https://community.wolfram.com RSS Feed for Wolfram Community showing any discussions tagged with Machine Learning sorted by active. https://community.wolfram.com/groups/-/m/t/2380163 I recently noticed that Mathematica uses MxNet as the backend for neural networks. It seems to have been integrated in 2015. The blog post listing the rationale is [here](https://www.oreilly.com/content/apache-mxnet-in-the-wolfram-language/). MxNet seems to have not gained the momentum to become popular, you can see the [trends](https://paperswithcode.com/trends) from "papers with code". Lack of popularity means framework may be slow to develop. For instance, this [question](https://mathematica.stackexchange.com/questions/256323/neural-network-automatic-differentiation-autograd) about using neural networks to fit ODEs from Joshua Schrier. It requires underlying framework to support higher order gradients. There's an [issue](https://github.com/apache/incubator-mxnet/issues/10002) to add support in MxNET but progress has stalled. Meanwhile PyTorch/TensorFlow/JAX support this feature. Yaroslav Bulatov 2021-10-06T00:49:07Z https://community.wolfram.com/groups/-/m/t/3768970 &[Wolfram Notebook][1] [1]: https://www.wolframcloud.com/obj/4abe5c51-2cab-4ae7-bc7a-6bc65ec438e0 Lim Lee 2026-07-28T02:06:03Z https://community.wolfram.com/groups/-/m/t/3766719 &[Wolfram Notebook][1] [1]: https://www.wolframcloud.com/obj/c7153a1e-792b-4b61-9985-e05b3473cf7c Michael Rogers 2026-07-23T00:32:41Z https://community.wolfram.com/groups/-/m/t/3726656 &[Wolfram Notebook][1] [1]: https://www.wolframcloud.com/obj/4b2aea05-d260-4b29-804b-43bac36d7569 Daniel Carvalho 2026-06-03T15:23:31Z https://community.wolfram.com/groups/-/m/t/3749957 &[Wolfram Notebook][1] [1]: https://www.wolframcloud.com/obj/58cd9e8e-c02b-47d1-9860-6e8d18a44c73 Tci Fang 2026-07-09T16:34:04Z https://community.wolfram.com/groups/-/m/t/3762346 ![Learning Mechanics of Neural Network: Chaotic Pendulum Metaphor][1] &[Wolfram Notebook][2] [1]: https://community.wolfram.com//c/portal/getImageAttachment?filename=Picture_poster1.png&userId=3760386 [2]: https://www.wolframcloud.com/obj/e95023e2-1371-48e9-a2a6-bef42df107eb Jinming Zhang 2026-07-16T19:50:36Z https://community.wolfram.com/groups/-/m/t/3563034 Has anyone been able to install and run Mathematica on NVIDIA's new DGX Spark computer? If yes, does CUDA work? Does, NetTrain work? Are you able to train models? David Laxer 2025-10-21T17:21:12Z https://community.wolfram.com/groups/-/m/t/3762535 ![enter image description here][1] &[Wolfram Notebook][2] [1]: https://community.wolfram.com//c/portal/getImageAttachment?filename=Perturbation.png&userId=3762486 [2]: https://www.wolframcloud.com/obj/3877831c-8e3e-482d-991f-37d20cf4f99d Shan Leng 2026-07-16T19:19:20Z https://community.wolfram.com/groups/-/m/t/3761138 Standard Model is extremely well tested, but e.g. is incompatible with general relativity, is rather for effective perturbative approximations, also uses this gigantic Lagrangian found in epicycle-style: by guess&fit terms. So maybe, like in Copernican Revolution, we should search for **compact deeper nonperturbative Lagrangian** (e.g. [Skyrme][1]-like), **effectively described close to Standard Model + gravity**? Nonperturbative Lagrangians look simple, but have extremely complex consequences - maybe AI could search through them, automatically performing simulations testing various agreements? This kind of approaches have already started, e.g.: "**Towards AI-assisted neutrino flavor theory design**": https://www.nature.com/articles/s42005-026-02627-2 , "**Agentic Exploration of Physics Models**" https://journals.aps.org/prx/abstract/10.1103/xnqc-q6nt , or https://github.com/openwave-labs/openwave/blob/main/MODELS.md **actually testing such deeper Lagrangian candidates** - currently winning is [liquid-crystal-like][2]: just assumption that field has preferred anisotropy. What do you think