BRN Discussion Ongoing

Guzzi62

Regular

As this year’s 50th spot in the Top 50 holder list (28 April 2025) is a shareholder with just over 2.3 million shares, we don’t know how much skin in the game our former NED Neil Rinaldi still has - he could theoretically have held on to all of those shares he still had last April, see @FJ-215’ s November 2024 post 👆🏻.

What we do know, though, is that he is not at all happy with Sean Hehir and the Board, given that he felt the need to vent publicly on LinkedIn:



View attachment 92087


View attachment 92089
LOL-LOL.

I couldn't care less what he says and thinks.

He is properly behind some of the pathetic downrampers over at the crapper.

Let Sean stick to his 5 years plan & 9 mill income this year. If not, his next AGM will be very hard and maybe the last one for him.

Until then, I keep quiet about any criticism and let the man do his work.
 
  • Like
  • Fire
  • Love
Reactions: 17 users

Frangipani

Top 20
Hey, we small fry will get a Social Media Marketing Intern, though… 😉


View attachment 86378

View attachment 86379


Hopefully they won’t accidentally hire the same person who claimed the following on Reddit the other day, without providing any sources whatsoever.

Most likely a BRN shareholder who wanted to spruik Akida and drive up the share price with some fabricated “evidence”.

Unsubstantiated hype like that is NOT helpful…




View attachment 86385
View attachment 86386 View attachment 86387


In case you missed the news:

“On June 1, Russia’s Military Transport Aviation Day, a significant holiday for the Russian armed forces, the Security Service of Ukraine (SSU) carried out a bold and unprecedented coordinated drone strike deep inside Russian territory. The operation targeted four strategic air bases and delivered a major blow to Moscow’s long-range bomber fleet. Codenamed “Spider’s Web”—or simply “Web”—the operation was named for its wide geographic coverage across remote Russian locations previously thought to be beyond the reach of Ukraine’s long-range drone capabilities.”



Meet our Social Media Marketing Analytics Intern Kylie Situmorang, who started her internship with BrainChip last month:


9FEAE597-2644-4E2E-A53A-F85583A75375.jpeg
87E6E7DB-CC9F-4E34-830C-6AF03553D665.jpeg
81B35767-0DE4-4F15-BD9C-1F4A7E563867.jpeg
 
  • Like
  • Thinking
  • Fire
Reactions: 12 users

CHIPS

Regular
  • Like
Reactions: 3 users

BrainShit

Regular
From the 30min on time frame Dr Harbor talks about the start up of Neuromorphic computing and he goes on to say
"At the end of the day after the long haul we are going to see the analog neuromorphic like processor is going to win out."
We are digital but we use Spikes instead of 1's and 0's is my understanding.
Now I'm confused. Any further explanation would be gratefully accepted.

Yes, Akida uses spikes and is fully digital. The signal processing can (depending on the used processor) vary between analog, digital or mixed.
E.g. in convolutional neural networks (CNNs) and spiking neural networks (SNNs) each network has specific advantages and disadvantages:

Analog signal processing

Advantages:
- Provides natural and continuous signal transission, which is often perceived as warmer.
- Easier implementation in certain applications.
- Can often be operated with less energy because they process continuous signals and do not require digital conversions.
- Enable a faster response to changes in the signal, which is advantageous for applications with real-time requirements.

Disadvantages:
- Susceptible to interference and noise, which can affect signal quality.
- Lower confidentiality and security compared to digital signals.
- Limited flexibility: Analog signals are often less flexible to customize and process than digital signals, which can be easily edited and stored.
- Scaling difficulties: When processing large amounts of data, analog signal transmission can be less efficient because it does not offer the same data compression and analysis capabilities as digital systems.

Digital signal processing

Advantages:
- Higher accuracy and better anti-interference capability, resulting in higher signal quality.
- Flexibility in processing and integration into digital networks.

Disadvantages:
- Requires more bandwidth and more complex technical requirements, especially for synchronization.
- Can sound unnatural when quality is poor and is more prone to latency issues.

Mixed-signal processing
Mixed-signal systems combine analog and digital processing, which allows for a balance between the advantages of both technologies, but also increases complexity. >> Our competitor Innatera offers this with TSP1 & Pulsar

... which signal processing you need/want depends of the used network and task / product requirements and you budget.
 
