mastodon.ie

Svenja GuhrUsing <a href="https://fedihum.org/tags/doc2vec" class="mention hashtag" rel="nofollow noopener" target="_blank">#doc2vec</a> <a href="https://fedihum.org/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a> and <a href="https://fedihum.org/tags/TextSimilarity" class="mention hashtag" rel="nofollow noopener" target="_blank">#TextSimilarity</a>, she analyzes how canonized works influence later literary production while highlighting texts that have been forgotten, marginalized, or overlooked. <a href="https://fedihum.org/tags/Canon" class="mention hashtag" rel="nofollow noopener" target="_blank">#Canon</a> vs. <a href="https://fedihum.org/tags/Counter" class="mention hashtag" rel="nofollow noopener" target="_blank">#Counter</a>-canon becomes a scale shaped by retrospective, cultural, and temporal markers. <a href="https://fedihum.org/tags/CLS" class="mention hashtag" rel="nofollow noopener" target="_blank">#CLS</a>

Mathieu JacomyAh, my latest tool, just out of the oven! Just in time for my Summer break... It's called *Vandolie*. It's for high school students, but it may work for you as well. I will let you discover it by yourself.👉 <a href="https://jacomyma.github.io/vandolie/en/" rel="nofollow noopener" translate="no" target="_blank">https://jacomyma.github.io/vandolie/en/</a>It's like a mini CorTexT for teenagers, if you know that tool. But it runs entirely in the browser.Entirely localized in Danish.Consider it a beta version. Usable, but feel free to file GitHub issues for feedback & bugs.<a href="https://mas.to/tags/CSSH" class="mention hashtag" rel="nofollow noopener" target="_blank">#CSSH</a> <a href="https://mas.to/tags/DistantReading" class="mention hashtag" rel="nofollow noopener" target="_blank">#DistantReading</a> <a href="https://mas.to/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a>

Christian Drumm 🇪🇺🧗🚵Playing with <a href="https://mastodon.social/@duckdb" class="u-url mention" rel="nofollow noopener" target="_blank">@duckdb</a>, <a href="https://mastodon.social/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a> and <a href="https://mastodon.social/tags/skiplists" class="mention hashtag" rel="nofollow noopener" target="_blank">#skiplists</a>. Got exercise to understand how <a href="https://mastodon.social/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#RAG</a> works under the hood.

➴➴➴Æ🜔Ɲ.Ƈꭚ⍴𝔥єɼ👩🏻‍💻Okay, Back of the napkin math: - There are probably 100 million sites and 1.5 billion pages worth indexing in a <a href="https://lgbtqia.space/tags/search" class="mention hashtag" rel="nofollow noopener" target="_blank">#search</a> engine - It takes about 1TB to <a href="https://lgbtqia.space/tags/index" class="mention hashtag" rel="nofollow noopener" target="_blank">#index</a> 30 million pages. - We only care about text on a page.I define a page as worth indexing if: - It is not a FAANG site - It has at least one referrer (no DD Web) - It's activeSo, this means we need 40TB of fast data to make a good index for the internet. That's not "runs locally" sized, but it is nonprofit sized.My size assumptions are basically as follows: - <a href="https://lgbtqia.space/tags/URL" class="mention hashtag" rel="nofollow noopener" target="_blank">#URL</a> - <a href="https://lgbtqia.space/tags/TFIDF" class="mention hashtag" rel="nofollow noopener" target="_blank">#TFIDF</a> information - Text <a href="https://lgbtqia.space/tags/Embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#Embeddings</a> - Snippet We can store an index for 30kb. So, for 40TB we can store an full internet index. That's about $500 in storage.Access time becomes a problem. TFIDF for the whole internet can easily fit in ram. Even with <a href="https://lgbtqia.space/tags/quantized" class="mention hashtag" rel="nofollow noopener" target="_blank">#quantized</a> embeddings, you can only fit 2 million per GB in ram. Assuming you had enough RAM it could be fast: TF-IDF to get 100 million candidated, <a href="https://lgbtqia.space/tags/FAISS" class="mention hashtag" rel="nofollow noopener" target="_blank">#FAISS</a> to sort those, load snippets dynamically, potentially modify rank by referers etc.6 128 MG <a href="https://lgbtqia.space/tags/Framework" class="mention hashtag" rel="nofollow noopener" target="_blank">#Framework</a> <a href="https://lgbtqia.space/tags/desktops" class="mention hashtag" rel="nofollow noopener" target="_blank">#desktops</a> each with 5tb HDs (plus one raspberry pi to sort the final condidates from the six machines) is enough to replace <a href="https://lgbtqia.space/tags/Google" class="mention hashtag" rel="nofollow noopener" target="_blank">#Google</a>. That's about $15k. In two to three years this will be doable on a single machine for around $3k.By the end of the decade it should be able to be run as an app on a powerful desktopThree years after that it can run on a <a href="https://lgbtqia.space/tags/laptop" class="mention hashtag" rel="nofollow noopener" target="_blank">#laptop</a>.Three years after that it can run on a <a href="https://lgbtqia.space/tags/cellphone" class="mention hashtag" rel="nofollow noopener" target="_blank">#cellphone</a>.By #2040 it's a background process on your cellphone.

