<?xml version="1.0" encoding="UTF-8"?>
<rdf:RDF xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"><channel rdf:about="https://www.bibsonomy.org/user/bshanks/ml"><title>BibSonomy bookmarks for /user/bshanks/ml</title><link>https://www.bibsonomy.org/user/bshanks/ml</link><description>BibSonomy RSS Feed for /user/bshanks/ml</description><items><rdf:Seq><rdf:li rdf:resource="https://medium.com/data-science/faster-time-series-forecasting-with-ray-air-distributed-computing-part-3-of-3-632c96974774"/><rdf:li rdf:resource="https://web.archive.org/web/20251006162539/https://neptune.ai/blog/predicting-stock-prices-using-machine-learning"/><rdf:li rdf:resource="https://web.archive.org/web/20251006160541/https://neptune.ai/blog/mlops-tools-platforms-landscape"/><rdf:li rdf:resource="https://web.archive.org/web/20251024042208/https://neptune.ai/blog/category/time-series-forecasting"/><rdf:li rdf:resource="https://ggbaker.ca/data-science/"/><rdf:li rdf:resource="https://technicalwriting.dev/ml/embeddings/overview.html"/><rdf:li rdf:resource="https://github.com/gerdm/prml"/><rdf:li rdf:resource="https://ai.meta.com/blog/yann-lecun-ai-model-i-jepa/"/><rdf:li rdf:resource="https://www.di.ens.fr/%7Efbach/ltfp_book.pdf"/><rdf:li rdf:resource="https://news.ycombinator.com/item?id=39593256"/><rdf:li rdf:resource="https://news.ycombinator.com/item?id=39560862"/><rdf:li rdf:resource="https://cgad.ski/blog/where-is-noethers-principle-in-machine-learning.html"/><rdf:li rdf:resource="https://ai.stanford.edu/~zayd/why-is-machine-learning-hard.html"/><rdf:li rdf:resource="https://www.nature.com/articles/s41562-023-01719-1"/><rdf:li rdf:resource="https://www.quora.com/When-would-one-use-Random-Forests-over-Gradient-Boosted-Machines-GBMs"/><rdf:li rdf:resource="https://github.com/facebook/prophet"/><rdf:li rdf:resource="https://news.ycombinator.com/item?id=37665177"/><rdf:li rdf:resource="https://jax.readthedocs.io/en/latest/notebooks/quickstart.html"/><rdf:li rdf:resource="https://www.marktechpost.com/2023/09/26/microsoft-researchers-propose-neural-graphical-models-ngms-a-new-type-of-probabilistic-graphical-models-pgm-that-learns-to-represent-the-probability-function-over-the-domain-using-a-deep-neural-n/"/><rdf:li rdf:resource="https://news.ycombinator.com/item?id=35239972"/></rdf:Seq></items></channel><item rdf:about="https://medium.com/data-science/faster-time-series-forecasting-with-ray-air-distributed-computing-part-3-of-3-632c96974774"><title>How to Train Time Series Forecasting Faster using Ray, part 3 of 3 | by Christy Bergman | TDS Archive | Medium</title><description></description><link>https://medium.com/data-science/faster-time-series-forecasting-with-ray-air-distributed-computing-part-3-of-3-632c96974774</link><dc:creator>bshanks</dc:creator><dc:date>2026-04-22T08:40:45+02:00</dc:date><dc:subject>ml timeseries </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2026-04-22T08:40:45+02:00&#034; href=&#034;https://medium.com/data-science/faster-time-series-forecasting-with-ray-air-distributed-computing-part-3-of-3-632c96974774&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://medium.com/data-science/faster-time-series-forecasting-with-ray-air-distributed-computing-part-3-of-3-632c96974774&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/timeseries"/></rdf:Bag></taxo:topics></item><item rdf:about="https://web.archive.org/web/20251006162539/https://neptune.ai/blog/predicting-stock-prices-using-machine-learning"><title>Machine Learning for Stock Price Prediction</title><description></description><link>https://web.archive.org/web/20251006162539/https://neptune.ai/blog/predicting-stock-prices-using-machine-learning</link><dc:creator>bshanks</dc:creator><dc:date>2026-04-17T17:52:44+02:00</dc:date><dc:subject>lstm ml timeseries </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2026-04-17T17:52:44+02:00&#034; href=&#034;https://web.archive.org/web/20251006162539/https://neptune.ai/blog/predicting-stock-prices-using-machine-learning&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://web.archive.org/web/20251006162539/https://neptune.ai/blog/predicting-stock-prices-using-machine-learning&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/lstm"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/timeseries"/></rdf:Bag></taxo:topics></item><item rdf:about="https://web.archive.org/web/20251006160541/https://neptune.ai/blog/mlops-tools-platforms-landscape"><title>MLOps Landscape in 2025: Top Tools and Platforms</title><description></description><link>https://web.archive.org/web/20251006160541/https://neptune.ai/blog/mlops-tools-platforms-landscape</link><dc:creator>bshanks</dc:creator><dc:date>2026-04-17T17:47:39+02:00</dc:date><dc:subject>lib ml mlops </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2026-04-17T17:47:39+02:00&#034; href=&#034;https://web.archive.org/web/20251006160541/https://neptune.ai/blog/mlops-tools-platforms-landscape&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://web.archive.org/web/20251006160541/https://neptune.ai/blog/mlops-tools-platforms-landscape&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/lib"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/mlops"/></rdf:Bag></taxo:topics></item><item rdf:about="https://web.archive.org/web/20251024042208/https://neptune.ai/blog/category/time-series-forecasting"><title>Time Series - neptune.ai</title><description></description><link>https://web.archive.org/web/20251024042208/https://neptune.ai/blog/category/time-series-forecasting</link><dc:creator>bshanks</dc:creator><dc:date>2026-04-17T17:43:16+02:00</dc:date><dc:subject>ml timeseries toread </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2026-04-17T17:43:16+02:00&#034; href=&#034;https://web.archive.org/web/20251024042208/https://neptune.ai/blog/category/time-series-forecasting&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://web.archive.org/web/20251024042208/https://neptune.ai/blog/category/time-series-forecasting&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/timeseries"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/toread"/></rdf:Bag></taxo:topics></item><item rdf:about="https://ggbaker.ca/data-science/"><title>CMPT 353 Lecture Notes</title><description></description><link>https://ggbaker.ca/data-science/</link><dc:creator>bshanks</dc:creator><dc:date>2025-08-15T09:01:08+02:00</dc:date><dc:subject>course data ml </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2025-08-15T09:01:08+02:00&#034; href=&#034;https://ggbaker.ca/data-science/&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://ggbaker.ca/data-science/&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/course"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/data"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/></rdf:Bag></taxo:topics></item><item rdf:about="https://technicalwriting.dev/ml/embeddings/overview.html"><title>Embeddings are underrated</title><description></description><link>https://technicalwriting.dev/ml/embeddings/overview.html</link><dc:creator>bshanks</dc:creator><dc:date>2025-05-15T07:01:35+02:00</dc:date><dc:subject>embedding ml </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2025-05-15T07:01:35+02:00&#034; href=&#034;https://technicalwriting.dev/ml/embeddings/overview.html&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://technicalwriting.dev/ml/embeddings/overview.html&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/embedding"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/></rdf:Bag></taxo:topics></item><item rdf:about="https://github.com/gerdm/prml"><title>GitHub - gerdm/prml: Repository of notes, code and notebooks in Python for the book Pattern Recognition and Machine Learning by Christopher Bishop</title><description></description><link>https://github.com/gerdm/prml</link><dc:creator>bshanks</dc:creator><dc:date>2025-04-16T21:55:15+02:00</dc:date><dc:subject>book ml textbook </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2025-04-16T21:55:15+02:00&#034; href=&#034;https://github.com/gerdm/prml&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://github.com/gerdm/prml&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/book"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/textbook"/></rdf:Bag></taxo:topics></item><item rdf:about="https://ai.meta.com/blog/yann-lecun-ai-model-i-jepa/"><title>The first AI model based on Yann LeCun’s vision for more human-like AI</title><description></description><link>https://ai.meta.com/blog/yann-lecun-ai-model-i-jepa/</link><dc:creator>bshanks</dc:creator><dc:date>2024-11-04T05:38:46+01:00</dc:date><dc:subject>ai lecun ml </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2024-11-04T05:38:46+01:00&#034; href=&#034;https://ai.meta.com/blog/yann-lecun-ai-model-i-jepa/&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://ai.meta.com/blog/yann-lecun-ai-model-i-jepa/&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ai"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/lecun"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/></rdf:Bag></taxo:topics></item><item rdf:about="https://www.di.ens.fr/%7Efbach/ltfp_book.pdf"><title>ltfp_book.pdf</title><description></description><link>https://www.di.ens.fr/%7Efbach/ltfp_book.pdf</link><dc:creator>bshanks</dc:creator><dc:date>2024-03-10T22:42:51+01:00</dc:date><dc:subject>learningtheory ml </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2024-03-10T22:42:51+01:00&#034; href=&#034;https://www.di.ens.fr/%7Efbach/ltfp_book.pdf&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://www.di.ens.fr/%7Efbach/ltfp_book.pdf&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/learningtheory"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/></rdf:Bag></taxo:topics></item><item