buena suerte :-)
BOB Bank of Brainchip
Largest trading day in well over a year!!!! What we got cooking?!
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Humble Genius
Regular
Also, serendipitously, I just happened to discover this November 2023 investor presentation online (and since none of its slides are marked ‘confidential’, I picked out my favourite ones…), which appears to be aimed at US investors, due to the listing of the ADRs (OTCQX: BCHPY) preceding that of the shares (ASX: BRN).
View attachment 51013
View attachment 51014
View attachment 51015
View attachment 51017
View attachment 51016
Imo, this is the most important slide in Todd's presentation:
You would think if nothing was happening, or not on the horizon, that these names would not appear on the slide. If Valeo, or Mercedes, or NASA had stalled or decided to go with a different/competeitor technology, then they would not be listed here? If the "early adoption" of the technology was not true, or moving forward, or they decided to go with an alternative technology they would ask Brainchip to remove their name.
The names are still there, and that is good and big things are going to happen soon!
(Ford's name doesn't appear in the list, and that is ok - they are the perhaps the ones who have put their project on hold........, ie a point of difference with this slide)
Mt09
Regular
They’ve left off Edgx!
Fullmoonfever
Top 20
Well, a nice bit of news today first posted up by some great contributors....thank you.
HG, agree with your logic and thought I'd do a quick search for anything updating on Vorago as a start.
The below came up for the 2024 Space Tech Expo exhibitors and I found it encouraging the additional info around the partnership with BRN is also front and centre.
Haven't had a chance to watch the capability video yet as about to be driving so don't know how recent it is.
May 13 – 15, 2024 // Long Beach, California, USA
*May 13: Invite only Preview May 14-15: Exhibits and ConferenceVORAGO Technologies
VORAGO designs and develops highly reliable semiconductor solutions with superior radiation and temperature endurance performance. VORAGO's patented, innovative technology, HARDSIL®, has been proven in multiple process generations at multiple fabs to harden semiconductor circuits without redesign and is scalable to any generation node (incl.FinFET).
VORAGO Technologies is a privately held, high technology company based in Austin, Texas with over 15 years of experience in providing radiation-hardened and extreme-temperature solutions for the Hi-rel marketplace. VORAGO’s patented HARDSIL® technology uses cost-effective high-volume manufacturing to harden any commercially designed semiconductor component for extreme environment operation, and has created a number of solutions throughout Aerospace, Defense and Industrial applications. VORAGO Technologies opens up a new world of possibilities for your designs, no matter how hostile the environment.
Categories: Engineering Consultancy || Design / Engineering Services || Components – Electronic / Electrical
News
VORAGO Technologies Debuts on the 2020 Inc. 5000 With Three-Year Revenue Growth of 87 Percent
Inc. Magazine Unveils Its Annual List of America's Fastest-Growing Private Companies—the Inc. 5000 Read more...BrainChip and VORAGO Technologies Agree to Collaborate through the Akida Early Access Program
greement to Support Phase I of NASA Program for Radiation-Hardened Neuromorphic Processo Read more...Radiation-hardened Arm Cortex-based microcontrollers for space and military applications introduced by VORAGO | Military & Aerospace
The VORAGO family of BGA processors compresses the functionality of as many as eight integrated circuits into one 12-by-12-millimeter BGA package. Read more...VORAGO Technologies Videos
VORAGO Capabilities | VORAGO Technologies
Back to Exhibitor List
Contact Exhibitor
Booth Number: 7029
Contact
WebsiteAddress:
1501 S. Mopac Expressway Suite 350,
Austin,
TX,
USA,
78746
LexLuther77
Regular
Yep happens every year… It would be nice if it was instos getting set though
Tothemoon24
Top 20
Adaptive Restraints Enabled by Camera-based In-cabin Analysis: the Evolution of Passive Safety
Nov 30, 2023 | Blog
Active Safety vs Passive Safety
In the realm of vehicle safety, it is important to distinguish between active and passive safety. Active safety is concerned with everything that could potentially lead to accidents and focuses on minimizing these factors. On the other hand, passive safety systems aim to minimize the impact of unavoidable accidents such as lowering the rate of fatalities and serious injuries. In contrast to active safety systems, passive safety systems are in effect during or after accidents.
