# Why is Python, not Julia, still used for most state-of-the-art AI research?

**URL:** <https://discourse.julialang.org/t/why-is-python-not-julia-still-used-for-most-state-of-the-art-ai-research/45896>\
**Category:** Offtopic\
**Tags:** knet, flux, machine-learning, mlj, sciml\
**Created:** [September 1, 2020, 1:49pm UTC](https://discourse.julialang.org/t/why-is-python-not-julia-still-used-for-most-state-of-the-art-ai-research/45896 "2020-09-01T13:49:21Z")\
**Posts on this page:** 1\
**Showing post:** 63

<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:** [May 25, 2021, 8:03pm UTC](https://discourse.julialang.org/t/why-is-python-not-julia-still-used-for-most-state-of-the-art-ai-research/45896/63 "2021-05-25T20:03:28Z")

</div>

> [@ToucheSir](#):
>
> What I’m saying is a lot of ML research follows this order:
> 
> 1. Make it work  
> […]  
> Currently, Julia’s ML/DL ecosystem is at a disadvantage

AI, even ML, is more the deep learning (DL) or neural networks and I would like to know where we’re behind that really matters, do the right nr. 1. We’re behind infrastructure-wise (only?) with scaling to really large [NLP] (neural) models, but I’m not sure it matters too much as the trend is working smarter not harder, in NLP and other neural networks.

The goal should be one-shot or few-shot learning, and probably smaller/different models.

DL may be a dead end, but I think more likely something else is needed, and DL can be part of an AI.

What I see we should be replicating (or I would like to know if Julia more ideal for), is e.g. non-DL:

A.  
[https://science.sciencemag.org/content/350/6266/1332](https://science.sciencemag.org/content/350/6266/1332)

> The model represents concepts as simple programs that best explain observed examples under a Bayesian criterion. On a challenging one-shot classification task, the model achieves human-level performance while outperforming recent deep learning approaches.

B.  
@DrChainsaw, while there is NAS-related, e.g.:

> **[GitHub - DrChainsaw/NaiveNASflux.jl: Your local Flux surgeon](https://github.com/DrChainsaw/NaiveNASflux.jl)**
>
> Your local Flux surgeon. Contribute to DrChainsaw/NaiveNASflux.jl development by creating an account on GitHub.

there’s also newer:: [Neural Architecture Transfer](http://hal.cse.msu.edu/papers/neural-architecture-transfer/)  
From the video: “NAT is consistently more efficient (3x-9x) than EfficientNet, across various datasets without losing accuracy.”

> Neural architecture search (NAS) has emerged as a promising avenue for automatically designing task-specific neural networks. […]  
> we propose Neural Architecture Transfer (NAT) to overcome this limitation […]  
> A pre-trained supernet is iteratively adapted while simultaneously searching for task-specific subnets. We demonstrate the efficacy of NAT on 11 benchmark image classification tasks ranging from large-scale multi-class to small-scale fine-grained datasets. In all cases, including ImageNet, NATNets improve upon the state-of-the-art under mobile settings

[https://arxiv.org/pdf/2105.09491.pdf](https://arxiv.org/pdf/2105.09491.pdf)

> benchmarks show that Retentive R-CNN significantly outperforms state-of-the-art methods on overall performance among all settings as it can achieve competitive results on few-shot classes and **does not degrade the base class performance at all**. Our approach has demonstrated that the long desired never-forgetting learner is available in object detection.

[https://arxiv.org/pdf/2006.10738.pdf](https://arxiv.org/pdf/2006.10738.pdf)

> Table 5: **Low-shot generation** results. With only **100** (Obama, Grumpy cat, Panda), **160** (Cat), or **389** (Dog) training images, our method is on par with the transfer learning algorithms that are pre-trained with **70,000** images.

> [@ANN: NaiveNASlib, NaiveNASflux, NaiveGAflux: Tools for network surgery and neural architecture search](https://discourse.julialang.org/t/ann-naivenaslib-naivenasflux-naivegaflux-tools-for-network-surgery-and-neural-architecture-search/31283):
>
> Hi All, I have made a trio of packages for neural architecture search, mostly because I fell in love with the language and couldn’t think of anything more useful to do which wasn’t already done (and maybe a little bit because I’m oddly amused by the thought of a computer doing crazy stuff while I sleep). The first member is [GitHub - DrChainsaw/NaiveNASlib.jl: Relentless mutation!!](https://github.com/DrChainsaw/NaiveNASlib.jl) Despite NAS being part of the name, it does not do any architecture search. In fact, it does not even do neural n…

---

_[View the full topic](https://discourse.julialang.org/t/why-is-python-not-julia-still-used-for-most-state-of-the-art-ai-research/45896)._