Seams like some people put each other into ignorlist… not your fault
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Luppo71
Founding Member
Been here since day one and don't have anyone one on ignore.Seams like some people put each other into ignorlist… not your fault
Although you've come close a couple times.
Sometimes I don't understand why people always react so aggressively... I sometimes think that many people just want to vent their frustration and do so on the first person they find... In my case, I didn't even write anything against you but simply shared a general observation. I even wrote that it wasn't your fault that others before you posted the same thing several times. Anyway... I really don't care how long you've been here, whether you're the king of a tribe in Papua New Guinea, or Elon Musk in disguise. If you feel the need to put me on ignore for trivial matters, then just do it... or do you think I'm now scared and thinking 'Oh no... he's considering blocking me'? Ridiculous.
You are painful.
Space Cadet
Regular
Come on 7 of 9. I took it as humour although sometimes it is hard to get the correct context of someone's post. The ironic thing is if it were just in jest, you are doing what you just accused him of.
SC
Alright then, if he meant it as a joke, he can just tell me... then I'll apologize
it's no problem... until then, what I wrote stands. That's clear. Anyway .. I think this topic is quite overrated and most of the people here are not interested on personal fights…. As I said. I am always kind, yes sometimes I post also „unfunny funny stuff“. But just because I am waiting here for really huge news. Until there are no news, everyone is posting his stuff…. Akida inside even there is no connection to us… articles from 250 years ago about how people imagined the future etc… sometimes some childish posts like how ugly our CEO looks on pics or why he is using simple toilet paper instead of silk based one…
Last edited:
Space Cadet
Regular
We're all a little frustrated. All good. Just.pointing out it is hard to understand what someone means in written word on a forum. Unless of course someone fires both barrels at someone and leaves no doubt.Alright then, if he meant it as a joke, he can just tell me... then I'll apologize
SC
I am also frustrated, and i am getting closer to putting my money elsewhere. I do believe in the product, but bank interest over the last 4 years would have been better. Not sure I can listen to this is our year again in 2025.
Thinking of switching shares and maybe jump back in on the way up after a concrete ip sign up or Ann that we are in this or that product.
Now to enjoy the weekend, off to broadbeach for a week.
Thinking of switching shares and maybe jump back in on the way up after a concrete ip sign up or Ann that we are in this or that product.
Now to enjoy the weekend, off to broadbeach for a week.
ANt61 confirmed in the comments akida inside
CHIPS
Regular
Last edited:
Smoothsailing
Regular
Might pay to open my eyes you recon
Luppo71
Founding Member
Its pretty simple, your post insinuated that if i didn't put people on ignore then i might know what has been posted.
i wasn't having a go at you, my comment was nothing more than that, you are the only person i have thought about ignoring.
Conversation over.
Last month, we had the honour of presenting our neuromorphic technology to edge-computing and in-orbit servicing program leaders at ESA/ESTEC. | ANT61
Last month, we had the honour of presenting our neuromorphic technology to edge-computing and in-orbit servicing program leaders at ESA/ESTEC. It's a significant milestone for us, as we are looking to partner with European satellite operators and manufacturers to enhance their future missions...
DingoBorat
Slim
I think it's just a cultural thing SC..We're all a little frustrated. All good. Just.pointing out it is hard to understand what someone means in written word on a forum. Unless of course someone fires both barrels at someone and leaves no doubt.
SC
I tried Googling "German comedians" and this is all that came up
..
Last month, we had the honour of presenting our neuromorphic technology to edge-computing and in-orbit servicing program leaders at ESA/ESTEC. | ANT61
Last month, we had the honour of presenting our neuromorphic technology to edge-computing and in-orbit servicing program leaders at ESA/ESTEC. It's a significant milestone for us, as we are looking to partner with European satellite operators and manufacturers to enhance their future missions...www.linkedin.com
View attachment 68741 View attachment 68742 View attachment 68743
Does anyone else get the feeling this snowball is starting to roll?
It's not my fault that you took my first post so seriously. I even added smileys, but it seems like you have a problem with me. Just ignore me if you want peace of mind, like 3/4 of the forum does. So, let's consider the topic closed now
Pom down under
Top 20
So glad I only use picturesWe're all a little frustrated. All good. Just.pointing out it is hard to understand what someone means in written word on a forum. Unless of course someone fires both barrels at someone and leaves no doubt.