Passive Safety Systems in Detail
Passive safety consists of three main subcategories:
Airbags: During a collision, airbags are deployed to protect the occupants of the vehicle. Through the fast inflation of airbags, a soft restraint between the occupants and the vehicle is created which reduces the severity of injuries and prevents fatalities. Historically, they were placed in the front of the driver and co-driver but nowadays there are also side airbags to protect occupants from side impacts.
Seatbelts: Similarly, seatbelts help occupants to stay in a safe position, away from the vehicle’s rigid parts, during an accident or sudden stop. They keep occupants from being ejected outside of the vehicle in the event of a severe crash. Moreover, the seatbelts in cars today are pre-tensioned, which indicates that they are tightened upon impact.
Crumble/Crush Zones: Crumble zones are specially engineered to release the kinetic energy of a crash in a controlled manner. Certain parts of the vehicles are designed to crumple during a crash to absorb the impact.
Additionally, a newer feature which could be counted as a new passive safety component in the European Union (EU) is the eCall which provides rapid assistance to passengers involved in accidents.
Passive Safety Regulations
Similar to other regulations in the automotive industry, passive safety regulations are in constant development. The commercial introduction of airbags in passenger vehicles was through the 1973 Oldsmobile Toronado, however, it was broadly adopted only in the early 1990s. It became mandatory for vehicles to be equipped with airbags in 1998 in the US and in 2009 in the EU.
As for seatbelts, the modern three-point seatbelt that we still use today, was invented in 1959 however, EU regulations only started mandating seatbelt use for all passengers in 2006.
The next step in passive safety regulations is the mandating of adaptive restraints. Compared to traditional systems, adaptive restraints react differently depending on the vehicle’s occupants and the situation in the vehicle before and during a crash. After EuroNCAP included adaptive restraint control systems in their Vision 2030, OEM’s and Tier 1’s search for the most effective solution gained pace. While it is crucially important to have effective passive safety systems in place, it is not as easily implemented.
To be able to prevent fatalities and injuries in the event of a crash, fast and accurate systems need to be created. This requires knowledge of the body positioning and characteristics of the occupants in the vehicle before and during the crash.
Solutions in the Industry
Multiple tools and systems are being developed to obtain the most accurate results. A novel approach is the smart-RCS project by emotion3D, Veoneer (now partly Magna) and AVL. Through a camera-based occupant monitoring system (OMS), the partners created the world’s first personalized restraint control system. In the event of a crash, the system captures the exact location and positioning of the passengers in the vehicle and calculates the appropriate airbag deployment strategy. This approach does not only help to better prevent injuries and fatalities but also overcomes inherent biases in the industry based on physical attributes, which is emphasized in EuroNCAP’s Vision 2030. The system features a Time of Flight (ToF) camera, to obtain a robust and accurate measurement of the occupants’ positioning within the vehicle, as well as the occupants’ height, weight and classification. The adaptive restraint control system takes this information into account when computing the optimized restraint deployment strategy.
Other direct sensing tools used in passive safety solutions are radar and ultrasound. These output the distance of occupants to the vehicle. While they provide accurate distance information, they lack further perception capabilities compared to camera-based systems and therefore shall only be used as a supplementary solution.
It is worth mentioning that there are also indirect sensing options that calculate the distance / occupant classification through the position of the seat rather than the occupants’ positions – solutions that have been heavily used in the past and present. Those sensing options, however, are inaccurate and can lead to misclassifications.
Future Outlook
As Euro NCAP will likely include adaptive restraints in their future protocols, it is expected that OEMs will start incorporating more and more safety solutions in their vehicles. The increase in interest and number of solutions being worked on is already noticeable.
As one of the pioneers in this area, emotion3D is continuing to work on its passive safety offerings with the aim to improve safety on all fronts.
If you’re taking part in CES 2024 in Las Vegas from the 9-12th of January, you can have the chance to experience Cabin Eye Safety first-hand, through our joint demo with Melexis!
Fullmoonfever
Top 20
Well, a nice bit of news today first posted up by some great contributors....thank you.
