BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
MDhere
Regular
foxdog firstly resorting to calling a fellow brner a peanut is rude. Secondly i can hold "forever" as in always for example if brn paid divideds i can hold them them and when I pass away well i guess my children can decide. Your concept of can't hold forever is subject to your individual idea of what forever is. Have a great night foxdog.
rgupta
Regular
If it goes that far I assume we are in a big trouble. Not just because of second strike but also that will mean not enough developments for the company as well
On a serious note I feel results will start coming before end of this year.
We must start recieving some royality payment by end of 2023 and on top we may get a few licence deals by that time.
Atleast renasas will tape out their chip. Akida 1500 will be available and we should see much more positivity.
Fingers crossed but donot want to over react.
Dyor
Apologies fellow brner - I'm just having a vent brought on by current impatience and frustration. Nothing personal intended
cosors
👀
"Why We Need to Re-Engineer AI to Work Like the Brain to Save on Energy
17 August, 2023Dr. Tehseen Zia
[Dr. Tehseen Zia has Doctorate and more than 10 years of post-Doctorate research experience in Artificial Intelligence (AI). He is Tenured Associate Professor and leads AI research at Comsats University Islamabad, and co-principle investigator in National Center of Artificial Intelligence Pakistan. In the past, he has worked as research consultant on European Union funded AI project Dream4cars.]
Recent AI progress poses energy challenges. Balancing advancements with sustainability is crucial. Traditional computing faces limitations, while the brain's efficiency inspires Neuromorphic Computing (NC) for energy-efficient AI. Leading companies drive innovative NC technologies, reflecting the fast-growing demand for energy-saving AI.
As artificial intelligence (AI) progresses, its accomplishments bring energy-intensive challenges.
One study predicts that if data growth persists, cumulative energy usage from binary operations could surpass 10^27 Joules by 2040 – more than what the world can generate.
So let’s explore AI’s environmental impact, the constraints of conventional computing models, and how Neuromorphic Computing (NC) draws inspiration from the energy-efficient human brain, leading to sustainable AI advancements.
Artificial Intelligence: The Dilemma
In recent years, artificial intelligence (AI) has achieved remarkable landmarks, exemplified by the evolution of language models like ChatGPT and advancements in computer vision that empower autonomous technology and elevate medical imaging.Moreover, AI’s astonishing proficiency in reinforcement learning, as seen in its victories over human champions in games like Chess and Go, highlights its remarkable capabilities.
While these developments have enabled AI to transform industries, foster business innovation, uncover scientific breakthroughs and make a strong impression on society, they are not without consequences.
Alongside that alarming forecast for 2040, even today the storage of extensive data and training AI models using these datasets requires significant energy and computational resources, with research showing that:
- Training a model can use more energy than an average car’s lifetime consumption, according to MIT Technology Review.
- Cloud computing’s environmental impact now exceeds that of airlines.
- Data centers contribute 2-3% of global greenhouse emissions, with energy-intensive servers using 7% of Denmark’s electricity and 2.8% in the US.
Hence, it becomes vital to achieve a balance between advancements and energy requirements, considering their environmental effects, as AI continues to develop.
Von Neumann architecture: The Bottleneck
AI models operate within the framework of Von Neumann architecture, a computer design that essentially separates processing and memory, requiring constant communication between them.As AI models grow complex and datasets expand, this architecture faces significant hurdles.
Firstly, the processing and memory units shared a communication bus, slowing AI computations and hampering training speed.
Secondly, the processing unit of the architecture lacks parallel processing capabilities which impacts the training.
While GPUs alleviate the issue by allowing parallel processing, they introduce data transfer overhead.
The frequent data movement faces additional overhead due to memory hierarchy which impacts the performance.
Large datasets cause extended memory access times, and limited memory bandwidth, resulting in performance bottlenecks.
Complex AI models strain Von Neumann systems, limiting memory and processing capacities. These limitations have given rise to high energy demands and carbon emissions in AI systems.
Addressing these challenges is crucial for optimizing AI performance and minimizing environmental impact.
Biological Brain: The Inspiration
The human brain is more powerful than any AI machines when it comes to cognitive abilities.Despite its immense power, the brain is incredibly light and operates on just 10W of power, in contrast to the energy-hungry machines we use today.
According to an estimate, even this modest power budget allows the brain to achieve an astonishing 1 exaflop, equivalent to 1000 petaflops—a feat that the world’s fastest supercomputer with its 30 megawatts of power struggles to match at 200 petaflops.