SC
Fullmoonfever
Top 20
Be nice if they were speaking to us...might help them.
At least they acknowledging the potential power of SNN as they put it and are exploring ...it's a start.
By Dongsheng Li , Principal Research Manager Dongqi Han , Researcher Yansen Wang , Researcher
As AI research and technology development continue to advance, there is also a need to account for the energy and infrastructure resources required to manage large datasets and execute difficult computations. When we look to nature for models of efficiency, the human brain stands out, resourcefully handling complex tasks. Inspired by this, researchers at Microsoft are seeking to understand the brain’s efficient processes and replicate them in AI.
At Microsoft Research Asia(opens in new tab), in collaboration with Fudan University(opens in new tab), Shanghai Jiao Tong University(opens in new tab), and the Okinawa Institute of Technology(opens in new tab), three notable projects are underway. One introduces a neural network that simulates the way the brain learns and computes information; another enhances the accuracy and efficiency of predictive models for future events; and a third improves AI’s proficiency in language processing and pattern prediction. These projects, highlighted in this blog post, aim not only to boost performance but also significantly reduce power consumption, paving the way for more sustainable AI technologies.
Figure 1: The four neural connectivity patterns in the brain. Each circle represents a neuron, and each arrow represents a synapse.
Inspired by this biological architecture, researchers have developed CircuitNet, a neural network that replicates multiple types of connectivity patterns. CircuitNet’s design features a combination of densely connected local nodes and fewer connections between distant regions, enabling enhanced signal transmission through circuit motif units (CMUs)—small, recurring patterns of connections that help to process information. This structure, shown in Figure 2, supports multiple rounds of signal processing, potentially advancing how AI systems handle complex information.
Figure 2. CircuitNet’s architecture: A generic neural network performs various tasks, accepts different inputs, and generates corresponding outputs (left). CMUs keep most connections local with few long-distance connections, promoting efficiency (middle). Each CMU has densely interconnected neurons to model universal circuit patterns (right).
Evaluation results are promising. CircuitNet outperformed several popular neural network architectures in function approximation, reinforcement learning, image classification, and time-series prediction. It also achieved comparable or better performance than other neural networks, often with fewer parameters, demonstrating its effectiveness and strong generalization capabilities across various machine learning tasks. Our next step is to test CircuitNet’s performance on large-scale models with billions of parameters.
To improve SNN’s predictive capabilities, researchers have proposed an SNN framework designed to predict trends over time, such as electricity consumption or traffic patterns. This approach utilizes the efficiency of spiking neurons in processing temporal information and synchronizes time-series data—collected at regular intervals—and SNNs. Two encoding layers transform the time-series data into spike sequences, allowing the SNNs to process them and make accurate predictions, shown in Figure 3.
Figure 3. A new framework for SNN-based time-series prediction: Time series data is encoded into spikes using a novel spike encoder (middle, bottom). The spikes are then processed by SNN models (Spike-TCN, Spike-RNN, and Spike-Transformer) for learning (top). Finally, the learned features are fed into the projection layer for prediction (bottom-right).
Tests show that this SNN approach is very effective for time-series prediction, often matching or outperforming traditional methods while significantly reducing energy consumption. SNNs successfully capture temporal dependencies and model time-series dynamics, offering an energy-efficient approach closely aligns with how the brain processes information. We plan to continue exploring ways to further improve SNNs based on the way the brain processes information.
Figure 4: Application of CPG-PE in an SNN. X, X′, and X-output are spike matrices.
We evaluated CPG-PE using four real-world datasets: two covering traffic patterns, and one each for electricity consumption and solar energy. Results demonstrate that SNNs using this method significantly outperform those without positional encoding (PE), shown in Table 1. Moreover, CPG-PE can be easily integrated into any SNN designed for sequence processing, making it adaptable to a wide range of neuromorphic chips and SNN hardware.
Table 1: Evaluation results of time-series forecasting on two benchmarks with prediction lengths 6, 24, 48, 96. “Metr-la” and “Pems-bay” are traffic-pattern datasets. The best SNN results are in bold. The up-arrows indicate a higher score, representing better performance.