rdf:about="https://news.ycombinator.com/item?id=39593256"><title>Opus 1.5 released: Opus gets a machine learning upgrade | Hacker News</title><description></description><link>https://news.ycombinator.com/item?id=39593256</link><dc:creator>bshanks</dc:creator><dc:date>2024-03-08T05:29:51+01:00</dc:date><dc:subject>codec ml opus </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2024-03-08T05:29:51+01:00&#034; href=&#034;https://news.ycombinator.com/item?id=39593256&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://news.ycombinator.com/item?id=39593256&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/codec"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/opus"/></rdf:Bag></taxo:topics></item><item rdf:about="https://news.ycombinator.com/item?id=39560862"><title>Where is Noether&#039;s principle in machine learning? | Hacker News</title><description></description><link>https://news.ycombinator.com/item?id=39560862</link><dc:creator>bshanks</dc:creator><dc:date>2024-03-04T09:32:28+01:00</dc:date><dc:subject>ml noether physics </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2024-03-04T09:32:28+01:00&#034; href=&#034;https://news.ycombinator.com/item?id=39560862&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://news.ycombinator.com/item?id=39560862&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/noether"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/physics"/></rdf:Bag></taxo:topics></item><item rdf:about="https://cgad.ski/blog/where-is-noethers-principle-in-machine-learning.html"><title>Where Is Noether&#039;s Principle in Machine Learning?</title><description>Noether</description><link>https://cgad.ski/blog/where-is-noethers-principle-in-machine-learning.html</link><dc:creator>bshanks</dc:creator><dc:date>2024-03-04T09:31:45+01:00</dc:date><dc:subject>ml noether physics </dc:subject><content:encoded>&lt;span itemprop=&#034;description&#034;&gt;Noether&lt;/span&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/noether"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/physics"/></rdf:Bag></taxo:topics></item><item rdf:about="https://ai.stanford.edu/~zayd/why-is-machine-learning-hard.html"><title>Zayd&#039;s Blog – Why is machine learning &#039;hard&#039;?</title><description></description><link>https://ai.stanford.edu/~zayd/why-is-machine-learning-hard.html</link><dc:creator>bshanks</dc:creator><dc:date>2024-01-25T00:33:43+01:00</dc:date><dc:subject>debug ml </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2024-01-25T00:33:43+01:00&#034; href=&#034;https://ai.stanford.edu/~zayd/why-is-machine-learning-hard.html&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://ai.stanford.edu/~zayd/why-is-machine-learning-hard.html&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/debug"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/></rdf:Bag></taxo:topics></item><item rdf:about="https://www.nature.com/articles/s41562-023-01719-1"><title>A model of conceptual bootstrapping in human cognition | Nature Human Behaviour</title><description></description><link>https://www.nature.com/articles/s41562-023-01719-1</link><dc:creator>bshanks</dc:creator><dc:date>2023-10-20T06:44:07+02:00</dc:date><dc:subject>cogsci commonsense concept ml </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2023-10-20T06:44:07+02:00&#034; href=&#034;https://www.nature.com/articles/s41562-023-01719-1&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://www.nature.com/articles/s41562-023-01719-1&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/cogsci"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/commonsense"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/concept"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/></rdf:Bag></taxo:topics></item><item rdf:about="https://www.quora.com/When-would-one-use-Random-Forests-over-Gradient-Boosted-Machines-GBMs"><title>When would one use Random Forests over Gradient Boosted Machines (GBMs)? - Quora</title><description></description><link>https://www.quora.com/When-would-one-use-Random-Forests-over-Gradient-Boosted-Machines-GBMs</link><dc:creator>bshanks</dc:creator><dc:date>2023-10-15T02:30:56+02:00</dc:date><dc:subject>gbm ml randomforest rf </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2023-10-15T02:30:56+02:00&#034; href=&#034;https://www.quora.com/When-would-one-use-Random-Forests-over-Gradient-Boosted-Machines-GBMs&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://www.quora.com/When-would-one-use-Random-Forests-over-Gradient-Boosted-Machines-GBMs&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/gbm"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/randomforest"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/rf"/></rdf:Bag></taxo:topics></item><item rdf:about="https://github.com/facebook/prophet"><title>facebook/prophet: Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.