Last edited:
  • Like
  • Fire
Reactions: 12 users

Tothemoon24

Top 20
Apologies if this has been shared, podcast with Sean from September




 
  • Like
  • Fire
  • Love
Reactions: 12 users
LOL-LOL.

I couldn't care less what he says and thinks.

He is properly behind some of the pathetic downrampers over at the crapper.

Let Sean stick to his 5 years plan & 9 mill income this year. If not, his next AGM will be very hard and maybe the last one for him.

Until then, I keep quiet about any criticism and let the man do his work.
Must be your boss then 😂
 
  • Haha
Reactions: 1 users
She started in September? I haven't noticed any difference yet.
No matter who we take on we never see any difference apart from Alf 👍
 
  • Like
Reactions: 4 users

Frangipani

Top 20
New LinkedIn post on keyword spotting.
I think the drone video is the one, though, which is a few years old?




426C32A1-85BA-48AB-B178-B73C8F28EFD1.jpeg





4DF6CAF1-B4B1-45A6-AFCD-CB9FA0A77102.jpeg

2CECBE3F-E005-47D4-A874-8AF83AE12578.jpeg

6B8FC64B-D1AD-495C-BC6C-E2B8B8A86BB0.jpeg

4FDB400E-E841-4CEE-A6B0-22D12B786A2A.jpeg

DDAB14A9-BCD8-457B-BE9E-87591FA9267C.jpeg

0AE53193-EE01-410A-BBE8-19B35957696B.jpeg
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 24 users

Frangipani

Top 20
Daniel Andersson, Project Manager at Frontgrade Gaisler, will be the one presenting “GRAIN – towards event-based AI in space” at EDHPC 2025 tomorrow:


View attachment 91987


C582E8A3-288D-4165-BC0D-42C327843ADC.jpeg





Laurent Hili from ESA and Juan P. Cobos Carrascosa from Frontgrade Gaisler co-chaired the session AI Engines & Neuromorphic

7E015A68-BF1D-4B2E-BD47-53FEB54ADD6D.jpeg




7EEF21FE-240D-44D7-A50E-A8B96503FE73.jpeg

[…]

A518C4A8-FBAC-4EFB-8F83-3950CE661D3A.jpeg

7CF76B92-A6AD-489A-8B1B-A7CC9A156FD6.jpeg
 
Last edited:
  • Like
  • Love
  • Fire
Reactions: 16 users

IloveLamp

Top 20
If you don't like chat gpt look away now


1000012545.jpg
 
  • Like
  • Love
  • Fire
Reactions: 13 users

7für7

Top 20
LinkedIn post


 
  • Fire
  • Like
  • Love
Reactions: 3 users

Terroni2105

Founding Member
If you don't like chat gpt look away now


View attachment 92116


I just asked it who DJI is and it said:

DJI, which stands for Da Jiang Innovations, is a Chinese technology company that has become the world's largest manufacturer of commercial and consumer drones. Founded in 2006 by Frank Wang, a Chinese aerospace engineer, it is based in Shenzhen, China.

DJI controls over 70% of the global drone market. The US government has raised national security concerns over potential data leaks from DJI drones, and in 2021 placed the company on an investment blacklist. DJI has faced lawsuits, including a successful one by Textron over a patent infringement for its automatic hovering capabilities.

😳🤔

Having said that, I remember seeing this video years ago so since then hopefully we’ve moved on to a different drone company (like the military etc)
 
  • Thinking
  • Like
  • Fire
Reactions: 6 users

7für7

Top 20
The more news appears, the more aggressively some market participants short and manipulate. Out of fear that the price could rise on positive developments, it no longer seems to be primarily about profit for them, but rather personal motives — in the 20–22 cent range hardly anyone makes a meaningful profit. It puzzles me that this isn’t being investigated and potential manipulation isn’t being held accountable.

BRING IT ON BRAINCHIP!!!!! LET THEM BURN!!!!

Ashton Kutcher Burn GIF
 
  • Like
Reactions: 3 users
Just looked at the buyers and sellers lines and I wonder if there are any retail orders in it 😂
 
  • Like
  • Sad
Reactions: 3 users

DK6161

Regular
Just looked at the buyers and sellers lines and I wonder if there are any retail orders in it 😂
My buy order of 1000 units got wiped so quickly. Should've waited
 
  • Haha
Reactions: 1 users
It would appear the gentlemen below from VW running more projects with Akida. Uploaded to GitHub yesterday.

