BRN Discussion Ongoing

Esq.111

Fascinatingly Intuitive.
Evening Chippers,

Just some quick math.....

That savvy seller of one share @ $561.70 AU....

Gives a rough valuation of our company ( 1,850,000,000 shares( I know this is a little light on total shares) ) =

AU $1,039,145,000,000.00 Market Cap.

=

USD $704,033,600,078.00

Exchange rate pressently... USD $1 = AU$1.475

* INTERESTING... US Gov . Just lifted their debt ceiling.... of which some $848 billion USD will be for millitary purposes????

😊.

Savvy Chipper , Gov. ? , I say.

Regards,
Esq.
 
Last edited:
  • Like
  • Haha
  • Fire
Reactions: 28 users

HopalongPetrovski

I'm Spartacus!
Evening Chippers,

Just some quick math.....

That savvy seller of one share @ $561.70 AU....

Gives a rough valuation of our company ( 1,850,000,000 shares( I know this is a little light on total shares) ) =

AU $1,039,145,000,000.00 Market Cap.

=

USD $704,033,600,078.00

Exchange rate pressently... USD $1 = AU$1.475

Savvy Chipper I say.

Regards,
Esq.
Yay, finally in the 1 trillion club along with NVIDA, Apple and Microsoft.
That didn't take long at all.
Brung it, Brainchip. 🤣
 
  • Haha
  • Like
Reactions: 14 users

cassip

Regular
From an article posted by @FrederickSchack

“A benchmark test using another video object recognition test resulted in a system that could process a 1382x512p video at 30 fps using less than 75 mW of power, in a 16 nm silicon design. This needed 50x fewer parameters and 5x fewer operations than the Resnet50 reference design.”

Then from the above:

“Xilinx appears to enjoy at least a year lead in manufacturing technology over Altera with Xilinx’s new 16nm FinFET generation silicon, which is now shipping in volume production. Xilinx has also focused on providing highly scalable solutions”

It is a fact that Brainchip has never mentioned 16nm at any point until the above interview.

It is a fact that Brainchip has had a long standing association with Xilinx.

My opinion only DYOR
FF

AKIDA BALLISTA
.... just had a look at Mercedes and their long-range-radar


Continental went into production with Mercedes 24 years ago:


for example: ARS540 is a high performance 4D premium long range radar sensor which enables highly automated driving in combination with other technologies. It provides best radar performance in a state-of-the-art sensor size.



partnership with Xilinx concerning this sensor:


In a whitepaper "Convolutional Neural Network with INT4 Optimization on Xilinx Devices White Paper"
they compare INT4 against INT8 (reminds of "4 bit are enough"?? Could this have to do with that? It is about CNNs, too)


interesting is also the whitepaper about ARM and the competitiveness (X86 vs. ARM)...

Regards
cassip
 
  • Like
  • Thinking
  • Wow
Reactions: 8 users

Diogenese

Top 20
.... just had a look at Mercedes and their long-range-radar


Continental went into production with Mercedes 24 years ago:


for example: ARS540 is a high performance 4D premium long range radar sensor which enables highly automated driving in combination with other technologies. It provides best radar performance in a state-of-the-art sensor size.



partnership with Xilinx concerning this sensor:


In a whitepaper "Convolutional Neural Network with INT4 Optimization on Xilinx Devices White Paper"
they compare INT4 against INT8 (reminds of "4 bit are enough"?? Could this have to do with that? It is about CNNs, too)


interesting is also the whitepaper about ARM and the competitiveness (X86 vs. ARM)...

Regards
cassip
Haven't looked at Xilinx patents for a couple of years, but they were using MACs in their NNs. So lots of room for improvement, even if they move to 4-bit integer.
 
  • Like
  • Fire
  • Love
Reactions: 10 users

equanimous

Norse clairvoyant shapeshifter goddess
You'll never starve in a bunker because of the sand which is there.
And never under estimate an Arab using a sandwich in a bunker

1686648578671.png
 
  • Haha
  • Like
  • Love
Reactions: 7 users
D

Deleted member 118

Guest
  • Haha
  • Like
Reactions: 12 users

Jimmy17

Regular
The calm before the storm🤣🤣 but we've been anticipating the storm for at least 2 years so that dismisses that theory
 
  • Like
  • Haha
Reactions: 9 users
Reading this article Know Labs glucose monitor is still some time away.