Markus EiseleFrom Strings to Semantics: Comparing Text with Java, Quarkus, and Embeddings Learn how to build an AI-powered text similarity service using Quarkus, LangChain4j, and local embedding models. <a href="https://myfear.substack.com/p/java-quarkus-text-embeddings-similarity" rel="nofollow noopener" translate="no" target="_blank">https://myfear.substack.com/p/java-quarkus-text-embeddings-similarity</a> <a href="https://mastodon.online/tags/Java" class="mention hashtag" rel="nofollow noopener" target="_blank">#Java</a> <a href="https://mastodon.online/tags/Quarkus" class="mention hashtag" rel="nofollow noopener" target="_blank">#Quarkus</a> <a href="https://mastodon.online/tags/Embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#Embeddings</a> <a href="https://mastodon.online/tags/Ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#Ollama</a> <a href="https://mastodon.online/tags/LangChain4j" class="mention hashtag" rel="nofollow noopener" target="_blank">#LangChain4j</a>

JMLR'Variance-Aware Estimation of Kernel Mean Embedding', by Geoffrey Wolfer, Pierre Alquier.<a href="http://jmlr.org/papers/v26/23-0161.html" rel="nofollow noopener" translate="no" target="_blank">http://jmlr.org/papers/v26/23-0161.html</a> <a href="https://sigmoid.social/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a> <a href="https://sigmoid.social/tags/embedding" class="mention hashtag" rel="nofollow noopener" target="_blank">#embedding</a> <a href="https://sigmoid.social/tags/empirical" class="mention hashtag" rel="nofollow noopener" target="_blank">#empirical</a>

FIZ ISE Research GroupWe are very happy that our colleage <a href="https://sigmoid.social/@GenAsefa" class="u-url mention" rel="nofollow noopener" target="_blank">@GenAsefa</a> has contributed the chapter on "Neurosymbolic Methods for Dynamic Knowledge Graphs" for the newly published Handbook on Neurosymbolic AI and Knowledge Graphs together with Mehwish Alam and Pierre-Henri Paris.Handbook: <a href="https://ebooks.iospress.nl/doi/10.3233/FAIA400" rel="nofollow noopener" translate="no" target="_blank">https://ebooks.iospress.nl/doi/10.3233/FAIA400</a> our own chapter on arxive: <a href="https://arxiv.org/abs/2409.04572" rel="nofollow noopener" translate="no" target="_blank">https://arxiv.org/abs/2409.04572</a><a href="https://sigmoid.social/tags/neurosymbolicAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#neurosymbolicAI</a> <a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://sigmoid.social/tags/generativeAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#generativeAI</a> <a href="https://sigmoid.social/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMs</a> <a href="https://sigmoid.social/tags/knowledgegraphs" class="mention hashtag" rel="nofollow noopener" target="_blank">#knowledgegraphs</a> <a href="https://sigmoid.social/tags/semanticweb" class="mention hashtag" rel="nofollow noopener" target="_blank">#semanticweb</a> <a href="https://sigmoid.social/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a> <a href="https://sigmoid.social/tags/graphembeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#graphembeddings</a>