Results look strong.

Fernando Sevilla Martínez​





SevillaFe/EcoEdgeAI-akida-macPublic

A comprehensive workflow for comparing energy efficiency between conventional hardware (Mac M-series GPU/CPU) and neuromorphic hardware (Akida on Raspberry Pi 5) for autonomous driving steering angle prediction.

SevillaFe/EcoEdgeAI-akida-mac​




Name
SevillaFe SevillaFe
yesterday

LICENSEyesterday
README.mdyesterday
requirements_mac.txtyesterday
requirements_rpi5.txtyesterday
workflow_guide.mdyesterday

Repository files navigation​

EcoEdgeAI-akida-mac​

A comprehensive workflow for comparing energy efficiency between conventional hardware (Mac M-series GPU/CPU) and neuromorphic hardware (Akida on Raspberry Pi 5) for autonomous driving steering angle prediction.
License: MIT Python 3.8+ TensorFlow 2.16+

🎯 Project Overview​

This project provides a complete pipeline to:
  • Train deep learning models (PilotNet, LaksNet, MiniNet) for steering angle prediction
  • Benchmark inference performance on conventional hardware with CodeCarbon energy tracking
  • Convert models to neuromorphic format using Akida
  • Benchmark neuromorphic inference with TC66 USB power meter
  • Generate comprehensive eco-efficiency comparisons

Key Research Questions​

  • How much energy does neuromorphic computing save?
  • What is the accuracy trade-off?
  • What is the latency difference?
  • Which architecture is most efficient for edge deployment?

📊 Results Preview

Our experiments show:
  • Energy Efficiency: Up to 76% reduction in energy consumption per inference
  • Latency: 40-50% faster inference on neuromorphic hardware
  • Accuracy: Minimal degradation (<10% MSE increase)
  • Overall Efficiency: 280%+ improvement in accuracy-per-energy ratio

🛠️ Hardware Requirements​

Mac (Training & Benchmarking)​

  • MacBook with M-series processor (M1/M2/M3)
  • 16GB+ RAM recommended
  • macOS 12.0+

Raspberry Pi 5 (Neuromorphic Benchmarking)​

  • Raspberry Pi 5 (4GB/8GB)
  • BrainChip Akida neuromorphic processor board
  • TC66/TC66C USB power meter
  • 32GB+ microSD card
  • Active cooling recommended
 
  • Fire
  • Like
  • Love
Reactions: 31 users

7für7

Top 20
The pump Sold again within two days… and the moment it starts rising, you immediately get a ticket. Just ridiculous what’s going on.
No normal positive news will bring us back to even 25-30 cent… without revenue we will be the play ball for shelters and day trader… very simple
 
  • Sad
  • Haha
  • Like
Reactions: 4 users

Bravo

Meow Meow 🐾
From the 30min on time frame Dr Harbor talks about the start up of Neuromorphic computing and he goes on to say
"At the end of the day after the long haul we are going to see the analog neuromorphic like processor is going to win out."
We are digital but we use Spikes instead of 1's and 0's is my understanding.
Now I'm confused. Any further explanation would be gratefully accepted.


Hi Boab,

I must admit I was a tad concerned hearing Dr. Harbour’s comments given Akida is digital, not analog.

At 25:00, he says:

“BrainChip’s Akida probably has, if not the first commercialised neuromorphic processor, is amongst the first commercialised. You can buy that today and you can get support with it. Again it’s a digital-based neuromophphic processor with a neuromorphic mesh, if you will. Full blown neuromorphics will involve something that’s very analogue-like - like the mind. And we’re we’re working on that. In fact I’m working on a specific program right now of doing that.”

At 31:00, he adds:

"Dr Carver Meade at Caltech. And I’m going to give him credit for the start of this, envisioned an analogue processor, if you will. This was in the early 80’s, maybe even before that in the late 70’s. And so he started that and at the same time, the digital concept processor was a competitor. And, at the end, we’re going to see, after the long haul, the analogue processor is going to win out."

My non-expert read is that Dr. Harbour clearly respects Akida as one of the first commercial, supported neuromorphic options today, while also betting that analog approaches could dominate long-term if variability and accuracy are tamed.