At least they acknowledging the potential power of SNN as they put it and are exploring ...it's a start.
Brain-inspired design for more capable and sustainable AI
Researchers and their collaborators are drawing inspiration from the brain to develop more sustainable AI models. Projects like CircuitNet and CPG-PE improve performance and energy efficiency by mimicking the brain's neural patterns:
www.microsoft.com
Microsoft Research Blog
Innovations in AI: Brain-inspired design for more capable and sustainable technology
Published August 29, 2024By Dongsheng Li , Principal Research Manager Dongqi Han , Researcher Yansen Wang , Researcher
As AI research and technology development continue to advance, there is also a need to account for the energy and infrastructure resources required to manage large datasets and execute difficult computations. When we look to nature for models of efficiency, the human brain stands out, resourcefully handling complex tasks. Inspired by this, researchers at Microsoft are seeking to understand the brain’s efficient processes and replicate them in AI.
At Microsoft Research Asia(opens in new tab), in collaboration with Fudan University(opens in new tab), Shanghai Jiao Tong University(opens in new tab), and the Okinawa Institute of Technology(opens in new tab), three notable projects are underway. One introduces a neural network that simulates the way the brain learns and computes information; another enhances the accuracy and efficiency of predictive models for future events; and a third improves AI’s proficiency in language processing and pattern prediction. These projects, highlighted in this blog post, aim not only to boost performance but also significantly reduce power consumption, paving the way for more sustainable AI technologies.
CircuitNet simulates brain-like neural patterns
Many AI applications rely on artificial neural networks, designed to mimic the brain’s complex neural patterns. These networks typically replicate only one or two types of connectivity patterns. In contrast, the brain propagates information using a variety of neural connection patterns, including feedforward excitation and inhibition, mutual inhibition, lateral inhibition, and feedback inhibition (Figure 1). These networks contain densely interconnected local areas with fewer connections between distant regions. Each neuron forms thousands of synapses to carry out specific tasks within its region, while some synapses link different functional clusters—groups of interconnected neurons that work together to perform specific functions.
Inspired by this biological architecture, researchers have developed CircuitNet, a neural network that replicates multiple types of connectivity patterns. CircuitNet’s design features a combination of densely connected local nodes and fewer connections between distant regions, enabling enhanced signal transmission through circuit motif units (CMUs)—small, recurring patterns of connections that help to process information. This structure, shown in Figure 2, supports multiple rounds of signal processing, potentially advancing how AI systems handle complex information.
Evaluation results are promising. CircuitNet outperformed several popular neural network architectures in function approximation, reinforcement learning, image classification, and time-series prediction. It also achieved comparable or better performance than other neural networks, often with fewer parameters, demonstrating its effectiveness and strong generalization capabilities across various machine learning tasks. Our next step is to test CircuitNet’s performance on large-scale models with billions of parameters.
Spiking neural networks: A new framework for time-series prediction
Spiking neural networks (SNNs) are emerging as a powerful type of artificial neural network, noted for their energy efficiency and potential application in fields like robotics, edge computing, and real-time processing. Unlike traditional neural networks, which process signals continuously, SNNs activate neurons only upon reaching a specific threshold, generating spikes. This approach simulates the way the brain processes information and conserves energy. However, SNNs are not strong at predicting future events based on historical data, a key function in sectors like transportation and energy.To improve SNN’s predictive capabilities, researchers have proposed an SNN framework designed to predict trends over time, such as electricity consumption or traffic patterns. This approach utilizes the efficiency of spiking neurons in processing temporal information and synchronizes time-series data—collected at regular intervals—and SNNs. Two encoding layers transform the time-series data into spike sequences, allowing the SNNs to process them and make accurate predictions, shown in Figure 3.
Tests show that this SNN approach is very effective for time-series prediction, often matching or outperforming traditional methods while significantly reducing energy consumption. SNNs successfully capture temporal dependencies and model time-series dynamics, offering an energy-efficient approach closely aligns with how the brain processes information. We plan to continue exploring ways to further improve SNNs based on the way the brain processes information.
