# \#machine-learning

**URL:** https://discourse.julialang.org/tag/machine-learning/259.md

[Latest](https://discourse.julialang.org/latest.md) · [Categories](https://discourse.julialang.org/categories.md) · [Tags](https://discourse.julialang.org/tags.md)

---

## [\[ANN\] ReactantNitro.jl: Reactant-first training framework](https://discourse.julialang.org/t/ann-reactantnitro-jl-reactant-first-training-framework/139500)

<div class="topic-metadata">

**Author:** [@csvance](https://discourse.julialang.org/u/csvance)\
**Replies:** 4\
**Last updated:** [September 22, 2026, 7:47am UTC](https://discourse.julialang.org/t/ann-reactantnitro-jl-reactant-first-training-framework/139500 "2026-09-22T07:47:15Z")

</div>

I’m excited to finally release ReactantNitro.jl; a Reactant-first training framework inspired by PyTorch Lightning, but specifically designed around making working with Reactant.jl easy while still allowing for a large a…

---

## [Looking for advice on package for lazily evaluated kernel matrix on the GPU](https://discourse.julialang.org/t/looking-for-advice-on-package-for-lazily-evaluated-kernel-matrix-on-the-gpu/139089)

<div class="topic-metadata">

**Author:** [@trevorgloe](https://discourse.julialang.org/u/trevorgloe)\
**Replies:** 2\
**Last updated:** [September 1, 2026, 12:37am UTC](https://discourse.julialang.org/t/looking-for-advice-on-package-for-lazily-evaluated-kernel-matrix-on-the-gpu/139089 "2026-09-01T00:37:29Z")

</div>

I am working on creating a package for lazily evaluated kernel matrices, which will work on the GPU via KernelAbstractions. The idea is to create a central object (LazyKernelMatrix) which does not allocate and evaluates …

---

## [Exact Network Surgery and Reactive Computational Graphs in Julia with NeuroDSL](https://discourse.julialang.org/t/exact-network-surgery-and-reactive-computational-graphs-in-julia-with-neurodsl/138303)

<div class="topic-metadata">

**Author:** [@Khemais\_Abdallah](https://discourse.julialang.org/u/Khemais_Abdallah)\
**Replies:** 14\
**Last updated:** [July 22, 2026, 12:21pm UTC](https://discourse.julialang.org/t/exact-network-surgery-and-reactive-computational-graphs-in-julia-with-neurodsl/138303 "2026-07-22T12:21:01Z")

</div>

Exact Network Surgery and Reactive Computational Graphs in Julia with NeuroDSL Hi everyone, I’d like to share some recent theoretical and systems results from NeuroDSL, a persistent, reactive computational graph framewo…

---

## [How can I significantly speed up conditional Universal Differential Equation training?](https://discourse.julialang.org/t/how-can-i-significantly-speed-up-conditional-universal-differential-equation-training/138126)

<div class="topic-metadata">

**Author:** [@NCCP](https://discourse.julialang.org/u/NCCP)\
**Replies:** 2\
**Last updated:** [July 13, 2026, 3:35pm UTC](https://discourse.julialang.org/t/how-can-i-significantly-speed-up-conditional-universal-differential-equation-training/138126 "2026-07-13T15:35:27Z")

</div>

Hello, I am training a conditional Universal Differential Equation in Julia. This is a regular UDE with an additional trainable parameter as input that is specific for each particle (individual) in the dataset. The mod…

---

## [\[ANN\] DataSplits.jl - data splitting for model selection](https://discourse.julialang.org/t/ann-datasplits-jl-data-splitting-for-model-selection/137274)

<div class="topic-metadata">

**Author:** [@davide.crucitti](https://discourse.julialang.org/u/davide.crucitti)\
**Replies:** 0\
**Last updated:** [May 25, 2026, 10:46am UTC](https://discourse.julialang.org/t/ann-datasplits-jl-data-splitting-for-model-selection/137274 "2026-05-25T10:46:06Z")

