Login

Recent searches

No recent searches

Search options

Only available when logged in.
social.coop is one of the many independent Mastodon servers you can use to participate in the fediverse.
A Fediverse instance for people interested in cooperative and collective projects. If you are interested in joining our community, please apply at https://join.social.coop/registration-form.html.

Administered by:

Server stats:

499
active users

social.coop: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.4

#tensor

0 posts0 participants0 posts today
JMLR<p>'A Random Matrix Approach to Low-Multilinear-Rank Tensor Approximation', by Hugo Lebeau, Florent Chatelain, Romain Couillet.</p><p><a href="http://jmlr.org/papers/v26/24-0193.html" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v26/24-0193.ht</span><span class="invisible">ml</span></a> <br> <br><a href="https://sigmoid.social/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> <a href="https://sigmoid.social/tags/multilinear" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>multilinear</span></a> <a href="https://sigmoid.social/tags/svd" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>svd</span></a></p>
JMLR<p>'Transfer learning for tensor Gaussian graphical models', by Mingyang Ren, Yaoming Zhen, Junhui Wang.</p><p><a href="http://jmlr.org/papers/v25/22-1313.html" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/22-1313.ht</span><span class="invisible">ml</span></a> <br> <br><a href="https://sigmoid.social/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> <a href="https://sigmoid.social/tags/gaussian" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>gaussian</span></a> <a href="https://sigmoid.social/tags/models" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>models</span></a></p>
JMLR<p>'Guaranteed Nonconvex Factorization Approach for Tensor Train Recovery', by Zhen Qin, Michael B. Wakin, Zhihui Zhu.</p><p><a href="http://jmlr.org/papers/v25/24-0029.html" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/24-0029.ht</span><span class="invisible">ml</span></a> <br> <br><a href="https://sigmoid.social/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> <a href="https://sigmoid.social/tags/tensors" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensors</span></a> <a href="https://sigmoid.social/tags/factorization" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>factorization</span></a></p>
alpharee<p>Hey, I'm stuck with this PyTorch problem and no one has answered on Stack Overflow yet. Need help creating a new tensor by using values from a 3D tensor as indices for a 1D tensor, efficiently and preferably without loops. Any PyTorch experts around?</p><p><a href="https://stackoverflow.com/q/79389115/21239182" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">stackoverflow.com/q/79389115/2</span><span class="invisible">1239182</span></a></p><p>Boosts appreciated - thanks! 🙏 </p><p><a href="https://mastodon.social/tags/pytorch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>pytorch</span></a> <a href="https://mastodon.social/tags/StackOverflow" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>StackOverflow</span></a> <a href="https://mastodon.social/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> <a href="https://mastodon.social/tags/torch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>torch</span></a> <a href="https://mastodon.social/tags/programming" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>programming</span></a> <a href="https://mastodon.social/tags/problem" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>problem</span></a> <a href="https://mastodon.social/tags/question" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>question</span></a> <a href="https://mastodon.social/tags/answer" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>answer</span></a> <a href="https://mastodon.social/tags/help" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>help</span></a></p>
EnigmaRotor<p><span class="h-card" translate="no"><a href="https://bsd.network/@dexter" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>dexter</span></a></span> <a href="https://mastodon.bsd.cafe/tags/Tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Tensor</span></a></p>
eicker.news tech news<p>»Has <a href="https://eicker.news/tags/Google" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Google</span></a>'s <a href="https://eicker.news/tags/Tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Tensor</span></a> project failed? Would future <a href="https://eicker.news/tags/Pixels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Pixels</span></a> be better of returning to <a href="https://eicker.news/tags/Snapdragon" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Snapdragon</span></a>?« <a href="https://www.androidauthority.com/has-google-tensor-failed-3499240/?eicker.news" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">androidauthority.com/has-googl</span><span class="invisible">e-tensor-failed-3499240/?eicker.news</span></a> <a href="https://eicker.news/tags/tech" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tech</span></a> <a href="https://eicker.news/tags/media" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>media</span></a></p>
JMLR<p>'A tensor factorization model of multilayer network interdependence', by Izabel Aguiar, Dane Taylor, Johan Ugander.</p><p><a href="http://jmlr.org/papers/v25/23-0205.html" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/23-0205.ht</span><span class="invisible">ml</span></a> <br> <br><a href="https://sigmoid.social/tags/tensors" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensors</span></a> <a href="https://sigmoid.social/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> <a href="https://sigmoid.social/tags/multilayer" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>multilayer</span></a></p>