about such approaches? Where to search for such deeper Lagrangians? Would be great if Wolfram had independent model benchmarking environment like OpenWave ... ![enter image description here][3] [1]: https://en.wikipedia.org/wiki/Skyrmion [2]: https://en.wikipedia.org/wiki/Draft:Liquid_crystal_particle_analogs [3]: https://community.wolfram.com//c/portal/getImageAttachment?filename=AI.png&userId=2844843 Jarek Duda 2026-07-16T09:52:33Z https://community.wolfram.com/groups/-/m/t/3751389 ![Implementing ancient musical systems][1] &[Wolfram Notebook][2] [1]: https://community.wolfram.com//c/portal/getImageAttachment?filename=Screenshot2026-07-09at15.55.53.png&userId=3750706 [2]: https://www.wolframcloud.com/obj/3c5aeb60-b448-4de6-b80e-78036eb90c9d Aahana Gupta 2026-07-09T19:56:13Z https://community.wolfram.com/groups/-/m/t/3751710 ![Characterizing the hypothesis and weight spaces of grid neural networks][1] &[Wolfram Notebook][2] [1]: https://community.wolfram.com//c/portal/getImageAttachment?filename=Screenshot2026-07-09at1.40.13%E2%80%AFPM.png&userId=3740350 [2]: https://www.wolframcloud.com/obj/a6ac34d2-d059-4a5e-bbb4-fa438b0922ca Jason Eun-Shik Tae 2026-07-09T20:06:06Z https://community.wolfram.com/groups/-/m/t/3745213 &[Wolfram Notebook][1] [1]: https://www.wolframcloud.com/obj/9e89fcf8-3b43-4fc3-a73a-c75a48f75394 Daniel Carvalho 2026-07-06T03:46:04Z https://community.wolfram.com/groups/-/m/t/3743024 &[Wolfram Notebook][1] [1]: https://www.wolframcloud.com/obj/65be4e60-1c9e-40c5-a92d-fe7c921344e0 Yewon Lim 2026-07-02T07:39:49Z https://community.wolfram.com/groups/-/m/t/3736647 ![Hunting anomalous comets with machine-learned probability distributions][1] &[Wolfram Notebook][2] [1]: https://community.wolfram.com//c/portal/getImageAttachment?filename=Huntinganomalouscometswithmachine-learnedprobabilitydistributions.png&userId=20103 [2]: https://www.wolframcloud.com/obj/38e2d744-d61d-46dd-8f55-addeecde7162 Lim Lee 2026-06-20T16:27:34Z https://community.wolfram.com/groups/-/m/t/3735063 ![The computational assyriologist - Part I: translating Akkadian cuneiform to English with a local LLM][1] &[Wolfram Notebook][2] [1]: https://community.wolfram.com//c/portal/getImageAttachment?filename=Thecomputationalassyriologist-PartI.png&userId=20103 [2]: https://www.wolframcloud.com/obj/75721bbd-04ae-4fdc-ac9d-ce02d7b3b7fe Marco Thiel 2026-06-17T14:08:42Z https://community.wolfram.com/groups/-/m/t/3732425 ![Edit-distance algorithm: categorification — NNG word graphs as path categories][1] &[Wolfram Notebook][2] [1]: https://community.wolfram.com//c/portal/getImageAttachment?filename=Edit-distancealgorithmcategorification.png&userId=20103 [2]: https://www.wolframcloud.com/obj/9906d027-0b83-4128-a28f-86327bacf821 Dara Shayda 2026-06-12T04:29:53Z https://community.wolfram.com/groups/-/m/t/3732807 ![Forging worlds: a generative model of the exoplanet population][1] &[Wolfram Notebook][2] [1]: https://community.wolfram.com//c/portal/getImageAttachment?filename=Forgingworldsagenerativemodeloftheexoplanetpopulation.png&userId=20103 [2]: https://www.wolframcloud.com/obj/da5be38e-e93d-4259-9e20-1181f27d05c8 Lim Lee 2026-06-12T15:17:56Z https://community.wolfram.com/groups/-/m/t/3729588 ![p-adic distance: a century-old number theory tool for robust hierarchical classification][1] &[Wolfram Notebook][2] [1]: https://community.wolfram.com//c/portal/getImageAttachment?filename=Thep-adicDistanceforHierarchicalData.png&userId=20103 [2]: https://www.wolframcloud.com/obj/80eb302f-91b8-4e09-a948-8eeaae22d9a9 Marco Thiel 2026-06-08T14:26:34Z https://community.wolfram.com/groups/-/m/t/3729841 &[Wolfram Notebook][1] [1]: https://www.wolframcloud.com/obj/833bf9a5-4767-4bbd-919f-4ff4bf5b460f Dara Shayda 2026-06-08T11:46:05Z https://community.wolfram.com/groups/-/m/t/3727339 &[Wolfram Notebook][1] [1]: https://www.wolframcloud.com/obj/445da91f-c3ac-454b-bd55-a682755493fc Hyeri Ahn 2026-06-04T10:56:07Z