HG, agree with your logic and thought I'd do a quick search for anything updating on Vorago as a start.
The below came up for the 2024 Space Tech Expo exhibitors and I found it encouraging the additional info around the partnership with BRN is also front and centre.
Haven't had a chance to watch the capability video yet as about to be driving so don't know how recent it is.
May 13 – 15, 2024 // Long Beach, California, USA
*May 13: Invite only Preview May 14-15: Exhibits and Conference
VORAGO Technologies
VORAGO designs and develops highly reliable semiconductor solutions with superior radiation and temperature endurance performance. VORAGO's patented, innovative technology, HARDSIL®, has been proven in multiple process generations at multiple fabs to harden semiconductor circuits without redesign and is scalable to any generation node (incl.FinFET).
VORAGO Technologies is a privately held, high technology company based in Austin, Texas with over 15 years of experience in providing radiation-hardened and extreme-temperature solutions for the Hi-rel marketplace. VORAGO’s patented HARDSIL® technology uses cost-effective high-volume manufacturing to harden any commercially designed semiconductor component for extreme environment operation, and has created a number of solutions throughout Aerospace, Defense and Industrial applications. VORAGO Technologies opens up a new world of possibilities for your designs, no matter how hostile the environment.
Categories: Engineering Consultancy || Design / Engineering Services || Components – Electronic / Electrical
News
VORAGO Technologies Debuts on the 2020 Inc. 5000 With Three-Year Revenue Growth of 87 Percent
Inc. Magazine Unveils Its Annual List of America's Fastest-Growing Private Companies—the Inc. 5000 Read more...
BrainChip and VORAGO Technologies Agree to Collaborate through the Akida Early Access Program
greement to Support Phase I of NASA Program for Radiation-Hardened Neuromorphic Processo Read more...
Radiation-hardened Arm Cortex-based microcontrollers for space and military applications introduced by VORAGO | Military & Aerospace
The VORAGO family of BGA processors compresses the functionality of as many as eight integrated circuits into one 12-by-12-millimeter BGA package. Read more...
VORAGO Technologies Videos
VORAGO Capabilities | VORAGO Technologies
Back to Exhibitor List
Contact Exhibitor
Booth Number: 7029
Contact
Website
Address:
1501 S. Mopac Expressway Suite 350,
Austin,
TX,
USA,
78746
Whilst I was checking out Vorago, I came across this upcoming conference.
Aerospace Conference
At the Yellowstone Conference Center in Big Sky, Montana,Mar 2 - Mar 9, 2024
Vorago was mentioned in so much as a cubesat project will be using one of their MCUs onboard.
Didn't mention neuromorphic, but I did search that keyword anyway and the below presso came up....
Autonomous Detection of Tiny, Fast Moving Objects in Infrared Imagery Using a Bio-inspired System
Suhas Chelian ()Presentation: Suhas Chelian - Wednesday, March 6th, 09:25 PM - Cheyenne
Would appear this presenter could be...
Suhas Chelian
Quantum Ventura Inc. Boston University
San Francisco Bay Area
2K followers 500+ connections
What piqued my interest was the last sentence...don't know many of those, especially linked to QVAutonomously detecting tiny, fast moving objects emitting thermal radiation in the infrared is a challenging technical problem. In addition to being fast, these targets are often dim, small and in the presence of clutter and occlusions. Conventional detection approaches require large SWaP systems which may introduce substantial latencies. Here we explore an end-to-end system composed of scene simulation, sensor capture from a novel highly sensitive MEMS microbolometer, a readout integrated circuit (ROIC) which uses a unique saliency computation to remove uninteresting image regions, and deep learning detection and tracking algorithms. Simulations across these modules verify the advantages of our approach compared to conventional approaches. We estimate our system’s ability to detect targets to be less than five seconds after a fast moving object enters a sensor’s field of view. To explore low energy implementations of our computer vision models, deep learning on COTS neuromorphic hardware is also discussed.
Kachoo
Regular
Hey HG your absolutely correct.