</div>

Hi all, I’m pleased to announce DataSplits.jl , a new package for constructing train/test splits and cross-validation folds for model selection. The motivation is simple: when benchmarking models, the split is often as…

---

## [\[ANN\] BetaKDE.jl: Boundary-Corrected Beta Kernel Density Estimation](https://discourse.julialang.org/t/ann-betakde-jl-boundary-corrected-beta-kernel-density-estimation/137057)

<div class="topic-metadata">

**Author:** [@egonmedhatten](https://discourse.julialang.org/u/egonmedhatten)\
**Replies:** 0\
**Last updated:** [May 9, 2026, 10:55pm UTC](https://discourse.julialang.org/t/ann-betakde-jl-boundary-corrected-beta-kernel-density-estimation/137057 "2026-05-09T22:55:52Z")

</div>

I am pleased to announce the release of BetaKDE.jl, a package for boundary-corrected density estimation on the unit interval \[0,1\]. Standard KDE with Gaussian kernels suffers from severe boundary bias when applied to da…

---

## [\[ANN\] NeuralEstimators.jl: Efficient simulation-based inference (SBI) using neural networks](https://discourse.julialang.org/t/ann-neuralestimators-jl-efficient-simulation-based-inference-sbi-using-neural-networks/136917)

<div class="topic-metadata">

**Author:** [@MattSainsbury-Dale](https://discourse.julialang.org/u/MattSainsbury-Dale)\
**Replies:** 3\
**Last updated:** [April 30, 2026, 11:47am UTC](https://discourse.julialang.org/t/ann-neuralestimators-jl-efficient-simulation-based-inference-sbi-using-neural-networks/136917 "2026-04-30T11:47:20Z")

</div>

NeuralEstimators.jl uses neural networks for fast simulation-based inference (SBI) for any model for which simulation is feasible. It supports: Neural posterior estimation (NPE): directly learn the posterior distributi…

---

## [\[ANN\] MichiBoost.jl — Native gradient boosting in Julia](https://discourse.julialang.org/t/ann-michiboost-jl-native-gradient-boosting-in-julia/136811)

<div class="topic-metadata">

**Author:** [@pebeto](https://discourse.julialang.org/u/pebeto)\
**Replies:** 1\
**Last updated:** [April 21, 2026, 10:51am UTC](https://discourse.julialang.org/t/ann-michiboost-jl-native-gradient-boosting-in-julia/136811 "2026-04-21T10:51:21Z")

</div>

Hi everyone, I’d like to share a project I’ve been working on: MichiBoost.jl, a gradient boosting library written 100% in Julia. The story starts with another project I maintain for JuliaAI, MLFlowClient.jl, where I ha…

---

## [Doctoral Researcher, Interdisciplinary Music Research, University of Jyväskylä, Finland](https://discourse.julialang.org/t/doctoral-researcher-interdisciplinary-music-research-university-of-jyvaskyla-finland/136514)

<div class="topic-metadata">

**Author:** [@mahmah](https://discourse.julialang.org/u/mahmah)\
**Replies:** 0\
**Last updated:** [April 2, 2026, 6:36am UTC](https://discourse.julialang.org/t/doctoral-researcher-interdisciplinary-music-research-university-of-jyvaskyla-finland/136514 "2026-04-02T06:36:17Z")

</div>

Doctoral Researcher - Interdisciplinary Music Research (MUSICOTAS Project) The Department of Music, Art and Culture Studies of the University of Jyväskylä is currently seeking to recruit a Doctoral Researcher for a 3-yea…

---

## [Improving the speed for the forward solve of a Universal Differential Equation (UDE)](https://discourse.julialang.org/t/improving-the-speed-for-the-forward-solve-of-a-universal-differential-equation-ude/130583)

<div class="topic-metadata">

**Author:** [@Ashima\_Kalathingal](https://discourse.julialang.org/u/Ashima_Kalathingal)\
**Replies:** 21\
**Last updated:** [March 30, 2026, 5:24pm UTC](https://discourse.julialang.org/t/improving-the-speed-for-the-forward-solve-of-a-universal-differential-equation-ude/130583 "2026-03-30T17:24:00Z")