The brain’s secret lies in its neurons, which integrate processing and memory, unlike the Von Neumann architecture.
The brain processes information in a massively parallel manner, with billions of neurons and trillions of synapses working simultaneously. Despite its remarkable intricacy, the brain remains compact and economical in its energy usage.
What is Neuromorphic Computing?
Neuromorphic computing (NC) is a branch of computing technology inspired by the structure and functioning of the human brain’s neural networks.It seeks to design and develop computer architectures and systems that mimic the parallel and distributed processing capabilities of the brain, enabling efficient and energy-effective processing of complex tasks.
This approach aims to overcome the limitations posed by the Von Neumann architecture for AI tasks especially by co-locating memory and processing at single location.
To comprehend NC, it is vital to understand how the brain works. Neurons, the building blocks of brain, communicate via electrical signals for information processing.
Upon receiving signals from interconnected neurons, they process and emit impulses.
These impulses travel along pathways formed by neurons, with synapses – gaps between neurons – facilitating the transmission.
Within the framework of NC, analog memristors are utilized to replicate the function of the synapses, achieving memory by adjusting resistance.
The rapid communication between neurons is typically achieved through the utilization of Spiking Neural Networks (SNNs).
These SNNs link spiking neurons using artificial synaptic devices, such as memristors, which employ analog circuits to mimic brain-like electrical signals.
These analog circuits offer significantly higher energy efficiency compared to the conventional Von Neumann architecture.
Neuromorphic Technologies
The rise of AI is boosting the demand for neuromorphic computing.The global neuromorphic computing market is expected to grow from USD 31.2 million in 2021 to around USD 8,275.9 million by 2030, with an impressive CAGR of 85.73%. In response, companies are advancing neuromorphic technologies, such as:
• IBM’s TrueNorth: Introduced in 2014, it’s a neuromorphic CMOS integrated circuit with 4096 cores, over a million neurons, and 268 million synapses. TrueNorth overcomes von Neumann bottlenecks, consuming only 70 milliwatts.
• Intel’s Loihi: Unveiled in 2017, Loihi is 1000 times more energy-efficient than typical neural network training. It features 131,072 simulated neurons and shows energy efficiency 30-1000 times greater than CPUs/GPUs.
• BrainChip’s Akida NSoC: Using spiking neural network architecture, it integrates 1.2 million neurons and 10 billion synapses. Akida supports real-time, low-power AI applications like video object detection and speech recognition.
These innovations signal the rapid evolution of neuromorphic computing to meet AI demands.
Challenges of Neuromorphic Computing
Realizing the potential of NC in AI demands addressing specific challenges.Firstly, the development of efficient algorithms compatible with neuromorphic hardware is crucial. This requires a deep understanding of hardware operations and tailored adaptations.
Secondly, the need to handle larger, intricate datasets is crucial. The present NC experiments involve relatively modest datasets, necessitating exploration of its performance with more substantial and complex problems.
As dataset size and complexity expand, NC’s computational demands increase. The challenge lies in designing NC systems capable of meeting these demands while delivering precise and effective solutions.
Despite encouraging outcomes from smaller-scale tests, NC’s performance with larger and more intricate datasets remains untested.
Further research and development are essential to optimize the technology for practical applications.
The Bottom Line
Neuromorphic Computing (NC) draws inspiration from the brain’s neural networks to revolutionize AI with energy efficiency.As AI advances bring environmental concerns, NC offers an alternative by mimicking the brain’s parallel processing.
Unlike the Von Neumann architecture, which hampers efficiency, NC co-locates memory and processing, overcoming bottlenecks.
Innovations like IBM’s TrueNorth, Intel’s Loihi, and BrainChip’s Akida NSoC showcase the potential of neuromorphic technologies.
Challenges persist, including algorithm adaptation and scalability to larger datasets. As NC evolves, it promises energy-effective AI solutions with sustainable growth potential."
https://www.techopedia.com/why-we-need-to-re-engineer-ai-to-work-like-the-brain-to-save-on-energy
Last edited:
equanimous
Norse clairvoyant shapeshifter goddess
supersonic001
Regular
Teksun Inc on LinkedIn: #teksun #technologies #cognitiveservices
Experience the future of intelligent solutions with #Teksun's cutting-edge Cognitive Services. Our advanced #technologies harness the power of artificial…
robsmark
Regular
I think one of the things that fucks me off the most about this SP is that many here have held for years, have performed significant research and have financially supported the company in its endeavours to this point in time where it can finally release Akida 2, and how have we being rewarded for that loyalty? I for one a significantly in the red now, and to think that some random investor can swoop in now and buy this stock and instantly be in a much better position that I, and many others like me is mentally exhausting. It’s alright the company saying that the SP will do what the SP will do, but to me personally it feels like they‘re spitting in my face.
