Join today and have your say! It’s FREE!

Become a member today, It's free!

We will not release or resell your information to third parties without your permission.
Please Try Again
{{ error }}
By providing my email, I consent to receiving investment related electronic messages from Stockhouse.

or

Sign In

Please Try Again
{{ error }}
Password Hint : {{passwordHint}}
Forgot Password?

or

Please Try Again {{ error }}

Send my password

SUCCESS
An email was sent with password retrieval instructions. Please go to the link in the email message to retrieve your password.

Become a member today, It's free!

We will not release or resell your information to third parties without your permission.
Quote  |  Bullboard  |  News  |  Opinion  |  Profile  |  Peers  |  Filings  |  Financials  |  Options  |  Price History  |  Ratios  |  Ownership  |  Insiders  |  Valuation

California Nanotechnologies Corp CANOF


Primary Symbol: V.CNO

California Nanotechnologies Corp. is engaged in the development of nanocrystalline materials through grain size reduction. The Company’s core technologies include Spark Plasma Sintering (SPS) and Cryogenic Milling. SPS is an advanced sintering and bonding technique for all varieties of materials including metallic alloys, high-temp ceramics, high entropy alloys, and everything in between. It provides powder consolidation and material bonding toll services via its multiple SPS systems for everything from fundamental research and development to production. Cryogenic Milling is a powder processing technique used for particle size reduction (to nano scale), mechanical alloying and nano-grain refinement. It provides toll services for research and development along with production and has multiple milling systems on-site. Other services offered by the Company are spark plasma sintering and hot-pressing tooling fabrication and design, wire electrical discharge machining (EDM), and others.


TSXV:CNO - Post by User

Post by 1Investdilemmaon Nov 23, 2024 4:52pm
39 Views
Post# 36327595

AI may enhance CalNano’s capabilities

AI may enhance CalNano’s capabilities Taylor Sparks   Professor of Materials Science & Engineering and co-host of Materialism Podcast 3d •
Linkedin     ttps://www.linkedin.com/    11-20-24
 
 are there differences in large language model embeddings for materials? we investigate and do some careful comparisons. excellent collaborative work with the pros over at Trinity College Dublin
 
>>>>>>>>>>>  My footnote: Embeddings are numerical representations of real-world objects that machine learning (ML) and artificial intelligence (AI) systems use to understand complex knowledge domains like humans do. <<<<<

Luke Gilligan, PhDLuke Gilligan, • Postdoctoral Research Fellow at Trinity College Dublin 
Linkedin  11-20-24
 
It's great to share that our latest paper is officially out!
In this work, we examine the untapped potential of large language models (LLMs) and explore how much information about compounds and materials might already be "hidden" within their parameters.  More importantly, we discuss potential interesting strategies for unlocking and using this data effectively
This is a pretty novel work, and we're excited about the new questions and possibilities it opens up for the integration of LLMs into the domain of materials science.

Huge thanks to the collaborators from Trinity College Dublin and The University of Utah:
Matteo Cobelli, Stefano Sanvito, Hasan Sayeed & Taylor Sparks
 

The full paper can be found here:
https://lnkd.in/eFyNhq83
 
Abstract
Vector embeddings derived from large language models (LLMs) show promise in capturing latent information from the literature. Interestingly, these can be integrated into material embeddings, potentially useful for data-driven predictions of materials properties. We investigate the extent to which LLM-derived vectors capture the desired information and their potential to provide insights into material properties without additional training. Our findings indicate that, although LLMs can be used to generate representations reflecting certain property information, extracting the embeddings requires identifying the optimal contextual clues and appropriate comparators. Despite this restriction, it appears that LLMs still have the potential to be useful in generating meaningful materials-science representations.


Conclusion:
All in all, we can then conclude that LLMs are likely not to be a valuable means of gaining an estimate of relative material property ranking immediately, at least when they are taken without any training or optimization step. However, a common sense choice of contextualization term and query key may be useful in certain contexts. This work serves to highlight the potential strengths and drawbacks of LLMs for constructing valuable materials representations for data-driven discovery.
 
<< Previous
Bullboard Posts