</div>

Hello everyone, I have a UDE here, and I am trying to improve its speed during the forward solve so that the optimization is also faster. Right now optimization part is very slow. Here is a working code you can try out …

---

## [Identical input in Zygote leads to different outputs](https://discourse.julialang.org/t/identical-input-in-zygote-leads-to-different-outputs/135120)

<div class="topic-metadata">

**Author:** [@Chrysoberyl](https://discourse.julialang.org/u/Chrysoberyl)\
**Replies:** 1\
**Last updated:** [January 19, 2026, 12:27am UTC](https://discourse.julialang.org/t/identical-input-in-zygote-leads-to-different-outputs/135120 "2026-01-19T00:27:54Z")

</div>

In this script, the forward pass has no error: using GNNGraphs, GraphNeuralNetworks, NNlib, Flux graph = GNNHeteroGraph( Dict( (:A, :a, :B) =\> (\[1, 2\], \[3, 4\]), (:B, :a, :A) =\> (\[1\], \[2\]), ); …

---

## [CUDA Warning about freeing DeviceMemory](https://discourse.julialang.org/t/cuda-warning-about-freeing-devicememory/135042)

<div class="topic-metadata">

**Author:** [@Chrysoberyl](https://discourse.julialang.org/u/Chrysoberyl)\
**Replies:** 1\
**Last updated:** [January 15, 2026, 7:37am UTC](https://discourse.julialang.org/t/cuda-warning-about-freeing-devicememory/135042 "2026-01-15T07:37:09Z")

</div>

I’m using Flux.jl for machine learning. When I run training, I got this error (seems to be generated from compiled code in Zygote) ERROR: LoadError: CUDA error: an illegal memory access was encountered (code 700, ERROR\_…

---

## [\[ANN\] Breakout.jl - A simple Breakout clone for fun and reinforcement learning on internal game state](https://discourse.julialang.org/t/ann-breakout-jl-a-simple-breakout-clone-for-fun-and-reinforcement-learning-on-internal-game-state/134872)

<div class="topic-metadata">

**Author:** [@rajgoel](https://discourse.julialang.org/u/rajgoel)\
**Replies:** 3\
**Last updated:** [January 5, 2026, 11:40pm UTC](https://discourse.julialang.org/t/ann-breakout-jl-a-simple-breakout-clone-for-fun-and-reinforcement-learning-on-internal-game-state/134872 "2026-01-05T23:40:55Z")

</div>

This package provides a Julia implementation of the Breakout game. My motivation for creating this package is to provide an easy to install library providing the Breakout game to get started with reinforcement learning (…

---

## [Machine Learning and Deep Learning Course with Julia](https://discourse.julialang.org/t/machine-learning-and-deep-learning-course-with-julia/134890)

<div class="topic-metadata">

**Author:** [@rajgoel](https://discourse.julialang.org/u/rajgoel)\
**Replies:** 1\
**Last updated:** [January 5, 2026, 4:13pm UTC](https://discourse.julialang.org/t/machine-learning-and-deep-learning-course-with-julia/134890 "2026-01-05T16:13:47Z")

</div>

I created a course on Machine Learning and Deep Learning that is using Julia and Flux.jl in particular. I wanted the course to be mathematically precise while providing concise implementations that match the notation use…

---

## [Very slow training of Neural ODE with exogeneous input compared to jax using dense interpolated solution](https://discourse.julialang.org/t/very-slow-training-of-neural-ode-with-exogeneous-input-compared-to-jax-using-dense-interpolated-solution/134557)

<div class="topic-metadata">

**Author:** [@johtok](https://discourse.julialang.org/u/johtok)\
**Replies:** 4\
**Last updated:** [December 15, 2025, 11:09pm UTC](https://discourse.julialang.org/t/very-slow-training-of-neural-ode-with-exogeneous-input-compared-to-jax-using-dense-interpolated-solution/134557 "2025-12-15T23:09:39Z")