I fully understand that my investment decisions are my responsibility, but that doesn’t make it any easier to swallow.
Last edited:
Learning
Learning to the Top 🕵♂️
Ai at the edge!
This is what Brainchip has been targeting the last few years. In this WSJ, clearly Ai is heading towards the 'edge'.
"Near-real-time inference and response times, for example, can become easier to achieve. Data transport and processing costs, meanwhile, can be reduced, particularly for high-bandwidth applications such as streaming video or real-time image or video analytics. And by processing more data at the edge and sending less to the cloud, edge AI can help ensure data privacy and security. It can also make it possible to run critical functions even when internet connections go down."
deloitte.wsj.com
Learning 🏖
This is what Brainchip has been targeting the last few years. In this WSJ, clearly Ai is heading towards the 'edge'.
"Near-real-time inference and response times, for example, can become easier to achieve. Data transport and processing costs, meanwhile, can be reduced, particularly for high-bandwidth applications such as streaming video or real-time image or video analytics. And by processing more data at the edge and sending less to the cloud, edge AI can help ensure data privacy and security. It can also make it possible to run critical functions even when internet connections go down."
AI Steps Onto the Edge - WSJ
With rapid response times, competitive costs, and a host of other potential benefits, edge devices are gaining ground as a location of choice for AI analytics
deloitte.wsj.com
Learning 🏖
overpup
Regular
I am with you robsmark - I am also a long term holder, feeling the pressure. I know some BRN folks who have had to sell large parcels, due to cost of living/high rents etc - poor buggers held on as long as they could, but just couldn't afford to any longer.
Now that would make me spew big time!
I wouldn't blame them for feeling that BRN let them down...
FJ-215
Regular
G'day Rise,Is that a typo
Who dares to 'love" forever?
I suppose it matters not as to love forever you must live forever
Also if I was to live forever I would definitely want those around who are my dearest and nearest to also live forever otherwise that would idea would totally suck without them.
And was going to post something that was brn related by your question sent me somewhere deep and now have totally lost what I was going to post.
Hmm yeah just recalled what I was going to post
And it's just an addition to a post earlier on ( more waffling)
Like a finely tuned clock of I send a mate some info which has not been discovered yet ( Akida brain hemorrhage) post damn price always drops.
A story now on abc about dogs painting and if I heard correctly they going to show robot dogs painting
You need to watch the movie (Highlander). Queen did the sound track (see: It's a kind of magic) An immortal dealing with the loss of the mortals he loved.
Hmm.....I think this is getting a bit weird.
So....
Back to BRN..
The Akida 1500 must be on the test bench by now. Am I wrong to think that it was cooked up for a long standing EAP customer? Not so fussed with Akida 2.0, It's years away by the time it is taped out and then tested. Then again, news of its launch may be positive for the SP.
Cartagena
Regular
Me too.It's been a tough journey for all no doubt and I share your frustrations Robsmark. I bought large parcels at 35 right up to 37 thinking we would never see 33 again and it's really hard to see the red and yes it's normal to feel pissed off and short changed, but the thing that gets me through is believing that it's not long to go for the Gen 2 launch and hopefully some new sizeable dollar producing contracts to be announced, we are all watching and expecting the promises Sean has made to be executed. I am also hoping BRN starts employing the best PR and media to provide max impact on the technology they have worked hard to commercialise so the world knows about it.. The PR aspect is a very critical part in attracting new quality investors hence SP will be far north of its current level.
Thanks to all the valuable contributors here who believe and have done the research that know Akida will prevail however the company will need to make good on their promises and the next announcement and it's delivery will be critical.
cosors
👀
Thanks!Ai at the edge!
This is what Brainchip has been targeting the last few years. In this WSJ, clearly Ai is heading towards the 'edge'.
"Near-real-time inference and response times, for example, can become easier to achieve. Data transport and processing costs, meanwhile, can be reduced, particularly for high-bandwidth applications such as streaming video or real-time image or video analytics. And by processing more data at the edge and sending less to the cloud, edge AI can help ensure data privacy and security. It can also make it possible to run critical functions even when internet connections go down."