CEOTECH.IT<p>Pixel Watch 5 potrebbe arrivare con chip Tensor dedicato<br><a href="https://mastodon.social/tags/Chip" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Chip</span></a> <a href="https://mastodon.social/tags/GadgetTech" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GadgetTech</span></a> <a href="https://mastodon.social/tags/GoogleWatch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GoogleWatch</span></a> <a href="https://mastodon.social/tags/Indossabili" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Indossabili</span></a> <a href="https://mastodon.social/tags/Leak" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Leak</span></a> <a href="https://mastodon.social/tags/Notizie" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Notizie</span></a> <a href="https://mastodon.social/tags/Novit%C3%A0" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Novità</span></a> <a href="https://mastodon.social/tags/Orologio" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Orologio</span></a> <a href="https://mastodon.social/tags/PixelWatch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PixelWatch</span></a> <a href="https://mastodon.social/tags/PixelWatch5" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PixelWatch5</span></a> <a href="https://mastodon.social/tags/Rumors" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Rumors</span></a> <a href="https://mastodon.social/tags/SmartDevice" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SmartDevice</span></a> <a href="https://mastodon.social/tags/Smartwatch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Smartwatch</span></a> <a href="https://mastodon.social/tags/TechNews" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TechNews</span></a> <a href="https://mastodon.social/tags/Tecnologia" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Tecnologia</span></a> <a href="https://mastodon.social/tags/Tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Tensor</span></a> <a href="https://mastodon.social/tags/WearOS" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>WearOS</span></a> <a href="https://mastodon.social/tags/Wearables" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Wearables</span></a> </p><p><a href="https://www.ceotech.it/pixel-watch-5-potrebbe-arrivare-con-chip-tensor-dedicato/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">ceotech.it/pixel-watch-5-potre</span><span class="invisible">bbe-arrivare-con-chip-tensor-dedicato/</span></a></p>
JMLR<p>'From continuous-time formulations to discretization schemes: tensor trains and robust regression for BSDEs and parabolic PDEs', by Lorenz Richter, Leon Sallandt, Nikolas Nüsken.</p><p><a href="http://jmlr.org/papers/v25/23-0982.html" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/23-0982.ht</span><span class="invisible">ml</span></a> <br> <br><a href="https://sigmoid.social/tags/discretization" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>discretization</span></a> <a href="https://sigmoid.social/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> <a href="https://sigmoid.social/tags/numerically" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>numerically</span></a></p>
JMLR<p>'Tensor-train methods for sequential state and parameter learning in state-space models', by Yiran Zhao, Tiangang Cui.</p><p><a href="http://jmlr.org/papers/v25/23-0743.html" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/23-0743.ht</span><span class="invisible">ml</span></a> <br> <br><a href="https://sigmoid.social/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> <a href="https://sigmoid.social/tags/sequentially" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>sequentially</span></a> <a href="https://sigmoid.social/tags/sequential" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>sequential</span></a></p>
IT News<p>Pixel 9 family: The “just hardware” review (no AI) - Enlarge / For this "neutral," hardware-focused review of the Pixel 9 ph... - <a href="https://arstechnica.com/?p=2044191" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arstechnica.com/?p=2044191</span><span class="invisible"></span></a> <a href="https://schleuss.online/tags/googlepixle" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>googlepixle</span></a> <a href="https://schleuss.online/tags/pixel9proxl" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>pixel9proxl</span></a> <a href="https://schleuss.online/tags/pixel9pro" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>pixel9pro</span></a> <a href="https://schleuss.online/tags/features" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>features</span></a> <a href="https://schleuss.online/tags/reviews" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>reviews</span></a> <a href="https://schleuss.online/tags/google" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>google</span></a> <a href="https://schleuss.online/tags/pixel9" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>pixel9</span></a> <a href="https://schleuss.online/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> <a href="https://schleuss.online/tags/tech" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tech</span></a></p>
Sophie Bremer<p>In case, someone missed it. Andrej Karpathy gives here probably the best technical introduction to GPT-based AI-models.</p><p><a href="https://www.youtube.com/watch?v=kCc8FmEb1nY" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">youtube.com/watch?v=kCc8FmEb1n</span><span class="invisible">Y</span></a></p><p><a href="https://mastodon.social/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a> <a href="https://mastodon.social/tags/chatgpt" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>chatgpt</span></a> <a href="https://mastodon.social/tags/gpt" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>gpt</span></a> <a href="https://mastodon.social/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llm</span></a> <a href="https://mastodon.social/tags/pytorch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>pytorch</span></a> <a href="https://mastodon.social/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a></p>