</div>

Hi guys! Ive been breaking my neck trying to get a julia alternative to this jax neural ode with exogeneous input script working but without luck! The julia version is painfully slow whereas the jax version runs in a c…

---

## [Correctness Issue in NeuralOperators.jl: Mode truncation in SpectralConv excludes negative low-frequency modes](https://discourse.julialang.org/t/correctness-issue-in-neuraloperators-jl-mode-truncation-in-spectralconv-excludes-negative-low-frequency-modes/134403)

<div class="topic-metadata">

**Author:** [@Azamat](https://discourse.julialang.org/u/Azamat)\
**Replies:** 2\
**Last updated:** [December 9, 2025, 8:26am UTC](https://discourse.julialang.org/t/correctness-issue-in-neuraloperators-jl-mode-truncation-in-spectralconv-excludes-negative-low-frequency-modes/134403 "2025-12-09T08:26:17Z")

</div>

I was looking at the mode truncation logic in NeuralOperators.jl and have a question about correctness. Link: NeuralOperators.jl/src/transform.jl at 39f8a3c6dc974e711c8de8a8fde804e096098157 · SciML/NeuralOperators.jl · …

---

## [\[ANN\] ChenSignatures.jl — Path signatures in Julia](https://discourse.julialang.org/t/ann-chensignatures-jl-path-signatures-in-julia/134361)

<div class="topic-metadata">

**Author:** [@aleCombi](https://discourse.julialang.org/u/aleCombi)\
**Replies:** 0\
**Last updated:** [December 4, 2025, 5:44pm UTC](https://discourse.julialang.org/t/ann-chensignatures-jl-path-signatures-in-julia/134361 "2025-12-04T17:44:22Z")

</div>

Path signatures in Julia I am excited to share ChenSignatures.jl, a Julia package for computing path signatures and log-signatures. What are signatures? The signature of a path X : \[0,T\] \\to \\mathbb{R}^d is the sequence…

---

## [Best options for Graph Neural Network integration with Flux](https://discourse.julialang.org/t/best-options-for-graph-neural-network-integration-with-flux/133368)

<div class="topic-metadata">

**Author:** [@AriMarkowitz](https://discourse.julialang.org/u/AriMarkowitz)\
**Replies:** 5\
**Last updated:** [October 24, 2025, 7:15am UTC](https://discourse.julialang.org/t/best-options-for-graph-neural-network-integration-with-flux/133368 "2025-10-24T07:15:42Z")

</div>

Hello! I built a library that utilizes GraphNeuralNetworks.jl and Flux.jl, but the GraphNeuralNetworks.jl tests are currently failing in Julia 1.12 (and the same failure is causing my custom library to crash when used).…

---

## [Dense Matrix sparse binary vector product](https://discourse.julialang.org/t/dense-matrix-sparse-binary-vector-product/132833)

<div class="topic-metadata">

**Author:** [@Fabrice\_Rosay](https://discourse.julialang.org/u/Fabrice_Rosay)\
**Replies:** 2\
**Last updated:** [October 7, 2025, 7:28am UTC](https://discourse.julialang.org/t/dense-matrix-sparse-binary-vector-product/132833 "2025-10-07T07:28:01Z")

</div>

Hi, I need to train very shallow networks(2 dense layers) whose inputs are sparse binary vector (i.e. only 0 and 1 entries, batched, it is for NNUE). I tried to write custom kernels for forward and backward pass but the…

---

## [\`NeuralPDE.jl\`: How to impose Dirichlet boundary conditions as hard constraints?](https://discourse.julialang.org/t/neuralpde-jl-how-to-impose-dirichlet-boundary-conditions-as-hard-constraints/132007)

<div class="topic-metadata">

**Author:** [@Sigmund](https://discourse.julialang.org/u/Sigmund)\
**Replies:** 1\
**Last updated:** [September 6, 2025, 10:24pm UTC](https://discourse.julialang.org/t/neuralpde-jl-how-to-impose-dirichlet-boundary-conditions-as-hard-constraints/132007 "2025-09-06T22:24:28Z")