Recent interview;

 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 5 users

rgupta

Regular
Yay, finally in the 1 trillion club along with NVIDA, Apple and Microsoft.
That didn't take long at all.
Brung it, Brainchip. 🤣
Don't you think brainchip in a trillion club is a big hype at this time. Especially considering the most successful IP business ARM had reached a maximum valuation of 70 billion US dollars even after 25 years in business and a market leader.
I am not saying it is impossible but it is quite a distant future for us.
 
  • Like
  • Fire
  • Haha
Reactions: 9 users

charmander

Regular
Don't you think brainchip in a trillion club is a big hype at this time. Especially considering the most successful IP business ARM had reached a maximum valuation of 70 billion US dollars even after 25 years in business and a market leader.
I am not saying it is impossible but it is quite a distant future for us.
Frustrated The Big Bang Theory GIF
 
  • Haha
  • Like
Reactions: 26 users

Frangipani

Regular
Would I be correct in assuming that before taking stock you would like to wait for the Greek goddess of hunting and wilderness and her handsome giant hunter companion to safely return back home from their long-planned round-trip (literally speaking), joined by an adventurous and heroic quartet of mere mortals (all of them chosen ones, one veritably a wise man), who by then will have been the first humans in decades to dare approach the ever-changing goddess Selene and get to view a side of her that will never be revealed to the eyes of us ordinary mortals?

And that you also expect those that will have helped prepare that journey to be over the moon about ακίδα?

Or is this all Greek to you, some lunatic’s gibberish? 🤭

P.S.: I refrained from describing the said demigod companion as a “giant huntsman“, as is often done, so as not to strike terror into readers suffering from arachnophobia… Ooops, too late… 🫣
 
  • Haha
  • Like
Reactions: 5 users
S

Straw

Guest
P.S.: I refrained from describing the said demigod companion as a “giant huntsman“, as is often done, so as not to strike terror into readers suffering from arachnophobia… Ooops, too late… 🫣
When you said 'giant huntsman' I was thinking Paul Bunyan (yes a lumberjack but that was the mental picture) or a big statue of Chris Hemsworth lol
 
  • Haha
  • Like
Reactions: 7 users

Frangipani

Regular
When you said 'giant huntsman' I was thinking Paul Bunyan (yes a lumberjack but that was the mental picture) or a big statue of Chris Hemsworth lol
I actually had to google Paul Bunyan (very entertaining ‘fakelore’, thanks to which I finally learned the “truth” about how some of North America's most impressive geological features came to be, such as the Grand Canyon, the Great Lakes, the Saint Lawrence and the Mississippi River or Minnesota’s 10,000 Lakes… 😉) and now I am trying very hard to get the image of an exquisite marble statue of an ancient Greek Heracles-style superhero clad in a checked flannel shirt out of my head! 🤣

Thor with his Norse heritage would obviously feel somewhat out of place in the Olympians’ pantheon, but I get the mental picture. And I wouldn’t be surprised if others (for obvious reasons) had associated the “giant huntsman” with yet another MCU hero, gravity-defying Spider-Man.

That adjective, by the way, is another clue for those of you still on a treasure hunt (or shall I say odyssey?) for my post #58741 to make sense, in case it continues to feel all Greek or double Dutch to you. Confused German speakers unfamiliar with these idioms will instead moan about “understanding ‘train station’ only” (“Ich verstehe nur Bahnhof”), but they may also say that when they don’t want to understand what’s being said. Then again, when they claim something seems Spanish to them, they insinuate what they’ve just heard seems somewhat weird, bizarre or even fishy to them, which in fact has historical reasons, having to do with Karl/Karel/Carlo/Charles V being crowned Holy Roman Emperor in 1520 and - as King of Spain (among other titles) - introducing an unwonted royal court etiquette and language, which was not appreciated by many of his subjects. And there are similar anthropologically interesting idioms in other languages.
But I digress…

Let me conclude by saying that I doubt Stan Lee will make a posthumous cameo appearance, while our floating quartet on their trajectory will Marvel at [insert title of Pink Floyd’s recently remastered, legendary and by far most successful album, although that title is of course scientific nonsense as said location gets plenty of sunlight for two weeks a month], but that I hope Merritt Island’s high-flyers will praise Akida’s performance to the skies.
 
