As I said I only know what I am told and read.
Therefore I can tell you that you are wrong as to your view at point 2. I was present at the 2019 AGM as were many who post here when Peter van der Made made it perfectly clear that what he was saying was that he could throw away the GPU and CPUs in the current cars and do all the compute with 100 AKD1000 chips as they were then called. He further stated that with nine AKD1000 including providing redundancy he could cover all the sensors necessary for ADAS.
( Also intended to mention that as well as the throwing out statement he referenced the fact that the current compute was costing a minimum of three thousand plus dollars and that AKIDA was likely to be $10 a chip in bulk so total compute cost per vehicle would be one third or about $1,000 he could not have been any clearer. Following this in early 2020 the then CEO Mr Dinardo in one of his webinars went to some length to hose down shareholder enthusiasm about this use of AKIDA saying that while Peter van der Made was correct their sole focus was to target the Edge.)
This debate about AKIDA only being suitable for Edge compute is a long dead smelly red herring. It has been stated by the company many times that they have chosen to target the Edge because there is no incumbent player and so they do not have any true competitor in that market.
The intention has always been to move back up the supply chain into the data centre as the company becomes established and the technology is recognised and understood.
You will notice that up to this point @Diogenese has not taken up my challenge to correct my view point as he has on many prior occasions.
I accept you are genuine but you really do need to do a lot more research around the AKIDA technology value proposition.
For example the following research from Sandia makes clear that the full power of SNN computing is not yet understood with the reservation that this is not the case where Peter van der Made and his team are concerned:
Sandia Researchers Show Neuromorphic Computing Widely Applicable
March 10, 2022
ALBUQUERQUE, N.M., March 10, 2022 — 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 even earn a place in high-performance computing.
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.
Showing a neuromorphic advantage, both the IBM TrueNorth and Intel Loihi neuromorphic chips observed by Sandia National Laboratories researchers were significantly more energy efficient than conventional computing hardware. The graph shows Loihi can perform about 10 times more calculations per unit of energy than a conventional processor.
“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.”
In optimal cases, neuromorphic computers will solve problems faster and use less energy than conventional computing, he said.
The bold assertions should be of interest to the high-performance computing community because finding capabilities to solve statistical problems is of increasing concern, Aimone said.
“These problems aren’t really well-suited for GPUs [graphics processing units], which is what future exascale systems are likely going to rely on,” Aimone said. “What’s exciting is that no one really has looked at neuromorphic computing for these types of applications before.”
Sandia engineer and paper author Brian Franke said, “The natural randomness of the processes you list will make them inefficient when directly mapped onto vector processors like GPUs on next-generation computational efforts. Meanwhile, neuromorphic architectures are an intriguing and radically different alternative for particle simulation that may lead to a scalable and energy-efficient approach for solving problems of interest to us.”
Franke models photon and electron radiation to understand their effects on components.
The team successfully applied neuromorphic-computing algorithms to model random walks of gaseous molecules diffusing through a barrier, a basic chemistry problem, using the 50-million-chip Loihi platform Sandia received approximately a year and a half ago from Intel Corp., said Aimone. “Then we showed that our algorithm can be extended to more sophisticated diffusion processes useful in a range of applications.”
The claims are not meant to challenge the primacy of standard computing methods used to run utilities, desktops and phones. “There are, however, areas in which the combination of computing speed and lower energy costs may make neuromorphic computing the ultimately desirable choice,” he said.
Unlike the difficulties posed by adding qubits to quantum computers — another interesting method of moving beyond the limitations of conventional computing — chips containing artificial neurons are cheap and easy to install, Aimone said.
There can still be a high cost for moving data on or off the neurochip processor. “As you collect more, it slows down the system, and eventually it won’t run at all,” said Sandia mathematician and paper author William Severa. “But we overcame this by configuring a small group of neurons that effectively computed summary statistics, and we output those summaries instead of the raw data.”
Severa wrote several of the experiment’s algorithms.
Like the brain, neuromorphic computing works by electrifying small pin-like structures, adding tiny charges emitted from surrounding sensors until a certain electrical level is reached. Then the pin, like a biological neuron, flashes a tiny electrical burst, an action known as spiking. Unlike the metronomical regularity with which information is passed along in conventional computers, said Aimone, the artificial neurons of neuromorphic computing flash irregularly, as biological ones do in the brain, and so may take longer to transmit information. But because the process only depletes energies from sensors and neurons if they contribute data, it requires less energy than formal computing, which must poll every processor whether contributing or not. The conceptually bio-based process has another advantage: Its computing and memory components exist in the same structure, while conventional computing uses up energy by distant transfer between these two functions. The slow reaction time of the artificial neurons initially may slow down its solutions, but this factor disappears as the number of neurons is increased so more information is available in the same time period to be totaled, said Aimone.