FIZ ISE Research GroupPoster from our colleague <a href="https://blog.epoz.org/" class="u-url mention" rel="nofollow noopener" target="_blank">@epoz</a> from UGent-IMEC Linked Data & Solid course. "Exploding Mittens - Getting to grips with huge SKOS datasets" on semantic embeddings enhanced SPARQL queries for ICONCLASS data. Congrats for the 'best poster' award ;-) poster: <a href="https://zenodo.org/records/14887544" rel="nofollow noopener" translate="no" target="_blank">https://zenodo.org/records/14887544</a> iconclass on GitHub: <a href="https://github.com/iconclass" rel="nofollow noopener" translate="no" target="_blank">https://github.com/iconclass</a><a href="https://sigmoid.social/tags/rdf2vec" class="mention hashtag" rel="nofollow noopener" target="_blank">#rdf2vec</a> <a href="https://sigmoid.social/tags/bert" class="mention hashtag" rel="nofollow noopener" target="_blank">#bert</a> <a href="https://sigmoid.social/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#llm</a> <a href="https://sigmoid.social/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a> <a href="https://sigmoid.social/tags/iconclass" class="mention hashtag" rel="nofollow noopener" target="_blank">#iconclass</a> <a href="https://sigmoid.social/tags/semanticweb" class="mention hashtag" rel="nofollow noopener" target="_blank">#semanticweb</a> <a href="https://sigmoid.social/tags/lod" class="mention hashtag" rel="nofollow noopener" target="_blank">#lod</a> <a href="https://sigmoid.social/tags/linkeddata" class="mention hashtag" rel="nofollow noopener" target="_blank">#linkeddata</a> <a href="https://sigmoid.social/tags/knowledgegraphs" class="mention hashtag" rel="nofollow noopener" target="_blank">#knowledgegraphs</a> <a href="https://sigmoid.social/tags/dh" class="mention hashtag" rel="nofollow noopener" target="_blank">#dh</a> <a href="https://nfdi.social/@nfdi4culture" class="u-url mention" rel="nofollow noopener" target="_blank">@nfdi4culture</a> <a href="https://wisskomm.social/@fiz_karlsruhe" class="u-url mention" rel="nofollow noopener" target="_blank">@fiz_karlsruhe</a> <a href="https://sigmoid.social/tags/iconclass" class="mention hashtag" rel="nofollow noopener" target="_blank">#iconclass</a>

Mark IgraIs there a consensus process or good paper on state of the art on using <a href="https://sciences.social/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a> & <a href="https://sciences.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLM</a> to do the kinds of things that were being done with topic models? I imagine for tasks with pre-defined classifications, prompts are sufficient, but any recommendations for identifying latent classes? After reading the paper below I think I'll want to use local models. <a href="https://sciences.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#machinelearning</a> <a href="https://drive.google.com/file/d/1wNDIkMZfAGoh4Oaojrgll9SPg3eT-YXz/view" rel="nofollow noopener" translate="no" target="_blank">https://drive.google.com/file/d/1wNDIkMZfAGoh4Oaojrgll9SPg3eT-YXz/view</a>

Andrew Wooldridge 🐲Embeddings are cool <a href="https://technicalwriting.dev/data/embeddings.html" rel="nofollow noopener" translate="no" target="_blank">https://technicalwriting.dev/data/embeddings.html</a> <a href="https://social.lol/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#llm</a> <a href="https://social.lol/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a>

JMLR'Recursive Estimation of Conditional Kernel Mean Embeddings', by Ambrus Tamás, Balázs Csanád Csáji.<a href="http://jmlr.org/papers/v25/23-0168.html" rel="nofollow noopener" translate="no" target="_blank">http://jmlr.org/papers/v25/23-0168.html</a> <a href="https://sigmoid.social/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a> <a href="https://sigmoid.social/tags/supervised" class="mention hashtag" rel="nofollow noopener" target="_blank">#supervised</a> <a href="https://sigmoid.social/tags/estimation" class="mention hashtag" rel="nofollow noopener" target="_blank">#estimation</a>

Ian K TindaleMy prediction of the day There will be a resurgence of kerfuffle and bustle around Virtual Reality again Why? I predict that there will be a direction ahead for multimodal LLMs and their agentic systems to be able to produce 3D scenarios which represent a sort of token-memory bound ‘known world’ in which the ‘perception’ of the LLM can ‘project’ things it ‘knows’ about into this imaginary world, giving eg Blender files that render the output (and even as moving pictures, kinematic sequences etc, resulting in movie or video playout) If a multimodal LLM with Blender output can make movies, it can also make virtual reality movies, and even turn this into a live scenario rather than playout, and then it turns into an input as well as output medium Your (and others) actions and decisions within a VR space (hosted or provided or run by the LLM system) act as contributing input and in fact can be tokenised as an embedding itself If that’s the case, anything within the ‘real’ to ‘virtual’ interface space can be tokenised into an embedding for that scenario, so ‘meaning’ might come to be extracted, regarding position and movement and why those ducks are now all moving over there instead of staying over here and what’s the problem with being here, what’s compelling them to be there, is there a meaning, what’s the meaning, nothing happens for no reason Anyway, AI systems that are capable of producing a virtual world which we can step into to experience the resulting output of the AI system, and at the same time we proffer input directly verbally, and behaviourally, will bring a whole load of interest in VR back again so we’ll be hearing about VR all over again <a href="https://toot.pikopublish.ing/tags/AI" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://toot.pikopublish.ing/tags/LLM" rel="nofollow noopener" target="_blank">#LLM</a> <a href="https://toot.pikopublish.ing/tags/MultimodalLLM" rel="nofollow noopener" target="_blank">#MultimodalLLM</a> <a href="https://toot.pikopublish.ing/tags/AgenticAI" rel="nofollow noopener" target="_blank">#AgenticAI</a> <a href="https://toot.pikopublish.ing/tags/VR" rel="nofollow noopener" target="_blank">#VR</a> <a href="https://toot.pikopublish.ing/tags/VirtualReality" rel="nofollow noopener" target="_blank">#VirtualReality</a> <a href="https://toot.pikopublish.ing/tags/Blender" rel="nofollow noopener" target="_blank">#Blender</a> <a href="https://toot.pikopublish.ing/tags/embeddings" rel="nofollow noopener" target="_blank">#embeddings</a> <a href="https://toot.pikopublish.ing/tags/meaning" rel="nofollow noopener" target="_blank">#meaning</a> <a href="https://toot.pikopublish.ing/tags/ducks" rel="nofollow noopener" target="_blank">#ducks</a>