Last edited:
  • Wow
  • Fire
  • Haha
Reactions: 6 users

cosors

👀
TS2 SPACE
https://ts2.space/en/brain-inspired-computing-for-railway-and-public-transportation/#

The potential benefits of brain-inspired computing for railway and public transportation are numerous. For example, it could be used to improve safety by monitoring the condition of tracks and vehicles, detecting anomalies, and alerting operators in real-time. It could also be used to improve efficiency by optimizing route planning and scheduling, and to enhance customer experience by providing personalized services.​



Brain-Inspired Computing for Railway and Public Transportation​

0
Brain-Inspired Computing for Railway and Public Transportation

How Brain-Inspired Computing is Revolutionizing Railway and Public Transportation​

The railway and public transportation industries are being revolutionized by brain-inspired computing. This new technology, also known as neuromorphic computing, is based on the architecture of the human brain and has the potential to revolutionize the way railway and public transportation systems operate.

Neuromorphic computing is a form of artificial intelligence (AI) that mimics the structure and function of the human brain. It uses a network of artificial neurons to process information and learn from it. This type of computing is highly efficient and can be used to solve complex problems quickly and accurately.
Neuromorphic computing is being used to improve the efficiency of railway and public transportation systems. It can be used to analyze large amounts of data to identify patterns and make predictions about the future. This can help to optimize the operation of railway and public transportation systems, making them more efficient and reliable.
Neuromorphic computing can also be used to improve safety. It can be used to detect potential hazards on the railway or in public transportation systems and alert operators to take corrective action. This can help to reduce the risk of accidents and improve the safety of passengers.

Neuromorphic computing is also being used to improve the customer experience. It can be used to analyze customer data and identify trends in customer behavior. This can help to improve the services offered by railway and public transportation systems, making them more attractive to customers.
Neuromorphic computing is revolutionizing the railway and public transportation industries. It is enabling more efficient and reliable operations, improving safety, and enhancing the customer experience. This technology is set to have a major impact on the future of these industries.

Exploring the Benefits of Brain-Inspired Computing for Railway and Public Transportation​


The railway and public transportation industry is rapidly evolving to meet the needs of an increasingly connected world. As such, the industry is exploring the potential of brain-inspired computing to improve safety, efficiency, and customer experience.
Brain-inspired computing, also known as neuromorphic computing, is a type of artificial intelligence (AI) that mimics the human brain’s neural networks. It is capable of processing large amounts of data in real-time and making decisions quickly and accurately. This makes it ideal for applications in the railway and public transportation industry, where safety and efficiency are paramount.
The potential benefits of brain-inspired computing for railway and public transportation are numerous. For example, it could be used to improve safety by monitoring the condition of tracks and vehicles, detecting anomalies, and alerting operators in real-time. It could also be used to improve efficiency by optimizing route planning and scheduling, and to enhance customer experience by providing personalized services.

In addition, brain-inspired computing could be used to reduce energy consumption and emissions. By analyzing data from sensors, it could identify areas where energy consumption could be reduced, such as reducing speed in certain sections of the track or using alternative routes.
Brain-inspired computing could also be used to improve security. By analyzing data from surveillance cameras, it could detect suspicious activity and alert security personnel in real-time.
The railway and public transportation industry is already beginning to explore the potential of brain-inspired computing. Several companies have already developed AI-based solutions for the industry, and more are expected to follow suit.
As the industry continues to evolve, brain-inspired computing could become an essential tool for improving safety, efficiency, and customer experience. It could also help reduce energy consumption and emissions, as well as improve security. The potential benefits of brain-inspired computing for railway and public transportation are clear, and the industry is only beginning to explore its possibilities.

The Impact of Brain-Inspired Computing on Railway and Public Transportation Safety​

The advent of brain-inspired computing is revolutionizing the safety of railway and public transportation systems. This new technology, which mimics the functioning of the human brain, is being used to develop sophisticated algorithms that can detect potential safety risks and provide real-time alerts to operators.
Brain-inspired computing is helping to improve the safety of railway and public transportation systems in a number of ways. For example, it can be used to detect anomalies in train movements, such as sudden speed changes or unexpected stops. This information can then be used to alert operators to potential safety risks and enable them to take corrective action.
Brain-inspired computing can also be used to detect potential safety hazards in public transportation systems. For example, it can be used to identify objects or people on the tracks, as well as any obstacles that may be blocking the path of a train. This information can then be used to alert operators and help them take appropriate action to avoid any potential accidents.
In addition, brain-inspired computing can be used to monitor the condition of railway infrastructure, such as bridges and tunnels. This information can then be used to alert operators to any potential safety risks, such as structural damage or corrosion.
Overall, brain-inspired computing is having a significant impact on the safety of railway and public transportation systems. By providing real-time alerts to operators, it is helping to reduce the risk of accidents and ensure that passengers are kept safe.