AI Steps Onto the Edge - WSJ
With rapid response times, competitive costs, and a host of other potential benefits, edge devices are gaining ground as a location of choice for AI analytics
Learning 🏖
I see this as a supplement to the article I posted above, which focuses on the really big models. For me the two articles paint a coherent picture and do not contain any hype as far as I can see. Only the necessity and also the opportunities.
Many businesses need an edge strategy. Companies that wait until the time “seems” right could run the risk of waiting too long: By the time they get there, the real opportunity may have already passed them by.
Last edited:
Fullmoonfever
Top 20
Nice to see emotion3D hire staff with neuromorphic experience 
Francesco Marrone, Ph.D.
Deep Learning Engineer | Software Architect
emotion3DPolitecnico di Torino
Vienna, Vienna, Austria
336 followers 335 connections
About
Motivated and accomplished Deep Learning Computer Vision Engineer with a PhD in electronics engineering and 4 years of experience in the industry. Skilled in C/C++, Python, MATLAB, Tensorflow, VHDL, Verilog-A, Spice, I have a proven track record of success in developing and implementing AI-based computer vision algorithms for a variety of applications, including biomedical imaging, manufacturing quality control, and ADAS. Currently working as a Deep Learning Computer Vision Engineer at an innovative automotive startup, where I am part of a team responsible for the development of the next generation of night vision systems for safe autonomous driving. In addition to my work experience, I have also served as a teaching assistant, lecturing on circuits theory and supervising multiple master students during their master's degree thesis. I have also published numerous papers in the field of neuromorphic computing and emerging memory technologies.Experience
-
emotion3D
1 year 5 monthsSoftware Architect & Lead Software Engineer
Mar 2023 - Present6 months
Vienna, AustriaComputer Vision Deep Learning Engineer
Apr 2022 - Mar 20231 year
Vienna, Austria
Tothemoon24
Top 20
AI & Neuromorphic Computing with BrainChip
IoT For All -
August 17, 2023
In the fourth episode of the AI For All Podcast, Nandan Nayampally, CMO at BrainChip, unravels the complexities and opportunities surrounding edge AI and neuromorphic computing. As the worldwide leader in edge AI on-chip processing and learning, BrainChip offers a front-row seat to what’s driving AI’s next frontier – hardware.
Edge AI: Intelligence at the Source
The conversation begins with an exploration of edge AI, which involves processing data on local devices instead of in centralized data centers. Nandan delves into the benefits and trade-offs of this technology, emphasizing its potential in enhancing efficiency, reducing latency, and improving privacy and security.Neuromorphic Computing: Mimicking the Human Brain
One of the most fascinating segments of the episode revolves around neuromorphic computing. These are chips and systems designed to mimic the human brain’s structure and function. Nandan explains the potential of neuromorphic chips in AIapplications, offering a glimpse into how they could revolutionize the way AI processes and learns information.AI Hardware: Economics and Evolution
A robust discussion on AI hardware’s economics gives listeners an understanding of the investments, innovations, and challenges involved in building the physical foundations of AI systems. From silicon chips to graphics processing units, Nandan shares insights into how hardware is evolving to meet the increasing demands of AI applications.Top AI Applications and AI in Health
Nandan provides an overview of the current top AI applications like autonomous driving. A particular focus on AI in health uncovers the groundbreaking ways in which AI technologies are improving well-being.Future Opportunities in AI
The episode concludes with an inspiring look at future opportunities in AI. As technologies like edge AI and neuromorphic computing continue to mature, the possibilities for innovation are vast.Watch the Episode
This episode offers a comprehensive and engaging exploration of the technologies at the cutting edge of artificial intelligence. Nandan Nayampally’s expert insights and BrainChip’s pioneering work invite listeners to envision a future where AI is more efficient, adaptive, and integrated into our daily lives.Whether you are a technologist, business leader, or curious learner, this episode promises to deepen your understanding of AI’s underlying architecture and its implications for our world.
Join the AI For All Podcast to dive into this thrilling conversation and continue to explore the technological innovations that are shaping the future of artificial intelligence.
AI Steps Onto the Edge - WSJ
With rapid response times, competitive costs, and a host of other potential benefits, edge devices are gaining ground as a location of choice for AI analytics
deloitte.wsj.com
Similar threads