Harald SackIn 2013, Mikolov et al. (from Google) published word2vec, a neural network based framework to learn distributed representations of words as dense vectors in continuous space, aka word embeddings.T. Mikolov et al. (2013). Efficient Estimation of Word Representations in Vector Space. arXiv:1301.3781 <a href="https://arxiv.org/abs/1301.3781" rel="nofollow noopener" translate="no" target="_blank">https://arxiv.org/abs/1301.3781</a><a href="https://sigmoid.social/tags/HistoryOfAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#HistoryOfAI</a> <a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://sigmoid.social/tags/ise2024" class="mention hashtag" rel="nofollow noopener" target="_blank">#ise2024</a> <a href="https://sigmoid.social/tags/lecture" class="mention hashtag" rel="nofollow noopener" target="_blank">#lecture</a> <a href="https://sigmoid.social/tags/distributionalsemantics" class="mention hashtag" rel="nofollow noopener" target="_blank">#distributionalsemantics</a> <a href="https://sigmoid.social/tags/wordembeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#wordembeddings</a> <a href="https://sigmoid.social/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a> <a href="https://fedihum.org/@sourisnumerique" class="u-url mention" rel="nofollow noopener" target="_blank">@sourisnumerique</a> <a href="https://sigmoid.social/@enorouzi" class="u-url mention" rel="nofollow noopener" target="_blank">@enorouzi</a> <a href="https://sigmoid.social/@fizise" class="u-url mention" rel="nofollow noopener" target="_blank">@fizise</a>

Sören Auer 🇪🇺🇺🇦Ask your (research) question against 76 Million scientific articles: <a href="https://ask.orkg.org" rel="nofollow noopener" translate="no" target="_blank">https://ask.orkg.org</a><a href="https://openbiblio.social/@orkg" class="u-url mention" rel="nofollow noopener" target="_blank">@orkg</a> ASK (Assistant for Scientific Knowledge) uses vector <a href="https://mstdn.social/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a> to find the most relevant papers and an open-source <a href="https://mstdn.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLM</a> to synthesize the answer for you.

Harald SackInteresting new survey paper on ontology embeddings: Jiaoyan Chen, Olga Mashkova, Fernando Zhapa-Camacho, Robert Hoehndorf, Yuan He, Ian Horrocks, Ontology Embedding: A Survey of Methods, Applications and Resources<a href="https://arxiv.org/abs/2406.10964" rel="nofollow noopener" translate="no" target="_blank">https://arxiv.org/abs/2406.10964</a><a href="https://sigmoid.social/tags/ontologies" class="mention hashtag" rel="nofollow noopener" target="_blank">#ontologies</a> <a href="https://sigmoid.social/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a> <a href="https://sigmoid.social/tags/knowledgegraphs" class="mention hashtag" rel="nofollow noopener" target="_blank">#knowledgegraphs</a>

