# Has Julia met your need for AI and ML?

**URL:** https://discourse.julialang.org/t/has-julia-met-your-need-for-ai-and-ml/119818
**Category:** New to Julia
**Created:** [September 24, 2024, 4:44pm UTC](https://discourse.julialang.org/t/has-julia-met-your-need-for-ai-and-ml/119818 "2024-09-24T16:44:11Z")
**Posts on this page:** 1
**Showing post:** 25

<div class="post-metadata">

### Author: ![Palli](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/palli/32/3380_2.png) [@Palli](https://discourse.julialang.org/u/Palli)
#### Post date: [October 6, 2024, 3:01pm UTC](https://discourse.julialang.org/t/has-julia-met-your-need-for-ai-and-ml/119818/25 "2024-10-06T15:01:31Z")

</div>

I think I can confirm Julia is used in all _those_ 7 branches of AI (note each has sub-fields, AI is an enormously big area of study, and Julia would certainly be useful for any possible AI area you can think of including e.g. robotics), except for probably expert systems, because outdated:

> **[Julia reaches 1.0 status, and that might be great news for data science](https://www.linkedin.com/pulse/julia-reaches-10-status-might-great-news-data-science-hidalgo/)**
>
> Just a few weeks ago, the Julia language reached version 1.0.

> DSLs evolved into “expert systems”, and although “expert systems” is pretty much an abandoned line of research nowadays, some of the early success in AI came from them (like the first mathematical theorems proved by a machine) and DSLs are alive and kicking

Domain-specific languages (DSLs) are a big part of Julia, and I would say Julia excellent for them, more so than most other languages.

I wasn’t sure about, but at least found:

> **[GitHub - lucaferranti/FuzzyLogic.jl: Julia package for fuzzy inference](https://github.com/lucaferranti/FuzzyLogic.jl)**
>
> Julia package for fuzzy inference

Is Julia most used for any current AI area (yet)? Probably not, except SciML. At least there is e.g. a book on computer vision:

> **[GitHub - PacktPublishing/Hands-On-Computer-Vision-with-Julia: Hands-On Computer Vision with Julia, published by...](https://github.com/PacktPublishing/Hands-On-Computer-Vision-with-Julia)**
>
> Hands-On Computer Vision with Julia, published by Packt

Natural language processing is where stuff is happening, and such transformer models (that Julia has available) have taken over computer vision too.

One thing not mentioned there is time-series prediction (and analysis) and Julia also good for that, but intriguingly computer vision is also taking over that in the form of transformer models:

[https://deeplearning.fr/visionts-revolutionizing-time-series-forecasting-with-image-based-models/](https://deeplearning.fr/visionts-revolutionizing-time-series-forecasting-with-image-based-models/)

> **[GitHub - Leezekun/ViTST: \[NeurIPS 2023\] The official repo for the paper:...](https://github.com/Leezekun/ViTST)**
>
> \[NeurIPS 2023\] The official repo for the paper: "Time Series as Images: Vision Transformer for Irregularly Sampled Time Series"."

The cutting edge is moving from transformers to e.g. liquid neural networks (they used Python/PyTorch):

> **[From Liquid Neural Networks to Liquid Foundation Models](https://www.liquid.ai/blog/liquid-neural-networks-research)**

There will always be some area where Julia is not yet there, though people are working on this:

> [@Julia implementation of Liquid Neural Networks - anyone wanna help make one?](https://discourse.julialang.org/t/julia-implementation-of-liquid-neural-networks-anyone-wanna-help-make-one/100953):
>
> Following a thread on #machine-learning on Julia slack, i’m interested in putting together a Julia implementation of [“Liquid Neural Networks”](https://cap.csail.mit.edu/sites/default/files/research-pdfs/Robust%20flight%20navigation%20out%20of%20distribution%20with%20liquid%20neural%20networks.pdf). These are time-adaptive neural networks, inspired by neuroscience models, where each neuron’s activity is a differential equation. The synapses are also plastic and continue to adapt after training. I think this is very interesting, and Julia has a great ecosystem for automatic differentiation with differential equations. Anyone interested in teaming toge…

[https://www.science.org/doi/10.1126/scirobotics.adc8892](https://www.science.org/doi/10.1126/scirobotics.adc8892)

I don’t know the difference between liquid neural networks (and Liquid Time-Constant Network) and Liquid State Machines, but I suspect all related and at least I see something in Julia related to that last one:

> ReservoirComputing.jl provides an efficient, modular and easy to use implementation of Reservoir Computing models such as Echo State Networks (ESNs). Reservoir Computing (RC) is an umbrella term used to describe a family of models such as ESNs and Liquid State Machines (LSMs)

---

_[View the full topic](https://discourse.julialang.org/t/has-julia-met-your-need-for-ai-and-ml/119818)._