How Brain-Inspired Computing is Enhancing the Efficiency of Railway and Public Transportation​

The use of brain-inspired computing is revolutionizing the efficiency of railway and public transportation systems around the world. By leveraging the power of artificial intelligence (AI) and machine learning, these systems are able to optimize operations and provide better service to passengers.
Brain-inspired computing is a form of AI that mimics the way the human brain works. It is based on the principles of neuroscience and uses algorithms to learn from data and make decisions. This type of computing has been used to develop systems that can predict traffic patterns, optimize routes, and improve safety.
Railway and public transportation systems are now leveraging brain-inspired computing to enhance their operations. For example, AI-powered systems can be used to monitor the condition of railway tracks and identify potential problems before they become serious. This helps to reduce delays and improve safety. AI can also be used to predict passenger demand and optimize routes to ensure that trains and buses are running on time.
In addition, AI-powered systems can be used to improve customer service. AI can be used to identify patterns in customer behavior and provide personalized recommendations. This can help to improve the overall experience for passengers.
Brain-inspired computing is also being used to improve the efficiency of railway and public transportation systems. AI-powered systems can be used to identify inefficiencies in operations and suggest improvements. This can help to reduce costs and improve the overall efficiency of the system.

The use of brain-inspired computing is revolutionizing the efficiency of railway and public transportation systems around the world. By leveraging the power of AI and machine learning, these systems are able to optimize operations and provide better service to passengers.

Examining the Challenges of Implementing Brain-Inspired Computing in Railway and Public Transportation​

Recent advances in artificial intelligence (AI) and machine learning have enabled the development of brain-inspired computing, which has the potential to revolutionize the way railway and public transportation systems are managed. However, there are several challenges associated with implementing this technology in these industries.
One of the biggest challenges is the complexity of the railway and public transportation systems. In order to effectively use brain-inspired computing, these systems must be able to accurately capture and analyze vast amounts of data from multiple sources. This data must then be used to make decisions in real-time, which can be difficult to achieve with traditional computing methods.

Another challenge is the cost associated with implementing brain-inspired computing. This technology requires significant investments in hardware and software, as well as specialized personnel to manage and maintain the system. Additionally, the technology is still in its early stages of development, so there is a risk that the system may not be able to meet the needs of the railway and public transportation industries.
Finally, there is the challenge of ensuring the security and privacy of the data collected by the system. As the system collects and stores large amounts of sensitive data, there is a risk that it could be accessed by unauthorized parties. This could lead to serious security and privacy issues, which must be addressed before the system can be successfully implemented.
Despite these challenges, brain-inspired computing has the potential to revolutionize the way railway and public transportation systems are managed. By enabling faster and more accurate decision-making, this technology could lead to improved safety, efficiency, and cost savings for these industries. As such, it is important for the industry to continue to invest in this technology and find ways to overcome the challenges associated with its implementation.

© 2023 TS2 Space Sp. z o.o.​

Tel: +48 22 364 58 00, +48 22 630 70 70
VAT
PL7010612151
KRS 0000635058
REGON 365328479
EORI PL701061215100000
RPT 11918
NCAGE 99B8H
DUNS 422248638
Address: LIM Center XVI, Aleje Jerozolimskie 65/79, 00-697 Warsaw, Poland
TS2 SPACE provides telecommunications services by using the global satellite constellations. We offer you all possibilities of using satellites to send data and voice, as well as appropriate data encryption. Solutions provided by TS2 SPACE work where traditional communication is difficult or impossible.
Shop | ISP | AI

Now they have posted a similar article but with a different subject:

"Benefits of Neuromorphic Computing for Smart Energy Management and Grid Control​

0
Benefits of Neuromorphic Computing for Smart Energy Management and Grid Control

Exploring the Potential of Neuromorphic Computing to Power Smart Energy Management​