:rss: Hacker NewsShow HN: AI Agent System to Analyze ArXiv AI Papers <a href="https://www.stack-ai.com/form/83883819-33d3-443c-88db-18106c9226da/ba81c6e6-b8af-4a97-b37a-174502daf8c4/6661deb730cbde865feba7f7" rel="nofollow noopener" translate="no" target="_blank">https://www.stack-ai.com/form/83883819-33d3-443c-88db-18106c9226da/ba81c6e6-b8af-4a97-b37a-174502daf8c4/6661deb730cbde865feba7f7</a> <a href="https://rss-mstdn.studiofreesia.com/tags/ycombinator" class="mention hashtag" rel="nofollow noopener" target="_blank">#ycombinator</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Stack_AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#Stack_AI</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Enterprise_AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#Enterprise_AI</a> <a href="https://rss-mstdn.studiofreesia.com/tags/AI_applications" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI_applications</a> <a href="https://rss-mstdn.studiofreesia.com/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#RAG</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Fine_tunning" class="mention hashtag" rel="nofollow noopener" target="_blank">#Fine_tunning</a> <a href="https://rss-mstdn.studiofreesia.com/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMs</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#Embeddings</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Custom_ChatGPT" class="mention hashtag" rel="nofollow noopener" target="_blank">#Custom_ChatGPT</a> <a href="https://rss-mstdn.studiofreesia.com/tags/AI_Applications" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI_Applications</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Generative_AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#Generative_AI</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Hospitality" class="mention hashtag" rel="nofollow noopener" target="_blank">#Hospitality</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Retail" class="mention hashtag" rel="nofollow noopener" target="_blank">#Retail</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Marketing" class="mention hashtag" rel="nofollow noopener" target="_blank">#Marketing</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Advertising" class="mention hashtag" rel="nofollow noopener" target="_blank">#Advertising</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Healthcare" class="mention hashtag" rel="nofollow noopener" target="_blank">#Healthcare</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Real_Estate" class="mention hashtag" rel="nofollow noopener" target="_blank">#Real_Estate</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Finance" class="mention hashtag" rel="nofollow noopener" target="_blank">#Finance</a> <a href="https://rss-mstdn.studiofreesia.com/tags/Insurance" class="mention hashtag" rel="nofollow noopener" target="_blank">#Insurance</a>

JMLR'An Embedding Framework for the Design and Analysis of Consistent Polyhedral Surrogates', by Jessie Finocchiaro, Rafael M. Frongillo, Bo Waggoner.<a href="http://jmlr.org/papers/v25/22-0743.html" rel="nofollow noopener" translate="no" target="_blank">http://jmlr.org/papers/v25/22-0743.html</a> <a href="https://sigmoid.social/tags/surrogates" class="mention hashtag" rel="nofollow noopener" target="_blank">#surrogates</a> <a href="https://sigmoid.social/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a> <a href="https://sigmoid.social/tags/surrogate" class="mention hashtag" rel="nofollow noopener" target="_blank">#surrogate</a>

o19sA substantial portion of unstructured data contains multimodal elements such as text, tables, and images. Praveen and Hajer from Amazon will explore the utilization of <a href="https://fosstodon.org/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMs</a> and multimodal <a href="https://fosstodon.org/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a> for <a href="https://fosstodon.org/tags/RAG" class="mention hashtag" rel="nofollow noopener" target="_blank">#RAG</a> at Haystack US <a href="https://haystackconf.com/us2024/talk-14/" rel="nofollow noopener" translate="no" target="_blank">https://haystackconf.com/us2024/talk-14/</a>

StarbeamrainbowlabsNew blog post time! A new blog post series explaining basic AI concepts. Got something you want explained? Do let me know!Defining AI: Word embeddings<a href="https://starbeamrainbowlabs.com/blog/article.php?article=posts%2F543-defining-ai-word-embeddings.html" rel="nofollow noopener" translate="no" target="_blank">https://starbeamrainbowlabs.com/blog/article.php?article=posts%2F543-defining-ai-word-embeddings.html</a><a href="https://fediscience.org/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ai</a> <a href="https://fediscience.org/tags/embeddings" class="mention hashtag" rel="nofollow noopener" target="_blank">#embeddings</a> <a href="https://fediscience.org/tags/nlp" class="mention hashtag" rel="nofollow noopener" target="_blank">#nlp</a> <a href="https://fediscience.org/tags/blogpost" class="mention hashtag" rel="nofollow noopener" target="_blank">#blogpost</a> <a href="https://fediscience.org/tags/iamslightlyburntoutfromthesiswriting" class="mention hashtag" rel="nofollow noopener" target="_blank">#iamslightlyburntoutfromthesiswriting</a>

Ferdinando Simonetti [ A story from Shaw Talebi on Medium ] Read this story from Shaw Talebi on Medium: <a href="https://towardsdatascience.com/text-embeddings-classification-and-semantic-search-8291746220be" rel="nofollow noopener" target="_blank">https://towardsdatascience.com/text-embeddings-classification-and-semantic-search-8291746220be</a> <a href="https://misskey.social/tags/LLM" rel="nofollow noopener" target="_blank">#LLM</a> <a href="https://misskey.social/tags/Embeddings" rel="nofollow noopener" target="_blank">#Embeddings</a>

Recent searches

Search options

Administered by:

Server stats:

#embeddings