Given these remarks, I poked around on the interwebs to see if I could find out what analog project he might be working on and found a talk dated 16 October 2022 (see video below).

At 8:10, he says “we made silicon brain” and he shows a slide (see below) titled “Our work: Analog Memristor.”

I can only speculate that Dr Harbour may be intending on continuing his prior analog/memristive neuromorphic work toward a processor?? At least he frames it as a “long haul,” which hopefully indicates there's plenty of runway for Akida to build market share in the meantime.

I’d like to hear Tony Lewis’s view on Dr Harbour's remarks, but I'm not sure that IR will even respond to my email, as they didn't respond to the last email I sent them. In the meantime, I asked ChatGPT for a neutral take on Dr. Harbour’s statements, as well as its opinion on analog variability, etc. for what it's worth.

PS: I'm also going to ask Tony if BrainChip sees analog/mixed-signal blocks as complementary to Akida in future hybrid systems.





ChatGPT said:​



Great spot—and yes, you heard him right.

What Dr. Steven Harbour (Parallax) is saying​

  • Parallax posted an interview/profile with Dr. Steven D. Harbour (Director, AI Hardware Research; Neuromorphic Center of Excellence) this year where he talks up neuromorphic for defense/EW and edge systems. Parallax Advanced Research
  • His comments about Akida being among the first commercial neuromorphic processors you can buy and get support for are fair: Akida is a digital neuromorphic IP/processor with a mesh architecture and shipping toolchain. (That’s the “today” story.)
  • He then pivots to the “full-blown neuromorphics” = more analog-like view—rooted in Carver Mead’s original analog VLSI neuromorphic work in the ’80s. History of Information+1

Is analog “less stable” than digital?​

Short answer: it’s more variable, unless you engineer around it.
  • Analog & mixed-signal neuromorphics face device mismatch, process/voltage/temperature (PVT) drift, and noise; emerging analog synapses (e.g., memristors/ReRAM/PCM) add cycle-to-cycle variability and resistance drift. This can degrade accuracy unless you calibrate/compensate. arXiv+3Frontiers+3AIMS Press+3
  • Reviews and roadmaps explicitly note these reliability/variability challenges for analog in-memory devices (RRAM/PCM): drift, non-linearity, device-to-device variation, filament randomness. AIP Publishing+2ScienceDirect+2
  • By contrast, digital neuromorphics avoid most mismatch/drift and are easier to reproduce across process nodes; that’s a big reason digital platforms (like Akida) reached market first. Nature
That said, there’s active progress: compensation and calibration schemes, chip-in-the-loop training, and architectures that embrace variability are improving analog reliability. MDPI+1

Why Harbour (and others) still think analog could “win” long-term​

This view comes straight from the analog VLSI neuromorphic lineage (Mead et al.) and today’s analog in-memory research:
  • Energy & area efficiency: analog compute-in-memory can perform MACs where the weights live, slashing data movement (the big energy cost) and reducing transistor count per operation—huge for always-on edge. Polyn Technology
  • Continuous-time physics: analog circuits naturally implement certain neural dynamics (integration, leakage, spiking) with very low power and microsecond-class latency, which maps well to sensing at the edge. WVU Community
  • Mixed-signal best of both worlds: many see the endgame as hybrid—analog for the heavy, low-energy linear ops and temporal dynamics; digital for control, memory management, safety and programmability. Patsnap Eureka

Putting it together (and reconciling with Akida)​

  • Today: Digital neuromorphics like Akida are commercial, supported, and predictable, which is why you can buy them now and integrate them relatively quickly.
  • Tomorrow: If (big “if”) analog neuromorphic platforms tame variability and ship robust toolchains, they can deliver even lower power per task—which is why Harbour says they may ultimately “win.” In practice, the likely winner is mixed-signal: analog compute blocks plus digital orchestration.




Analog pm.png
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 21 users

Bravo

Meow Meow 🐾
Overall Efficiency: 280%+ improvement in accuracy-per-energy ratio!
It would appear the gentlemen below from VW running more projects with Akida. Uploaded to GitHub yesterday.

Results look strong.