One thing I would say about Ford is that they have always wanted to be annomynous but with LD putting out that ASX news about a Detroit automaker news has to be updated with a name. So I would say after that they were on a very thin line with Ford. I would think based on Tony's communication about the list Ford is still doing what they do but we won't see anything or hear much from them IMO.
Cheers
Boab
I wish I could paint like Vincent
Orebro University is in Sweden.
Wasn't aware we had a connection with them?
The tentacles keep reaching out
Frangipani
Regular
Orebro University is in Sweden.
Wasn't aware we had a connection with them?
The tentacles keep reaching out
Hi Pom down under and Boab,
the tweet (or whatever it is called these days) BrainChip published yesterday is unfortunately somewhat misleading - as far as I understand it, there is no actual collaboration with Örebro University, even though by using the Swedish uni’s coat of arms, the tweet makes it look like there is. Our company merely utilised a decade-old dataset collected by Örebro University researchers:
Excerpt from my earlier post, linking to the research paper found on the BrainChip website:
Overview:
In this research, we utilized the ‘bacteria in blood’ dataset, which was previously collected by the Mednose project team at Örebro University. Their project was centred on the early detection of different bacterial species in blood, by identifying the unique chemical signatures they emit during initial growth phases.The collection was carried out using the NST 3220 Emission Analyzer, a sophisticated electronic nose device developed by Applied Sensors, equipped with a combined array of 22 metal-oxide semiconductor (MOS) and MOSFET sensors. The project’s objective was to distinguish between ten types of bacteria in blood samples, and for this purpose, a comprehensive dataset of 1200 samples was created, with 120 samples representing each bacterial species. For an in-depth understanding of the electronic nose experiments and the sampling protocols, a detailed description is available in the work by Trincavelli et al. titled “Direct identification of bacteria in blood culture samples using an electronic nose,” published in the IEEE Transactions on Biomedical Engineering
Last edited:
Hi Frangipani,Hi Pom down under and Boab,
the tweet (or whatever it is called these days) BrainChip published yesterday is unfortunately somewhat misleading - as far as I understand it, there is no actual collaboration with Örebro University, even though by using the Swedish uni’s coat of arms, the tweet makes it look like there is. Our company merely utilised a decade-old dataset collected by Örebro University researchers:
View attachment 51050
View attachment 51051
Excerpt from my earlier post, linking to the research paper found on the BrainChip website:
Overview:
In this research, we utilized the ‘bacteria in blood’ dataset, which was previously collected by the Mednose project team at Örebro University. Their project was centred on the early detection of different bacterial species in blood, by identifying the unique chemical signatures they emit during initial growth phases.The collection was carried out using the NST 3220 Emission Analyzer, a sophisticated electronic nose device developed by Applied Sensors, equipped with a combined array of 22 metal-oxide semiconductor (MOS) and MOSFET sensors. The project’s objective was to distinguish between ten types of bacteria in blood samples, and for this purpose, a comprehensive dataset of 1200 samples was created, with 120 samples representing each bacterial species. For an in-depth understanding of the electronic nose experiments and the sampling protocols, a detailed description is available in the work by Trincavelli et al. titled “Direct identification of bacteria in blood culture samples using an electronic nose,” published in the IEEE Transactions on Biomedical Engineering
View attachment 51052
In all NN applications, the model library is a crucial part of the setup. It is the information against which the test samples are to be compared. A NN cannot function without the model.
Maybe the Orebro Uni requires acknowledgement of the use of its database in exchange for access to their proprietary database, and they may require the display of their logo as acknowledgement of their authorship of the data.
Frangipani
Regular
You are right, that’s indeed a possible explanation for the uni’s coat of arms being displayed.
But I would venture a guess that the vast majority of people seeing that tweet would automatically assume it signified there was an existing research collaboration between our company and Örebro University and visualise biomedical researchers at the Swedish uni experimenting with Akida. Which is clearly not what this press release is about.
