braindersnn.bsky.social
Neuromorph at #ProjectPhasor | Ex: Loihi @Intel Labs; MLPerf, TPU, Chrome GPU, Android GPU; HT patch clamp | Runner
https://www.project-phasor.org
https://www.linkedin.com/in/brian-anderson-6739ba25
62 posts
385 followers
963 following
Regular Contributor
Active Commenter
comment in response to
post
Haha. I got tricked! Only after I zoomed into the image did I see the missing ‘n’
comment in response to
post
For more info:
Homepage: www.project-phasor.org
Discord: discord.com/invite/jh9VQ...
Invite AMD to join the party: docs.google.com/forms/d/e/1F...
Why Project Phasor: docs.google.com/document/d/1...
comment in response to
post
To be notified by email of future meetings, fill out the following form:
docs.google.com/forms/d/e/1F...
#projectphasor #ai #ml #neuromorphic #neuroai
comment in response to
post
We will discuss the proposed efforts and technical considerations, coordinate additional outreach and recruitment, and prepare for a public presentation to be hosted by Open Neuromorphic at the end of January.
comment in response to
post
EMEA and APAC friendly versions of each meeting will be held - 10am and 11pm California time respectively:
>>> Jan 8 - General Kickoff
>>> Jan 9 - Funding + VMs
>>> Jan 10 - Compiler
>>> Jan 14 - Datacenter Scale + Heterogeneous Compute
>>> Jan 15 - AMD Invitation
Meetings will not be recorded.
comment in response to
post
Register for January Project Phasor meetings here: docs.google.com/forms/d/e/1F...
comment in response to
post
#projectphasor #ai #ml #funding #compilers #virtualmachines #heterogeneouscomputing #datacenterscale #neuromorphic #neuroai
For more info:
Homepage: www.project-phasor.org
Discord: discord.com/invite/jh9VQ...
comment in response to
post
#projectphasor #ai #ml #funding #compilers #virtualmachines #heterogeneouscomputing #datacenterscale #neuromorphic #neuroai
comment in response to
post
How things shape out will depend on the community. We have a lot of meetings slated for January, to be capped off with an Open Neuromorphic hosted presentation. Register your interest here to prioritize the NeuroAI and neuromorphic issues best solved together!
docs.google.com/forms/d/e/1F...
comment in response to
post
By throwing everything at the wall at the same time, Project Phasor hopes to use the power of coincidence to trigger positive feedback that cascades into a stable attractor basin of neuromorphic awesomeness.
comment in response to
post
The “roots” of the banana plant will be the joint research fund, which will be used to produce future plants of the Gros Michael variety.
comment in response to
post
...removing artificial hardware constraints as much as possible (by encouraging a zoo of neuromorphic VMs), and encourage a zoo of higher level frameworks (by explicitly NOT trying to force a neuromorphic framework standard, which several have tried and failed to do since it is still to early).
comment in response to
post
Project Phasor will also eradicate Panama disease by focusing on production-quality software (compilers and heterogeneous integration), ...
comment in response to
post
The Panama disease (short term vision and diffuse efforts) incentivizes industry to produce Cavendish even though Gros Michael is what everyone actually wants to work on.
comment in response to
post
Notably, the fruit will be of the rare Gros Michael variety (large scale neuromorphic training) rather than the common Cavendish variety (neuromorphic inference at the edge)....
comment in response to
post
<Project Phasor> intends to be like the trunk of a banana plant, to fruit a bunch of bananas (i.e. the proposed 5 areas of focus) all at once and then wither away. Notably...
comment in response to
post
For more #projectphasor info:
Homepage: www.project-phasor.org
Discord: discord.com/invite/jh9VQ...
Invite AMD to join the party: docs.google.com/forms/d/e/1F...
Why Project Phasor: docs.google.com/document/d/1...
comment in response to
post
Here’s to making 2025 a big year for neuromorphics and NeuroAI!
#projectphasor #ai #ml #funding #compilers #virtualmachines #heterogenouscomputing #datacenterscale
comment in response to
post
Please register your interest to participate in each meeting/group. We will coordinate meet up times at the beginning of January so folks can brainstorm, prepare, and do additional outreach if needed.
forms.gle/LYxu7ru72KmL...
comment in response to
post
We will also hold an initial Project Phasor kick-off meeting in the first half of January. Exact date also TBD.
comment in response to
post
Small groups include:
1. Forming a joint research fund.
2. Neuromorphic compiler.
3. Neuromorphic VMs and arch search.
4. Heterogenous integration.
5. Datacenter-scale training.
comment in response to
post
Open Neuromorphic will host a large group meeting for Project Phasor in the later half of January, inviting the broader community to listen in and participate. Exact date TBD.
In anticipation of that, we are forming a few small groups to prepare to present at the Open Neuromorphic meeting.
comment in response to
post
Yeah, not a good idea to put a huge amount of resources into one idea when a field is still at the point where most ideas are wrong.
comment in response to
post
I agree that more funding for #NeuroAI is needed! #projectphasor proposes a bottom-up approach, which I like better though. Low-level software like compilers to enable creativity, exploration, and scale at higher levels. #projectphasor is also starting a fund. Everyone put your $$$ there instead!
comment in response to
post
#projectphasor #ml #ai #research #grants #doge
For more info:
Homepage: www.project-phasor.org
Discord: discord.com/invite/jh9VQ...
Invite AMD to join the neuromorphic party: ://docs.google.com/forms/d/e/1FAIpQLSfJRMWpV4hDAuRZzawVil9cbYxDZh-lwocrATosPrjOtc2F9g/viewform?usp=sf_link
comment in response to
post
5) With some estimating overall public budget cuts could reach $2T/y in some locales, the private sector will need to pick up the slack using the resulting tax savings. Infrastructure like joint funds to handle the transition will need to be there in advance to avoid a devastating funding gap.
comment in response to
post
3) A joint fund would make it easier for more funding sources to participate.
4) Recently, public and private grants appear to be lacking for algorithmic research in this space.
comment in response to
post
1) Amazing progress recently, with a lot of untapped potential for more energy-efficient AI.
2) A larger fund will attract the best researchers and a more diverse set of topics.
comment in response to
post
Join Project Phasor!
Discord: discord.com/invite/jh9VQ...
Homepage: www.project-phasor.org
Invite AMD to join the neuromorphic party: docs.google.com/forms/d/e/1F...
#projectphasor #backprop #robustai #continuallearning #mlir #ml #ai
comment in response to
post
Project Phasor aims to help prove this out by prioritizing the #NeuroAI and #neuromorphic issues best solved together.
#projectphasor
comment in response to
post
I’m willing to bet NeuroAI will lead us to the most robust neural networks. Ones that are most resilient to adversarial attack vectors and that are best able to handle out-of-distribution situations. Wdyt?