered threat detection systems that can identify and respond to emerging threats in real-time, reducing the risk of cyber-attacks and data breaches before they occur.
These systems use advanced analytics and ML algorithms to analyze network traffic and system data to identify patterns and anomalies that may indicate a potential threat. This in turn enables swift and effective response, reducing the risk of cyber-attacks, protecting critical systems and infrastructure.
Vulnerability Assessment ___
Lockheed Martin has developed a new approach to identifying cyber vulnerabilities, exposing exploits and potential attack vectors. By leveraging a multi-agent reinforcement learning (MARL) framework, cyber-attack sequences can be prioritized based on adversarial mission objectives. By understanding how adversaries can potentially compromise our mission systems/platforms, our defenders can now develop countermeasures and effective mitigation techniques with AI at a fraction of the previous cost.
Cloud Transformation ___
To further enhance cybersecurity, Lockheed Martin is leading the way in cloud transformation, recognizing the immense benefits it offers in terms of scalability, flexibility, and cost savings. By migrating its systems and applications to the cloud, the company is able to enhance cybersecurity, reduce latency, and improve data processing speeds. The LAIC is playing a critical role in this effort, leveraging its expertise in AI and ML to develop cloud-based solutions that enable real-time data analysis, predictive maintenance, and advanced threat detection.
One notable example of Lockheed Martin's cloud transformation is its work on the Department of Defense's (DoD) Joint All-Domain Command and Control (JADC2) program. The LAIC is collaborating with the DoD to develop a cloud-based architecture that enables seamless communication and data sharing across different domains, including air, land, sea, space, and cyber. This innovative approach will enhance situational awareness, improve decision-making, and increase the speed of response to emerging threats.

Warfighting Solutions​

By embracing cloud computing and AI/ML technologies, Lockheed Martin is enhancing cybersecurity, improving efficiency, and unlocking new insights and capabilities. These new cutting-edge technologies are also increasing the effectiveness of military operations, and drive the development of a more agile, adaptive, and responsive military force, capable of addressing the complex and evolving threats of the modern battlefield.
“What's exciting about AI is its ability to transform not only how we do work within Lockheed, but ultimately how we transform and provide new capabilities to the warfighter,” stated Greg Forrest, AI Foundations Director. “At the end of the day, that's why we're here. We're here to support our customers. We're here to support our service members. And I think there's tremendous opportunity to utilize AI across the board to enable a more safe, secure world for our warfighters.”

Artificial Intelligence and Machine Learning

Lockheed Martin pioneers in AI-driven advancements. With a commitment to ethical AI, we enhance decision-making and deliver actionable intelligence.

www.lockheedmartin.com

Hi, Bravo, thanks, after the AGM its only a matter of time before we drop a Quantum Ventura CRNT type gamechanger on Pico.
I am sure it's being planned as we speak.
If we look at the cybersecurity white paper its small devices that connect to the main network that are the weak/vulnerable points.
Pico or a Pico plus running with TENNs/QV cybersecurity SSM could close those loops.
The possibilities are huge.
Personal mobiles, Health small devices, all DOD small devices etc.

 

[Diogenese]

Thanks FK,

The roadmap is chock full of groundbreaking advances. I felt that question time could have been better utilized by addressing the new opportunities these advances provide.

Akida GenAI & Akida 3 have been adapted to handle 16-bit integer and 32-bit FP. This, in addition to the malleable architecture, enables these two chips to be flexibly configured to handle all types of models and to be adapted for future applications.

The provision of a LUT in place of an activation function seems like a patentable idea if original. We are also told by JT that a patent application is in the pipeline for a new technique for retrieving data from memory. This is the most energy intensive action so the invention will further increase the power efficiency and probably latency.

Akida 2 is 8 times more efficient than Akida 1, and presumably that also applies to GenAI & Akida 3 for equivalent Akida 1 tasks. However, 16-bit integer and 32-bit FP seem to provide excessive capabilities for an edge device. Does Nvidia need to look over its shoulder "like one that on a lonesome road doth walk in fear and dread, and having once turned round, walks on, and turns no more his head, because he knows that close behind a frightful fiend doth tread"?

 

[supersonic001]

CEO Sean Hehir was happy to have the chance to meet with Marc Kennis in Australia this week to discuss BrainChip’s product roadmap including Akida Generative AI technology and the advancement of our… | BrainChip

CEO Sean Hehir was happy to have the chance to meet with Marc Kennis in Australia this week to discuss BrainChip’s product roadmap including Akida Generative AI technology and the advancement of our Temporal Event Neural Network models. Sean also shared on the Stocks Down Under podcast some of...

www.linkedin.com

Go Sean …. !

 

[TECH]

Akida GenAI & Akida 3 have been adapted to handle 16-bit integer and 32-bit FP. This, in addition to the malleable architecture, enables these two chips to be flexibly configured to handle all types of models and to be adapted for future applications.

The provision of a LUT in place of an activation function seems like a patentable idea if original. We are also told by JT that a patent application is in the pipeline for a new technique for retrieving data from memory. This is the most energy intensive action so the invention will further increase the power efficiency and probably latency.

Akida 2 is 8 times more efficient than Akida 1, and presumably that also applies to GenAI & Akida 3 for equivalent Akida 1 tasks. However, 16-bit integer and 32-bit FP seem to provide excessive capabilities for an edge device. Does Nvidia need to look over its shoulder "like one that on a lonesome road doth walk in fear and dread, and having once turned round, walks on and turns no more his head, because he knows that close behind a frightful fiend doth tread"?

Hi Dio,

We, Brainchip are at an amazing point in our development, it's super exciting!

You, being a retired engineer could appreciate the amount of work that's been quietly going on behind the scenes over the last
12 months, we all thought no more doors could possibly open up to this technology, but this latest news out of the engineering
department dispels that idea, is it just me, or do you and others think that Nvidia are just plain stubborn in their approach to our
architecture? (if that makes sense).

Is the gap going to potentially widen after the release of our advancement of the Akida suite of offerings?

Our solid roadmap will definitely get the attention of all our potential competition, I'm hoping like many I'd suggest who would like
to see us succeed on our own two feet for a few years before considering an offer, if it happened to surface at some future point.

Regards....Tech

 

[MDhere]

Todaya price .24c x 10 would be where we need to be before we enter any redomicils at the very minimum.

.24 x 10 would be where we need to be for shareholders, all shareholders that experienced the Mercedes hype to feel better.

I am hoping 1 or two million bookings brings what a mountain of revenue and positive onflow which is expected.

Bring on zero shot learning after that and we are on a winner for the long run!

But bring on the .24 x 10 first then we can get back to where we were.

I'm encouraged by the roadmap but moreso encouraged by Sean axknowledging that he needs to deliver the promise of "watch the financials".