Learning
Learning to the Top 🕵♂️
Hi Frangipani,Hi Pom down under and Boab,
the tweet (or whatever it is called these days) BrainChip published yesterday is unfortunately somewhat misleading - as far as I understand it, there is no actual collaboration with Örebro University, even though by using the Swedish uni’s coat of arms, the tweet makes it look like there is. Our company merely utilised a decade-old dataset collected by Örebro University researchers:
View attachment 51050
View attachment 51051
Excerpt from my earlier post, linking to the research paper found on the BrainChip website:
Overview:
In this research, we utilized the ‘bacteria in blood’ dataset, which was previously collected by the Mednose project team at Örebro University. Their project was centred on the early detection of different bacterial species in blood, by identifying the unique chemical signatures they emit during initial growth phases.The collection was carried out using the NST 3220 Emission Analyzer, a sophisticated electronic nose device developed by Applied Sensors, equipped with a combined array of 22 metal-oxide semiconductor (MOS) and MOSFET sensors. The project’s objective was to distinguish between ten types of bacteria in blood samples, and for this purpose, a comprehensive dataset of 1200 samples was created, with 120 samples representing each bacterial species. For an in-depth understanding of the electronic nose experiments and the sampling protocols, a detailed description is available in the work by Trincavelli et al. titled “Direct identification of bacteria in blood culture samples using an electronic nose,” published in the IEEE Transactions on Biomedical Engineering
View attachment 51052
I agree with what Dio said above, as this media release didn't say Brainchip (partners/ collaborate) with Örebro University. It's state this:
With findings achieved through studies by BrainChip Research, “Finding Bacteria in the Blood: Scaling a Hardware-Driven Neuromorphic Solution for Real-World E-Nose Applications” presents how a hardware-based, low-power neuromorphic solution can be combined with electronic sensors to create compelling real-world healthcare solutions that are cost-effective, portable and accurate. These assisted devices could significantly speed up disease diagnosis in remote locations, or even outside of traditional clinical facilities.
The paper explores a blood dataset collected as part of the Mednose project at Örebro University. The classifier model developed using Akida™ was able to identify ten different bacteria species in blood samples with a classification accuracy of 97.42%, outperforming previous implementations.
“Leveraging neuromorphic hardware to provide portable, power-efficient solutions for use in the identification of sensory data is a game-changer for a plethora of practical applications, such as e-nose systems,” said Anup Vanarse, Research Scientist at BrainChip. “This latest research paper shows how Akida’s olfactory analysis technology allows for efficient and accurate detection of various strains of bacteria in blood to help with important disease diagnosis. Incorporating beneficial AI within sensory devices will provide the means for massive breakthroughs in the healthcare industry.”
I understand it's as Brainchip Research has came to this conclusion of by using AKD1000 to analyse the blood samples and achieve 97.42% again the Örebro University paper.
Learning
That's probably right, but I think there is more benefit for the Uni than Bainchip. Having their decade-old research not merely cited, but used, in relation to THE chip of the hour is a feather in their cap.
And it also does serve to expand awareness of Akida in Sweden. Who knows ... it may even trigger further cooperation with the Uni.
So it's a win-win.
And the public who get to read it, present company excepted, will mostly be involved in the relevant field of research.
Fastback6666
Regular
Ohh they are getting set and have been buying up for months now!Yep happens every year… It would be nice if it was instos getting set though
Frangipani
Regular
Hi Learning,Hi Frangipani,
I agree with what Dio said above, as this media release didn't say Brainchip (partners/ collaborate) with Örebro University. It's state this:
With findings achieved through studies by BrainChip Research, “Finding Bacteria in the Blood: Scaling a Hardware-Driven Neuromorphic Solution for Real-World E-Nose Applications” presents how a hardware-based, low-power neuromorphic solution can be combined with electronic sensors to create compelling real-world healthcare solutions that are cost-effective, portable and accurate. These assisted devices could significantly speed up disease diagnosis in remote locations, or even outside of traditional clinical facilities.
The paper explores a blood dataset collected as part of the Mednose project at Örebro University. The classifier model developed using Akida™ was able to identify ten different bacteria species in blood samples with a classification accuracy of 97.42%, outperforming previous implementations.
“Leveraging neuromorphic hardware to provide portable, power-efficient solutions for use in the identification of sensory data is a game-changer for a plethora of practical applications, such as e-nose systems,” said Anup Vanarse, Research Scientist at BrainChip. “This latest research paper shows how Akida’s olfactory analysis technology allows for efficient and accurate detection of various strains of bacteria in blood to help with important disease diagnosis. Incorporating beneficial AI within sensory devices will provide the means for massive breakthroughs in the healthcare industry.”