Fernando Sevilla Martínez​





SevillaFe/EcoEdgeAI-akida-macPublic

A comprehensive workflow for comparing energy efficiency between conventional hardware (Mac M-series GPU/CPU) and neuromorphic hardware (Akida on Raspberry Pi 5) for autonomous driving steering angle prediction.

SevillaFe/EcoEdgeAI-akida-mac​




Name
SevillaFe SevillaFe
yesterday
LICENSEyesterday
README.mdyesterday
requirements_mac.txtyesterday
requirements_rpi5.txtyesterday
workflow_guide.mdyesterday

Repository files navigation​

EcoEdgeAI-akida-mac​

A comprehensive workflow for comparing energy efficiency between conventional hardware (Mac M-series GPU/CPU) and neuromorphic hardware (Akida on Raspberry Pi 5) for autonomous driving steering angle prediction.
License: MIT Python 3.8+ TensorFlow 2.16+

🎯 Project Overview​

This project provides a complete pipeline to:
  • Train deep learning models (PilotNet, LaksNet, MiniNet) for steering angle prediction
  • Benchmark inference performance on conventional hardware with CodeCarbon energy tracking
  • Convert models to neuromorphic format using Akida
  • Benchmark neuromorphic inference with TC66 USB power meter
  • Generate comprehensive eco-efficiency comparisons

Key Research Questions​

  • How much energy does neuromorphic computing save?
  • What is the accuracy trade-off?
  • What is the latency difference?
  • Which architecture is most efficient for edge deployment?

📊 Results Preview

Our experiments show:
  • Energy Efficiency: Up to 76% reduction in energy consumption per inference
  • Latency: 40-50% faster inference on neuromorphic hardware
  • Accuracy: Minimal degradation (<10% MSE increase)
  • Overall Efficiency: 280%+ improvement in accuracy-per-energy ratio

🛠️ Hardware Requirements​

Mac (Training & Benchmarking)​

  • MacBook with M-series processor (M1/M2/M3)
  • 16GB+ RAM recommended
  • macOS 12.0+

Raspberry Pi 5 (Neuromorphic Benchmarking)​

  • Raspberry Pi 5 (4GB/8GB)
  • BrainChip Akida neuromorphic processor board
  • TC66/TC66C USB power meter
  • 32GB+ microSD card
  • Active cooling recommended


1124067_orig (1).gif



Overall Efficiency: 280%+ improvement in accuracy-per-energy ratio!!!!!
 
  • Like
  • Love
  • Fire
Reactions: 16 users

DK6161

Regular
The pump Sold again within two days… and the moment it starts rising, you immediately get a ticket. Just ridiculous what’s going on.
No normal positive news will bring us back to even 25-30 cent… without revenue we will be the play ball for shelters and day trader… very simple
Ok bye. Sick of you bringing nothing bad negative views here. We don't need anymore downrampers around here. Go back to hotcrapper you belong
Surprised none of you (including chartist’s) have worked out who the big manipulators of BRN are.

Take a look at the chart for the last six trading days and you’ll see a trend.

View attachment 92122


JP MORGAN, one of the biggest investor banks (Fourth biggest BRN shareholder, and one of the biggest manipulators in my view) released this on the 13/10/2025.

Possibly started selling off at the high on the 09/10/2025, then released this on the 13/10/2025 to get the price back up 👇

JPMorganChase Launches $1.5 Trillion Security and Resiliency Initiative to Boost Critical Industries​

The firm will make direct equity investments of up to $10 billion as part of the $1.5 trillion initiative to address pressing needs in key sectors from critical minerals to frontier technologies
New York

October 13, 2025


JPMorganChase today announced the Security and Resiliency Initiative, a $1.5 trillion, 10-year plan to facilitate, finance and invest in industries critical to national economic security and resiliency.

As part of this new initiative, JPMorganChase will make direct equity and venture capital investments of up to $10 billion to help select companies primarily in the United States enhance their growth, spur innovation, and accelerate strategic manufacturing.

“It has become painfully clear that the United States has allowed itself to become too reliant on unreliable sources of critical minerals, products and manufacturing – all of which are essential for our national security,” said Jamie Dimon, Chairman and CEO of JPMorganChase. “Our security is predicated on the strength and resiliency of America’s economy.