</div>

Im solving a coupled PDE-problem using NeuralPDE.jl, the boundary conditions are now set by the penalization method. Instead I want to apply these as hard boundary constraints, or as an output transformation, as it is d…

---

## [Using Enzyme.jl with Flux: Issues Computing Gradients of a Model with Duplicated Parameters and Mixed Forward/Reverse AD](https://discourse.julialang.org/t/using-enzyme-jl-with-flux-issues-computing-gradients-of-a-model-with-duplicated-parameters-and-mixed-forward-reverse-ad/131135)

<div class="topic-metadata">

**Author:** [@Gianmarco](https://discourse.julialang.org/u/Gianmarco)\
**Replies:** 11\
**Last updated:** [July 29, 2025, 11:23pm UTC](https://discourse.julialang.org/t/using-enzyme-jl-with-flux-issues-computing-gradients-of-a-model-with-duplicated-parameters-and-mixed-forward-reverse-ad/131135 "2025-07-29T23:23:35Z")

</div>

Hi everyone, I’m trying to use Enzyme.jl to compute gradients for a Flux model during training. My goal is to differentiate a custom loss function that combines a regular mean squared error term with an additional gradi…

---

## [Why is the loss function increasing when fitting a line?](https://discourse.julialang.org/t/why-is-the-loss-function-increasing-when-fitting-a-line/130600)

<div class="topic-metadata">

**Author:** [@\_jovian](https://discourse.julialang.org/u/_jovian)\
**Replies:** 2\
**Last updated:** [July 10, 2025, 1:37pm UTC](https://discourse.julialang.org/t/why-is-the-loss-function-increasing-when-fitting-a-line/130600 "2025-07-10T13:37:12Z")

</div>

Hello everyone, I’m following the “Fitting a Line” from the Flux.jl guide. It works as expected with the given data, as well as when modifying the predicted function (e.g. actual(x) = 3x - 1). I was trying to change th…

---

## [Native Julia FID (Fréchet Inception Distance) Computation](https://discourse.julialang.org/t/native-julia-fid-frechet-inception-distance-computation/129798)

<div class="topic-metadata">

**Author:** [@josemanuel22](https://discourse.julialang.org/u/josemanuel22)\
**Replies:** 0\
**Last updated:** [June 11, 2025, 10:00am UTC](https://discourse.julialang.org/t/native-julia-fid-frechet-inception-distance-computation/129798 "2025-06-11T10:00:18Z")

</div>

Is there a relatively simple way to calculate the FID (Fréchet Inception Distance) metric in Julia? Metalhead doesn’t include a pre-trained Inception-v3 model. I know you can try ONNX or PythonCall (though all of those h…

---

## [Estimating parameter and function in an ODE model](https://discourse.julialang.org/t/estimating-parameter-and-function-in-an-ode-model/126109)

<div class="topic-metadata">

**Author:** [@dg.aragones](https://discourse.julialang.org/u/dg.aragones)\
**Replies:** 11\
**Last updated:** [May 15, 2025, 9:50am UTC](https://discourse.julialang.org/t/estimating-parameter-and-function-in-an-ode-model/126109 "2025-05-15T09:50:17Z")

</div>

Hi all, I’m working on an ODE model where I want to infer a parameter μ and a function ϕ(t), and I’m looking for recommendations for tools or approaches in Julia to solve this problem. My dataset is small, with just 7 d…

---

## [\[pre-ANN\] Differentiable FDTD for inverse design in photonics, acoustics and RF](https://discourse.julialang.org/t/pre-ann-differentiable-fdtd-for-inverse-design-in-photonics-acoustics-and-rf/105405)

<div class="topic-metadata">

**Author:** [@pxshen](https://discourse.julialang.org/u/pxshen)\
**Replies:** 54\
**Last updated:** [May 10, 2025, 5:04am UTC](https://discourse.julialang.org/t/pre-ann-differentiable-fdtd-for-inverse-design-in-photonics-acoustics-and-rf/105405 "2025-05-10T05:04:24Z")