Refining SNN sequence prediction
While SNNs can help models predict future events, research has shown that its reliance on spike-based communication makes it challenging to directly apply many techniques from artificial neural networks. For example, SNNs struggle to effectively process rhythmic and periodic patterns found in natural language processing and time-series analysis. In response, researchers developed a new approach for SNNs called CPG-PE, which combines two techniques:- Central pattern generators (CPGs): Neural networks in the brainstem and spinal cord that autonomously generate rhythmic patterns, controlling function like moving, breathing, and chewing
- Positional encoding (PE): A process that helps artificial neural networks discern the order and relative positions of elements within a sequence
We evaluated CPG-PE using four real-world datasets: two covering traffic patterns, and one each for electricity consumption and solar energy. Results demonstrate that SNNs using this method significantly outperform those without positional encoding (PE), shown in Table 1. Moreover, CPG-PE can be easily integrated into any SNN designed for sequence processing, making it adaptable to a wide range of neuromorphic chips and SNN hardware.
Ongoing AI research for greater capability, efficiency, and sustainability
The innovations highlighted in this blog demonstrate the potential to create AI that is not only more capable but also more efficient. Looking ahead, we’re excited to deepen our collaborations and continue applying insights from neuroscience to AI research, continuing our commitment to exploring ways to develop more sustainable technology.
Bravo
If ARM was an arm, BRN would be its biceps💪!
Be nice if they were speaking to us...might help them.
At least they acknowledging the potential power of SNN as they put it and are exploring ...it's a start.
Brain-inspired design for more capable and sustainable AI
Researchers and their collaborators are drawing inspiration from the brain to develop more sustainable AI models. Projects like CircuitNet and CPG-PE improve performance and energy efficiency by mimicking the brain's neural patterns:www.microsoft.com
Microsoft Research Blog
Innovations in AI: Brain-inspired design for more capable and sustainable technology
Published August 29, 2024
By Dongsheng Li , Principal Research Manager Dongqi Han , Researcher Yansen Wang , Researcher
As AI research and technology development continue to advance, there is also a need to account for the energy and infrastructure resources required to manage large datasets and execute difficult computations. When we look to nature for models of efficiency, the human brain stands out, resourcefully handling complex tasks. Inspired by this, researchers at Microsoft are seeking to understand the brain’s efficient processes and replicate them in AI.
At Microsoft Research Asia(opens in new tab), in collaboration with Fudan University(opens in new tab), Shanghai Jiao Tong University(opens in new tab), and the Okinawa Institute of Technology(opens in new tab), three notable projects are underway. One introduces a neural network that simulates the way the brain learns and computes information; another enhances the accuracy and efficiency of predictive models for future events; and a third improves AI’s proficiency in language processing and pattern prediction. These projects, highlighted in this blog post, aim not only to boost performance but also significantly reduce power consumption, paving the way for more sustainable AI technologies.
CircuitNet simulates brain-like neural patterns
Many AI applications rely on artificial neural networks, designed to mimic the brain’s complex neural patterns. These networks typically replicate only one or two types of connectivity patterns. In contrast, the brain propagates information using a variety of neural connection patterns, including feedforward excitation and inhibition, mutual inhibition, lateral inhibition, and feedback inhibition (Figure 1). These networks contain densely interconnected local areas with fewer connections between distant regions. Each neuron forms thousands of synapses to carry out specific tasks within its region, while some synapses link different functional clusters—groups of interconnected neurons that work together to perform specific functions.
Figure 1: The four neural connectivity patterns in the brain. Each circle represents a neuron, and each arrow represents a synapse.
Inspired by this biological architecture, researchers have developed CircuitNet, a neural network that replicates multiple types of connectivity patterns. CircuitNet’s design features a combination of densely connected local nodes and fewer connections between distant regions, enabling enhanced signal transmission through circuit motif units (CMUs)—small, recurring patterns of connections that help to process information. This structure, shown in Figure 2, supports multiple rounds of signal processing, potentially advancing how AI systems handle complex information.
Figure 2. CircuitNet’s architecture: A generic neural network performs various tasks, accepts different inputs, and generates corresponding outputs (left). CMUs keep most connections local with few long-distance connections, promoting efficiency (middle). Each CMU has densely interconnected neurons to model universal circuit patterns (right).