The process begins by using a Markov chain — a mathematical construct where, like a Monopoly gameboard, the next outcome depends only on the current state and not the history of all previous states. That randomness contrasts, said Sandia mathematician and paper author Darby Smith, with most linked events. For example, he said, the number of days a patient must remain in the hospital are at least partially determined by the preceding length of stay.
Beginning with the Markov random basis, the researchers used Monte Carlo simulations, a fundamental computational tool, to run a series of random walks that attempt to cover as many routes as possible.
“Monte Carlo algorithms are a natural solution method for radiation transport problems,” said Franke. “Particles are simulated in a process that mirrors the physical process.”
The energy of each walk was recorded as a single energy spike by an artificial neuron reading the result of each walk in turn. “This neural net is more energy efficient in sum than recording each moment of each walk, as ordinary computing must do. This partially accounts for the speed and efficiency of the neuromorphic process,” said Aimone. More chips will help the process move faster using the same amount of energy, he said.
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. Larger scale systems then combine multiple chips to a board.
“Perhaps it makes sense that a technology like Loihi may find its way into a future high-performance computing platform,” said Aimone. “This could help make HPC much more energy efficient, climate-friendly and just all around more affordable.”
The work was funded under the
NNSA Advanced Simulation and Computing program and Sandia’s
Laboratory Directed Research and Development program.
A random walk diffusion model based on data from Sandia National Laboratories algorithms running on an Intel Loihi neuromorphic platform. Video courtesy of Sandia National Laboratories.
About Sandia National Laboratories
Sandia National Laboratories is a multimission laboratory operated by National Technology and Engineering Solutions of Sandia LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration. Sandia Labs has major research and development responsibilities in nuclear deterrence, global security, defense, energy technologies and economic competitiveness, with main facilities in Albuquerque, New Mexico, and Livermore, California.
Source: Sandia National Laboratories
*********************************************************************************************************************************************************
Moving on from this in the final report to NASA of the outcome of its Phase 1 project to provide a design for a hardsil AKIDA 1000 for unconnected autonomous space applications Vorago stated that AKIDA would allow Rover to achieve full autonomy and the NASA goal of speeds up to 20 kph.
AKIDA technology is not just about processing sensors and again accepting you are genuine why do you not contact Edge Impulse or Brainchip and ask them for the details of the bench marking they engaged in.
I will say this at the 2021 Ai Field Day Anil Mankar said this about GPUs and AKIDA
"And that's why we are able to do low power analysis.. The same Mobilenet V1 that you can run on a GPU I can do inference on it. I'll be doing exactly the same level of computation that you want to do because depending on the number of parameters in your CNN, what your input resolutions, you have to do certain calculations to find object classification. We do something similar, but because we do an event domain, I will not be doing, I will be avoiding operations where they are zero value events."
Your statement that if AKIDA could do these things then our valuation would not be where it is and that is the whole point AKIDA technology is beyond anything you are imaging to be its limits.
Finally these researchers do not share your view regarding being able to do regression analysis using SNN technology in fact they think they are on to something however Peter van der Made and team beat them to it by a significant margin:
Spiking Neural Networks for Nonlinear Regression
Alexander Henkes, Jason K. Eshraghian, Member, IEEE, Henning Wessels
Abstract—Spiking neural networks, also often referred to as
the third generation of neural networks, carry the potential for
a massive reduction in memory and energy consumption over
traditional, second-generation neural networks. Inspired by the
undisputed efficiency of the human brain, they introduce temporal
and neuronal sparsity, which can be exploited by next-generation
neuromorphic hardware. To broaden the pathway toward engi-
neering applications, where regression tasks are omnipresent, we
introduce this exciting technology in the context of continuum
mechanics. However, the nature of spiking neural networks poses
a challenge for regression problems, which frequently arise in
the modeling of engineering sciences. To overcome this problem,
a framework for regression using spiking neural networks
is proposed. In particular, a network topology for decoding
binary spike trains to real numbers is introduced, utilizing the
membrane potential of spiking neurons. Several different spiking
neural architectures, ranging from simple spiking feed-forward
to complex spiking long short-term memory neural networks,
are derived. Numerical experiments directed towards regression
of linear and nonlinear, history-dependent material models are
carried out. As SNNs exhibit memory-dependent dynamics, they
are a natural fit for modelling history-dependent materials which
are prevalent through all of engineering sciences. For example, we
show that SNNs can accurately model materials that are stressed
beyond reversibility, which is a challenging type of non-linearity.
A direct comparison with counterparts of traditional neural
networks shows that the proposed framework is much more
efficient while retaining precision and generalizability. All code
has been made publicly available in the interest of reproducibility
and to promote continued enhancement in this new domain
(Sorry left out this paper was published in October, 2022)
My opinion only so DYOR
FF
AKIDA BALLISTA