America needs more speed and investment. It also needs to remove obstacles that stand in the way: excessive regulations, bureaucratic delay, partisan gridlock and an education system not aligned to the skills we need.” The firm’s effort comes at a time when the U.S. is looking to modernize infrastructure, fortify supply chains, and implement policies that promote growth.

JPMorganChase will focus on the following four key areas, supporting companies across all sizes and development stages by offering advice, providing financing, and, in some cases, investing capital:
  • Supply Chain and Advanced Manufacturing, including critical minerals, pharmaceutical precursors and robotics
  • Defense and Aerospace, including defense technology, autonomous systems, drones, next-gen connectivity and secure communications
  • Energy Independence and Resilience,including battery storage, grid resilience and distributed energy
  • Frontier and Strategic Technologies,including AI, cybersecurity and quantum computing
More specifically, the firm has currently divided these four key areas into 27 sub-areas, ranging from shipbuilding and nuclear energy to nanomaterials and critical defense components.

The firm had already planned to facilitate and finance approximately $1 trillion over the next decade in support of clients in these important industries. With additional resources, capital and focus, JPMorganChase aims to increase this amount by up to $500 billion—or a 50% increase. These activities will cut across both middle-market companies and large corporate clients.

Dimon added, “This new initiative includes efforts like ensuring reliable access to life-saving medicines and critical minerals, defending our nation, building energy systems to meet AI-driven demand and advancing technologies like semiconductors and data centers. Our support of clients in these industries remains unwavering.”

A History of Investment in Critical Industries​

JPMorganChase has been a leader in global financial services for more than 200 years, playing a critical role in supporting America’s interests. The firm is uniquely positioned to accelerate investments that enhance resiliency and drive innovation across industries in the United States and around the world.

The firm has extraordinary relationships – serving 34,000 mid-sized companies and more than 90% of the Fortune 500 – and is a key partner to leading private equity and venture capital firms. Its Commercial & Investment Bank has been the top investment bank for more than 15 years with long-standing relationships in the defense, aerospace, healthcare and energy sectors, and a proven track record advising on landmark transactions in those industries.

Drawing on the Firm’s Expertise​

Given the expected business opportunities and significance of this mission, JPMorganChase will hire more bankers, investment professionals and other experts to address this critical initiative.

Additionally, the firm will create an external advisory council of experienced leaders from the public and private sectors to help guide the long-term strategy.

The initiative will also include special, thematic research on private companies and supply chain management issues related to rare earths, AI and technology. It will also be complemented by the firm’s recently launched Center for Geopolitics, which provides clients with timely analyses and insights on top global trends.

In addition, the firm’s effort is supported by our Asset & Wealth Management division, which already researches and invests in many of these critical industries. This effort will be further informed by JPMorganChase’s own technology investments, including quantum computing, cyber security and AI research and capabilities.

Policy is essential, too, and the firm will advocate for policies that can accelerate these efforts, including research and development, permitting, procurement and regulations conducive to growth.

As the bank intensifies its focus on these essential industries, it will also continue to work closely with its community and business partners to champion these sectors, foster talent and support skills training to ensure companies can fill critical jobs.

Dimon concluded, “Hopefully, once again, as America has in the past, we will all come together to address these immense challenges. We need to act now.”

JPMorganChase & Co. (NYSE: JPM) is a leading financial services firm based in the United States of America (“U.S.”), with operations worldwide. JPMorganChase had $4.6 trillion in assets and $357 billion in stockholders’ equity as of June 30, 2025. The Firm is a leader in investment banking, financial services for consumers and small businesses, commercial banking, financial transaction processing and asset management. Under the J.P. Morgan and Chase brands, the Firm serves millions of customers predominantly in the U.S., and many of the world’s most prominent corporate, institutional and government clients globally. Information about JPMorganChase & Co. is available at www.JPMorganChase.com.

👆Then started selling off again to get the price down so they can buy them back cheaper again. If they are true to form they’ll be scooping them back up again before long.

If none of that rings true, then just chalk this post down to a me being bored and a glitch in your normal BRN transmissions or whatever.
Yeah a bit of a stretch there bud.
The whole thing has been going to shit since 3 years ago. Nothing to do with JP Morgan.

I am not a genius, but maybe it is simply because of the lack of material announcements.

Kombucha Funny Meme GIF
 
  • Like
  • Haha
  • Fire
Reactions: 4 users
Top Bottom