Evaluation results are promising. CircuitNet outperformed several popular neural network architectures in function approximation, reinforcement learning, image classification, and time-series prediction. It also achieved comparable or better performance than other neural networks, often with fewer parameters, demonstrating its effectiveness and strong generalization capabilities across various machine learning tasks. Our next step is to test CircuitNet’s performance on large-scale models with billions of parameters.
Spiking neural networks: A new framework for time-series prediction
Spiking neural networks (SNNs) are emerging as a powerful type of artificial neural network, noted for their energy efficiency and potential application in fields like robotics, edge computing, and real-time processing. Unlike traditional neural networks, which process signals continuously, SNNs activate neurons only upon reaching a specific threshold, generating spikes. This approach simulates the way the brain processes information and conserves energy. However, SNNs are not strong at predicting future events based on historical data, a key function in sectors like transportation and energy.
To improve SNN’s predictive capabilities, researchers have proposed an SNN framework designed to predict trends over time, such as electricity consumption or traffic patterns. This approach utilizes the efficiency of spiking neurons in processing temporal information and synchronizes time-series data—collected at regular intervals—and SNNs. Two encoding layers transform the time-series data into spike sequences, allowing the SNNs to process them and make accurate predictions, shown in Figure 3.
Figure 3. A new framework for SNN-based time-series prediction: Time series data is encoded into spikes using a novel spike encoder (middle, bottom). The spikes are then processed by SNN models (Spike-TCN, Spike-RNN, and Spike-Transformer) for learning (top). Finally, the learned features are fed into the projection layer for prediction (bottom-right).
Tests show that this SNN approach is very effective for time-series prediction, often matching or outperforming traditional methods while significantly reducing energy consumption. SNNs successfully capture temporal dependencies and model time-series dynamics, offering an energy-efficient approach closely aligns with how the brain processes information. We plan to continue exploring ways to further improve SNNs based on the way the brain processes information.
Refining SNN sequence prediction
While SNNs can help models predict future events, research has shown that its reliance on spike-based communication makes it challenging to directly apply many techniques from artificial neural networks. For example, SNNs struggle to effectively process rhythmic and periodic patterns found in natural language processing and time-series analysis. In response, researchers developed a new approach for SNNs called CPG-PE, which combines two techniques:
By integrating these two techniques, CPG-PE helps SNNs discern the position and timing of signals, improving their ability to process time-based information. This process is shown in Figure 4.
- Central pattern generators (CPGs): Neural networks in the brainstem and spinal cord that autonomously generate rhythmic patterns, controlling function like moving, breathing, and chewing
- Positional encoding (PE): A process that helps artificial neural networks discern the order and relative positions of elements within a sequence
Figure 4: Application of CPG-PE in an SNN. X, X′, and X-output are spike matrices.
We evaluated CPG-PE using four real-world datasets: two covering traffic patterns, and one each for electricity consumption and solar energy. Results demonstrate that SNNs using this method significantly outperform those without positional encoding (PE), shown in Table 1. Moreover, CPG-PE can be easily integrated into any SNN designed for sequence processing, making it adaptable to a wide range of neuromorphic chips and SNN hardware.
Table 1: Evaluation results of time-series forecasting on two benchmarks with prediction lengths 6, 24, 48, 96. “Metr-la” and “Pems-bay” are traffic-pattern datasets. The best SNN results are in bold. The up-arrows indicate a higher score, representing better performance.
Ongoing AI research for greater capability, efficiency, and sustainability
The innovations highlighted in this blog demonstrate the potential to create AI that is not only more capable but also more efficient. Looking ahead, we’re excited to deepen our collaborations and continue applying insights from neuroscience to AI research, continuing our commitment to exploring ways to develop more sustainable technology.
Here's another example of Microsoft researching SNN's. Research paper published Feb 2024.
This one looks like it would be a perfect fit with incorporation of TENNs.
Efficient and Effective Time-Series Forecasting with Spiking Neural Networks - Microsoft Research
Spiking neural networks (SNNs), inspired by the spiking behavior of biological neurons, provide a unique pathway for capturing the intricacies of temporal data. However, applying SNNs to time-series forecasting is challenging due to difficulties in effective temporal alignment, complexities in...
www.microsoft.com
Last edited:
Similar threads