</title><description></description><link>https://github.com/facebook/prophet</link><dc:creator>bshanks</dc:creator><dc:date>2023-10-04T03:37:56+02:00</dc:date><dc:subject>ml timeseries </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2023-10-04T03:37:56+02:00&#034; href=&#034;https://github.com/facebook/prophet&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://github.com/facebook/prophet&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/timeseries"/></rdf:Bag></taxo:topics></item><item rdf:about="https://news.ycombinator.com/item?id=37665177"><title>Model development on Prophet stopped this year: https://medium.com/@cuongduong_3... | Hacker News</title><description></description><link>https://news.ycombinator.com/item?id=37665177</link><dc:creator>bshanks</dc:creator><dc:date>2023-10-04T03:37:50+02:00</dc:date><dc:subject>ml timeseries </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2023-10-04T03:37:50+02:00&#034; href=&#034;https://news.ycombinator.com/item?id=37665177&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://news.ycombinator.com/item?id=37665177&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/timeseries"/></rdf:Bag></taxo:topics></item><item rdf:about="https://jax.readthedocs.io/en/latest/notebooks/quickstart.html"><title>JAX Quickstart — JAX documentation</title><description></description><link>https://jax.readthedocs.io/en/latest/notebooks/quickstart.html</link><dc:creator>bshanks</dc:creator><dc:date>2023-10-04T02:42:57+02:00</dc:date><dc:subject>gpu ml numpy </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2023-10-04T02:42:57+02:00&#034; href=&#034;https://jax.readthedocs.io/en/latest/notebooks/quickstart.html&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://jax.readthedocs.io/en/latest/notebooks/quickstart.html&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/gpu"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/numpy"/></rdf:Bag></taxo:topics></item><item rdf:about="https://www.marktechpost.com/2023/09/26/microsoft-researchers-propose-neural-graphical-models-ngms-a-new-type-of-probabilistic-graphical-models-pgm-that-learns-to-represent-the-probability-function-over-the-domain-using-a-deep-neural-n/"><title>Microsoft Researchers Propose Neural Graphical Models (NGMs): A New Type of Probabilistic Graphical Models (PGM) that Learns to Represent the Probability Function Over the Domain Using a Deep Neural Network - MarkTechPost</title><description></description><link>https://www.marktechpost.com/2023/09/26/microsoft-researchers-propose-neural-graphical-models-ngms-a-new-type-of-probabilistic-graphical-models-pgm-that-learns-to-represent-the-probability-function-over-the-domain-using-a-deep-neural-n/</link><dc:creator>bshanks</dc:creator><dc:date>2023-10-03T23:32:52+02:00</dc:date><dc:subject>bayesnet ml pgm </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2023-10-03T23:32:52+02:00&#034; href=&#034;https://www.marktechpost.com/2023/09/26/microsoft-researchers-propose-neural-graphical-models-ngms-a-new-type-of-probabilistic-graphical-models-pgm-that-learns-to-represent-the-probability-function-over-the-domain-using-a-deep-neural-n/&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://www.marktechpost.com/2023/09/26/microsoft-researchers-propose-neural-graphical-models-ngms-a-new-type-of-probabilistic-graphical-models-pgm-that-learns-to-represent-the-probability-function-over-the-domain-using-a-deep-neural-n/&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/bayesnet"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/pgm"/></rdf:Bag></taxo:topics></item><item rdf:about="https://news.ycombinator.com/item?id=35239972"><title>Run 100B+ language models at home, BitTorrent‑style | Hacker News</title><description></description><link>https://news.ycombinator.com/item?id=35239972</link><dc:creator>bshanks</dc:creator><dc:date>2023-03-21T21:39:38+01:00</dc:date><dc:subject>gpt ml neuralnet nnet </dc:subject><content:encoded>&lt;a itemprop=&#034;url&#034; data-versiondate=&#034;2023-03-21T21:39:38+01:00&#034; href=&#034;https://news.ycombinator.com/item?id=35239972&#034; rel=&#034;nofollow&#034; class=&#034;description-link&#034;&gt;https://news.ycombinator.com/item?id=35239972&lt;/a&gt;</content:encoded><taxo:topics><rdf:Bag><rdf:li rdf:resource="https://www.bibsonomy.org/tag/gpt"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/ml"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/neuralnet"/><rdf:li rdf:resource="https://www.bibsonomy.org/tag/nnet"/></rdf:Bag></taxo:topics></item></rdf:RDF>