</div>

Planning to release a differentiable FDTD package for inverse design in photonics, acoustics and RF. I’ll include examples on designing stacks, gratings and couplers as well as meta-materials and meta-surfaces. The elect…

---

## [Patient Level Prediction in Julia Blog Series](https://discourse.julialang.org/t/patient-level-prediction-in-julia-blog-series/128758)

<div class="topic-metadata">

**Author:** [@TheCedarPrince](https://discourse.julialang.org/u/TheCedarPrince)\
**Replies:** 0\
**Last updated:** [May 6, 2025, 1:42pm UTC](https://discourse.julialang.org/t/patient-level-prediction-in-julia-blog-series/128758 "2025-05-06T13:42:18Z")

</div>

NOTE: JuliaHealth contributor, @kosuri-indu, wrote a great series on Patient Level Prediction Julia workflows! She can’t post links to Discourse so I am posting her work below! Introduction Hello everyone! I’m Kosuri …

---

## [LIBSVM call on remote workers requires waiting](https://discourse.julialang.org/t/libsvm-call-on-remote-workers-requires-waiting/127796)

<div class="topic-metadata">

**Author:** [@alequa](https://discourse.julialang.org/u/alequa)\
**Replies:** 1\
**Last updated:** [April 7, 2025, 1:13pm UTC](https://discourse.julialang.org/t/libsvm-call-on-remote-workers-requires-waiting/127796 "2025-04-07T13:13:46Z")

</div>

Hello, I have been getting a bit crazy on this (now solved) problem. I am running a SVM classification on a remote worker, the LIBSVM is imported under the hood of another module, let’s call it ClassifierModule, so th…

---

## [Inplace implementation for neural networks in Lux.jl](https://discourse.julialang.org/t/inplace-implementation-for-neural-networks-in-lux-jl/126749)

<div class="topic-metadata">

**Author:** [@Yang-yang](https://discourse.julialang.org/u/Yang-yang)\
**Replies:** 1\
**Last updated:** [March 12, 2025, 1:26am UTC](https://discourse.julialang.org/t/inplace-implementation-for-neural-networks-in-lux-jl/126749 "2025-03-12T01:26:26Z")

</div>

Hi everyone, I want to know if using an in-place version of the Lux layers is better. I noticed a related pull request https://github.com/LuxDL/Lux.jl/pull/463, but I don’t know why this pull request was canceled. Sinc…

---

## [Lux + Enzyme and Zygote + NeuralODE, segmentation fault](https://discourse.julialang.org/t/lux-enzyme-and-zygote-neuralode-segmentation-fault/123645)

<div class="topic-metadata">

**Author:** [@vleon1234](https://discourse.julialang.org/u/vleon1234)\
**Replies:** 6\
**Last updated:** [March 3, 2025, 10:26pm UTC](https://discourse.julialang.org/t/lux-enzyme-and-zygote-neuralode-segmentation-fault/123645 "2025-03-03T22:26:40Z")

</div>

Hi all, I’m using Julia v1.11.2, and installed the used packages on 12/6 (last Friday), so I assume I have the most recent package versions. I’ve been following along the SciML tutorials for Neural ordinary differentia…

---

## [\[ANN\] LearnAPI.jl 1.0: General API for ML/statistics](https://discourse.julialang.org/t/ann-learnapi-jl-1-0-general-api-for-ml-statistics/126089)

<div class="topic-metadata">

**Author:** [@ablaom](https://discourse.julialang.org/u/ablaom)\
**Replies:** 1\
**Last updated:** [February 19, 2025, 9:30pm UTC](https://discourse.julialang.org/t/ann-learnapi-jl-1-0-general-api-for-ml-statistics/126089 "2025-02-19T21:30:01Z")

</div>

This is the first official and stable release of LearnAPI.jl, a new general API for machine learning and statistics. This is not a general ML toolbox but aims to support toolbox meta-algorithms, such as cross-validation,…

[Next page](https://discourse.julialang.org/tag/machine-learning/259.md?match_all_tags=true&page=1&tags%5B%5D=machine-learning)