I understand it's as Brainchip Research has came to this conclusion of by using AKD1000 to analyse the blood samples and achieve 97.42% again the Örebro University paper.
Learning
I think you misunderstood my post: I never claimed the media release said there was a collaboration between our company and Örebro University. In fact, I myself quoted part of the research paper to prove my point. My original post was in reaction to two forum members who may not have actually read the media release, but had obviously concluded just from seeing that tweet displaying both logos that it was about some kind of collaboration with Örebro University researchers utilising Akida.
I was simply trying to stick to the facts and correct that assumption. And that’s why I called the tweet ‘somewhat misleading’, as IMO it is understandable why someone just looking at the tweet could come to that conclusion and might interpret too much into it. And these kind of misinterpretations will ultimately play into the hands of downrampers. That’s all. Apart from that ambiguous use of Örebro University’s coat of arms, I love the announcement.
Cheers,
Frangipani
P.S.: It just occurred to me that ‘misleading’ may not have been the ideal choice of adjective here, as it could imply intention?
The word I would use in German (‘missverständlich’) is much more neutral.
DerAktienDude
Regular
Obviously it’s good that BRN is updating us regarding olfactory devices but it’s nothing new. I don’t get the excitement. Back then we were debating about the possibility of having a product launched this year. Doing studies with other universities or using their samples is no valuable progress at this point.
For the newer investors this is/ was what I’m talking about.
semico.com
For the newer investors this is/ was what I’m talking about.
NaNose Medical and BrainChip Innovation | Semico Research
Semico recently published an article in our March, 2021 IPI Newsletter detailing a press release between NaNose (Nano Artificial Nose) Medical and BrainChip in which they jointly announced a new system for medical diagnosis COVID-19. This system used an artificially intelligent nano-array based...
semico.com
... and this is just one small problem with which AGI will have to wrestle.Hi Learning,
I think you misunderstood my post: I never claimed the media release said there was a collaboration between our company and Örebro University. In fact, I myself quoted part of the research paper to prove my point. My original post was in reaction to two forum members who may not have actually read the media release, but had obviously concluded just from seeing that tweet displaying both logos that it was about some kind of collaboration with Örebro University researchers utilising Akida.
I was simply trying to stick to the facts and correct that assumption. And that’s why I called the tweet ‘somewhat misleading’, as IMO it is understandable why someone just looking at the tweet could come to that conclusion and might interpret too much into it. And these kind of misinterpretations will ultimately play into the hands of downrampers. That’s all. Apart from that ambiguous use of Örebro University’s coat of arms, I love the announcement.
Cheers,
Frangipani
P.S.: It just occurred to me that ‘misleading’ may not have been the ideal choice of adjective here, as it could imply intention?
Tothemoon24
Top 20
Great little 
for the mighty chip
Thinking at the edge: How neuromorphic computing empowers edge devices
Nov 29, 2023 | Abhishek JadhavCATEGORIES Edge Computing News | Hardware
As experts in the industry believe that Moore’s Law and Dennard scaling is coming to an end, it becomes clear that the traditional approach to improving computer performance has reached its limits. To address these limitations, neuromorphic computing has emerged as a promising solution. Coined by Carver Mead in the late 1980s, the term “neuromorphic” refers to a computing approach inspired by the brain, combining analog and digital components.
Over recent years, the field of neuromorphic computing has expanded, particularly in its application to deep learning and machine learning. When we compare neuromorphic computers to von Neumann machines, which use separate CPUs and memory units, running programs based on explicit instructions, the difference is significant. Neuromorphic computers are inspired from neurons and synapses.
One key advantage of neuromorphic hardware lies in its integration of processing and memory, which helps mitigate the von Neumann bottleneck that can slow down the data processing speed. This integration also reduces the need for frequent data access from main memory, a common operation in conventional computing systems that consumes a substantial amount of energy.