Sos Sosowski<p>Chipmakers puting AI cores in your CPU and not letting you use them for absolutely anything is the biggest waste of silicon in the history of modern computing.</p><p>Those tensor cores are godsend for things like large-scale CAD simulations but the only SDKs/samples provided are hardwired to run pretrained models. </p><p>There's no way to access the matrix/tensor capabilities directly. And that goes for both AMD and Intel.</p><p><a href="https://mastodon.gamedev.place/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a> <a href="https://mastodon.gamedev.place/tags/NPU" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NPU</span></a> <a href="https://mastodon.gamedev.place/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> <a href="https://mastodon.gamedev.place/tags/programming" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>programming</span></a> <a href="https://mastodon.gamedev.place/tags/hardware" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>hardware</span></a> <a href="https://mastodon.gamedev.place/tags/cpu" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>cpu</span></a></p>
JMLR<p>'Grokking phase transitions in learning local rules with gradient descent', by Bojan Žunkovič, Enej Ilievski.</p><p><a href="http://jmlr.org/papers/v25/22-1228.html" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/22-1228.ht</span><span class="invisible">ml</span></a> <br> <br><a href="https://sigmoid.social/tags/grokking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>grokking</span></a> <a href="https://sigmoid.social/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> <a href="https://sigmoid.social/tags/models" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>models</span></a></p>
JMLR<p>'Sharp analysis of power iteration for tensor PCA', by Yuchen Wu, Kangjie Zhou.</p><p><a href="http://jmlr.org/papers/v25/24-0006.html" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/24-0006.ht</span><span class="invisible">ml</span></a> <br> <br><a href="https://sigmoid.social/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> <a href="https://sigmoid.social/tags/pca" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>pca</span></a> <a href="https://sigmoid.social/tags/iterations" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>iterations</span></a></p>
JMLR<p>'More Efficient Estimation of Multivariate Additive Models Based on Tensor Decomposition and Penalization', by Xu Liu, Heng Lian, Jian Huang.</p><p><a href="http://jmlr.org/papers/v25/22-0578.html" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/22-0578.ht</span><span class="invisible">ml</span></a> <br> <br><a href="https://sigmoid.social/tags/multivariate" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>multivariate</span></a> <a href="https://sigmoid.social/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> <a href="https://sigmoid.social/tags/nonparametric" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nonparametric</span></a></p>
katch wreck<p>... that's a good stopping point for this short autobiographical story :) one of the algorithms i "reinvented" during this period of advancement i had was <a href="https://mastodon.social/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> (or multilinear) least-squares. i searched the literature as best i could, but i was not able to find all of this material presented in any article or textbook. so i decided to write it up myself, and try to publish it. the journal editor told me it was correct, but not novel. if you use tensors, take a look:</p><p><a href="https://www.researchgate.net/publication/280722977_Multilinear_Least_Squares" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">researchgate.net/publication/2</span><span class="invisible">80722977_Multilinear_Least_Squares</span></a></p>
Gazdag Péter Medde<p><a href="https://galeriasavaria.hu/termekek/reszletek/kezmuves/5713870/MeddeDesign-B-org-Tensor-terplasztika-001/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">galeriasavaria.hu/termekek/res</span><span class="invisible">zletek/kezmuves/5713870/MeddeDesign-B-org-Tensor-terplasztika-001/</span></a></p><p><a href="https://mastodon.social/tags/handmade" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>handmade</span></a> <a href="https://mastodon.social/tags/hungary" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>hungary</span></a> <a href="https://mastodon.social/tags/galeriasavaria" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>galeriasavaria</span></a> <a href="https://mastodon.social/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a></p>
Crypto News<p>Solana-Based NFT Marketplace Tensor to Launch TNSR Governance Token - Tensor, an NFT marketplace on Solana launched in 2022, is planning to launch its governan... - <a href="https://cryptonews.com/news/solana-based-nft-marketplace-tensor-to-launch-tnsr-governance-token.htm" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">cryptonews.com/news/solana-bas</span><span class="invisible">ed-nft-marketplace-tensor-to-launch-tnsr-governance-token.htm</span></a> <a href="https://schleuss.online/tags/altcoinnews" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>altcoinnews</span></a> <a href="https://schleuss.online/tags/nftnews" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nftnews</span></a> <a href="https://schleuss.online/tags/solana" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>solana</span></a> <a href="https://schleuss.online/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> <a href="https://schleuss.online/tags/nft" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nft</span></a></p>
Christos Argyropoulos MD, PhD<p>3 hours before the talk about going small and towards the <a href="https://mstdn.science/tags/edge" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>edge</span></a> with <a href="https://mstdn.science/tags/nanopore" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nanopore</span></a> <a href="https://mstdn.science/tags/RNAseq" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RNAseq</span></a> <a href="https://mstdn.science/tags/sequencing" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>sequencing</span></a> <a href="https://mstdn.science/tags/flongle" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>flongle</span></a> and <a href="https://mstdn.science/tags/tensor" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tensor</span></a> processing units!</p>
ExploreLive feeds
About