Smart energy management systems are revolutionizing the way we interact with and use energy. As the world continues to move towards a more sustainable energy future, the need for smarter and more efficient energy management systems becomes increasingly important. To meet this need, researchers are exploring the potential of neuromorphic computing to enhance smart energy management.
Neuromorphic computing is a type of computing that mimics the neural networks of the human brain. By leveraging the principles of artificial intelligence , neuromorphic computing can provide energy managers with more efficient and reliable ways to manage and optimize energy consumption.
Neuromorphic computing can be used to monitor the energy consumption of individual devices as well as entire systems. This allows energy managers to quickly identify system inefficiencies and make necessary adjustments to optimize energy consumption. In addition, neuromorphic computing can be used to predict future energy demand, giving energy managers time to plan and prepare for future energy demand.
Neuromorphic computing can also be used to improve energy security. Using AI-enabled algorithms, energy managers can detect energy usage anomalies and quickly identify potential threats. This helps ensure the safety and reliability of your energy system.
Finally, neuromorphic computing can be used to create more intelligent and efficient energy management systems. By integrating AI into energy management systems, energy managers can create more responsive and adaptive systems that can quickly respond to changes in energy demand. This helps reduce waste and maximize energy efficiency.
Overall, neuromorphic computing has the potential to revolutionize how we manage and optimize energy. By integrating AI into energy management systems, energy managers can create more intelligent and efficient systems that help ensure the safety, reliability and efficiency of energy supplies.

How Neuromorphic Computing Streamlines Grid Control Systems​

The introduction of neuromorphic computing into grid control systems could revolutionize the way such systems are managed. Neuromorphic computing is a form of artificial intelligence (AI) inspired by the structure and function of the human brain. This technology uses specialized circuitry to simulate the way neurons in the brain interact with each other. In other words, neuromorphic computing mimics the behavior of neurons in the brain to enable machines to think more like humans.
One of the ways neuromorphic computing streamlines grid control systems is by allowing machines to learn from their environment. Neuromorphic computing uses sensors and AI algorithms to detect patterns in data in real time and can adapt to changes in the environment. This makes the grid control system more sensitive to changes in power demand and supply, potentially improving efficiency and reliability.
Another way neuromorphic computing can streamline grid control systems is by allowing machines to make decisions based on their environment. Using AI algorithms, neuromorphic computing can predict how best to adjust the grid to optimize performance. This could improve power delivery and reduce costs associated with maintaining the grid.
Finally, neuromorphic computing can also be used to improve the security of grid control systems. By using AI algorithms, neuromorphic computing can detect system anomalies and take appropriate measures to prevent malicious intrusions. This could ensure that the grid is protected from cyberattacks.
Overall, the introduction of neuromorphic computing into grid control systems has the potential to significantly improve the efficiency, reliability, and security of such systems. Neuromorphic computing has the potential to revolutionize the way grid control systems are managed by enabling machines to learn from their environment and make data-driven decisions in real time.

Exploring the Benefits of Neuromorphic Computing for Smart Energy Management​

Smart energy management is becoming increasingly important in the face of rising energy costs and environmental concerns. To this end, neuromorphic computing has the potential to revolutionize how energy systems are managed.
Neuromorphic computing is a form of artificial intelligence that mimics the functions of the human brain. It is based on neural network principles and designed to be very efficient, making it an ideal tool for energy management.
Neuromorphic computing is more efficient than traditional computing systems because it uses a distributed network of low-power computing nodes. This means that less energy is required to process data, making it more cost effective than traditional computing systems.
Moreover, neuromorphic computing is more scalable and easily adaptable to different energy management scenarios. This makes it ideal for developing applications such as smart grids, energy storage systems and renewable energy systems.
Neuromorphic computing can also learn from the environment and adapt to changing conditions. This makes it ideal for real-time energy management as it can quickly adapt to changes in demand and prices.
Finally, neuromorphic computing provides greater insight into energy usage patterns, enabling more efficient energy management. This can significantly reduce energy costs and improve environmental performance.
Overall, neuromorphic computing promises to revolutionize the way energy systems are managed. It is more efficient, scalable, and adaptable than traditional computing systems, making it an ideal tool for smart energy management.

Neuromorphic Computing: Force Multipliers in Smart Energy Management​

Neuromorphic computing is fast becoming an essential technology for smart energy management. This technology combines the latest advances in artificial intelligence (AI) and machine learning with the power of data analytics to create a powerful power multiplier in the field of energy management.
Neuromorphic computing is a form of machine intelligence that mimics how the human brain works. It uses machine learning algorithms to process data and make decisions in real time. This technology can help you quickly identify patterns of energy use, detect anomalies in energy consumption, and identify opportunities for energy efficiency.
Neuromorphic computing is also helping reduce the cost of energy management. By using AI algorithms, energy management systems can quickly detect and respond to changes in energy demand, thus optimizing energy usage and reducing energy costs. Neuromorphic computing can also help reduce the complexity of energy management by automating processes and reducing the amount of manual intervention required.
The use of neuromorphic computing in energy management is still in its infancy, but the potential is clear. This technology helps energy managers make better decisions and reduce energy costs by optimizing energy usage. Already, some of the world's leading energy companies have invested in neuromorphic computing, which is expected to become a standard part of smart energy management in the near future.