In this article, we will explore the convergence of neuromorphic computing with edge devices and explore its potential benefits in distributed edge computing. Additionally, we will examine industry contributions to the field of neuromorphic computing within the specific context of edge infrastructure. Finally, we will discuss the market opportunities and the future prospects of this advanced computing technology.
Neuromorphic computing meets edge devices
One of the most interesting aspects of neuromorphic computing lies in its ability to operate with low power consumption. This capability can be attributed to two key factors – the event-driven nature of neuromorphic systems and their massive parallelism. Unlike traditional computing hardware, which continuously consumes power, neuromorphic computers only engage in computations when there are specific events or spikes to process. Its inherent parallelism allows many neurons and synapses to operate simultaneously, meaning that only a small portion of the system is active at any given time, while the rest remains idle.Both of these factors have significant implications for the efficiency and effectiveness of computing in edge environments. The event-driven characteristic is particularly advantageous when dealing with thousands of edge devices deployed in remote settings where data is generated sporadically or in response to specific events. For instance, in scenarios such as oil and gas plants, sensors may only produce data when certain parameters exceed normal values, or surveillance cameras may transmit data upon detecting motion. Event-driven processing aligns well with the need for efficient utilization of computational resources and the minimization of power consumption, which is the case of edge computing environments.
Similarly, the concept of massive parallelism holds promise for edge computing. Many edge devices now incorporate multi-core processors or specialized AI accelerators, enabling them to engage in parallel processing of tasks. Edge computing can leverage this feature to execute resource-intensive AI computations concurrently, thereby delivering high performance and quick responses for mission-critical applications. The massive parallelism enables edge devices to reduce latency, provide real-time feedback, and take data-driven actions to enhance operational efficiency within the ecosystem.
Industry contributes to embedded intelligence at the edge
Initially, a significant portion of research and industrial efforts in the field of neuromorphic hardware primarily focused on large-scale implementations that weren’t particularly suitable for edge platforms. However, Intel disrupted this landscape by introducing Loihi, a neuromorphic computing hardware platform based on open-source software frameworks designed for the development of intelligent computing applications.Intel continued its development in advancing neuromorphic technology, which led to the launch of Loihi’s second-generation, which had been developed utilizing Intel’s 4th-generation pre-production process. In this iteration, the company introduced programmable neuron models and a generalized spike messaging system, thereby opening doors to a wide array of neural network models that can be trained in deep learning.
Another embedded manufacturer in the field of commercial neuromorphic computing hardware, BrainChip recently unveiled its second-generation Akida IP solution, built on the neuromorphic principles, with a claim of delivering low-power performance in compact edge devices. This new generation enhances energy efficiency by supporting 8-bit weights, activations, and long-range skip connections, thereby making complex neural networks feasible on edge devices.
Amid all the buzz around these developments in neuromorphic hardware, it is essential to consider their future in the context of the exponential growth of generative AI, which heavily relies on cloud computing resources. As the industry moves toward hybrid AI solutions, the demand for more capable and efficient computing at the network edge becomes increasingly evident.
Neuromorphic computing hardware, such as Akida, get attention for their temporal event-based neural networks that support vision transformers, thus ensuring high accuracy for large language models. The future of these advanced computing technologies holds promise as they play a key role in addressing the evolving landscape of AI and edge computing.
Outlook on neuromorphic computing at the edge
In its 2023 report, Gartner highlights four emerging technologies expected to disrupt industries over the next three to eight years, with neuromorphic computing occupying the top position. According to the market research firm, neuromorphic computing is identified as a crucial enabler that will make a significant impact on existing products and markets.While the continuous evolution of computing hardware is a given, experts believe that there are opportunities to achieve unprecedented levels of algorithmic performance, particularly in terms of speed and energy efficiency, through the utilization of neuromorphic computers. More specifically, graph algorithms and optimization tasks stand to benefit significantly from the extensive parallelism and event-driven operations inherent to neuromorphic computing.
It is anticipated that the growth of neuromorphic computing will play an important role in supporting the requirements of generative AI. The trajectory of neuromorphic computing’s future hinges on the maturation of the technology to meet the demands of the next generation of intelligent applications.
Similar threads