Integrating Neuromorphic Computing into Smart Energy Management Strategies for Grid Control​

The energy industry is evolving rapidly to meet the growing demand for clean and renewable energy sources. With the advent of smart energy management strategies, the industry is leveraging cutting edge technology to optimize energy production and consumption. One of his most promising advances in the field is the integration of neuromorphic computing into smart energy management strategies for grid control.
Neuromorphic computing is a type of artificial intelligence that emulates the biological neural networks found in the human brain. This technology has the potential to revolutionize how energy grids are managed because it can process large amounts of data quickly and accurately. With this technology, you can optimize your energy grid to efficiently manage energy production and consumption, minimizing waste and inefficiency.
Neuromorphic computing can be used to enable smart energy management strategies such as load balancing, peak load management, and energy forecasting. Load balancing is a method of using sensors to monitor energy consumption and adjust supply accordingly. Peak load management is a method of using sensors to detect times of high energy consumption in an area and automatically adjusting supply to meet demand. Energy forecasting is a method of using sensors and data analytics to forecast future energy demand and adjust supply accordingly.
Integrating neuromorphic computing into smart energy management strategies can optimize energy grids for greater efficiency and reliability. This technology can be used to improve the accuracy of energy forecasting, optimize load distribution, and reduce peak load demand. Additionally, neuromorphic computing can be used to detect potential failures in the grid and take action to prevent outages and other problems.
Integrating neuromorphic computing into smart energy management strategies is a major advancement in the industry. With this technology, you can optimize your energy grid for efficiency and reliability while minimizing waste and inefficiency. As the industry continues to evolve, neuromorphic computing will become a key tool in the smart energy management toolkit.

Post navigation​

Beforerevious post:The Importance of Satellites for Space-Based Cybersecurity and Intelligence"

https://ts2.space/ja/スマート-エネルギー管理とグリッド制御のため-2/

Strangely enough, the post is in Japanese and the company is from Poland.
 
Last edited:
  • Like
  • Love
  • Fire
Reactions: 26 users

goodvibes

Regular
Nothing to do with BRN…just SNN.


Spiking Neural Networks (SNNs) have gained significant attention as an energy-efficient machine learning solution. With growing interest in the SNN algorithms, it is mandatory to understand the overheads of SNNs when implemented on real hardware accelerators. Most SNN training works are algorithm-focused and estimate the energy-efficiency of SNNs with metrics such as spike data sparsity (i.e., higher data sparsity equals higher energy-efficiency). However, sparsity is not a valid metric to claim energy-efficiency in real hardware. To this end, our recent works in IEEE TCAD propose two hardware evaluation platforms for SNN- SATA and SpikeSim.

SATA is a sparsity-aware systolic array based training accelerator architecture for state-of-the-art Backpropagation Through Time (BPTT)-based SNN training. From SATA, we find that repetitive data-movements across time-steps hinder the energy-efficiency of SNNs.
SpikeSim is an inference evaluation platform for SNNs on In-memory Computing (IMC) architectures (Collaborative work with Prof. Yu (Kevin) Cao). In SpikeSim, we find that SNNs are specifically prone to crossbar non-idealities and incur large membrane potential memory area in the LIF neuronal module owing to repeated computations over multiple time-steps.
Both SATA and SpikeSim motivate redesigning SNN algorithms to make them more energy efficient on the hardware.

More insights and results from SATA and SpikeSim can be found in the papers at https://lnkd.in/ecXHrPbu; https://lnkd.in/eiHDMADu.

Codes for SpikeSim and SATA are available at:
SATA - https://lnkd.in/eaFFe6cc
SpikeSim - https://lnkd.in/eBz5ZnRD

#SpikingNeuralNetworks #NeuromorphicComputing #HardwareBenchmarking #InMemoryComputing
 
  • Like
  • Fire
Reactions: 6 users

charles2

Regular
"Wouldn't it be lovely......"

 
  • Like
  • Love
  • Fire
Reactions: 12 users

equanimous

Norse clairvoyant shapeshifter goddess
 
  • Like
  • Love
  • Fire
Reactions: 47 users

Quiltman

Regular
In the league of legends ....

1686696313535.png
 
  • Like
  • Love
  • Fire
Reactions: 38 users

IloveLamp

Top 20
  • Like
  • Wow
  • Thinking
Reactions: 16 users
Top Bottom