Almost multilingual

#2
by TeaCult - opened

People says it is not multilingual but it translates a lot better than many translation neural nets. It was a suprise.
It keeps original terms but do not loose the meaning which is most important chatGPT 3.5 - 4 nllb-3B , google translate , they all loose the meaning while translating.

It is not perfect but seems promising somehow. It was suprising to me.

A Neural-Guided Dynamic Symbolic Network for
Exploring Mathematical Expressions from Data
Wenqiang Li1,2,4 Weijun Li1,3,4,∗ Lina Yu1,3,4,∗ Min Wu1,3,4
Jingyi Liu1,3,4 Yanjie Li1,3,4
1
Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China
2School of Electronic, Electrical and Communication Engineering, University of
Chinese Academy of Sciences, Beijing, China
3School of Integrated Circuits, University of Chinese Academy of Sciences, Beijing, China
4Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and
Computing Technology, Beijing, China
Abstract
Symbolic regression (SR) is a powerful technique for discovering the underlying
mathematical expressions from observed data. Inspired by the success of deep
learning, recent efforts have focused on two categories for SR methods. One is using
a neural network or genetic programming to search the expression tree directly.
Although this has shown promising results, the large search space poses difficulties
in learning constant factors and processing high-dimensional problems. Another
approach is leveraging a transformer-based model training on synthetic data and
offers advantages in inference speed. However, this method is limited to fixed
small numbers of dimensions and may encounter inference problems when given
data is out-of-distribution compared to the synthetic data. In this work, we propose
DYSYMNET, a novel neural-guided Dynamic Symbolic Network for SR. Instead of
searching for expressions within a large search space, we explore DYSYMNET with
various structures and optimize them to identify expressions that better-fitting the
data. With a topology structure like neural networks, DYSYMNET not only tackles
the challenge of high-dimensional problems but also proves effective in optimizing
constants. Based on extensive numerical experiments using low-dimensional
public standard benchmarks and the well-known SRBench with more variables,
our method achieves state-of-the-art performance in terms of fitting accuracy and
robustness to noise.

///////////////////////////////////////////////
Sure, I'd be happy to help! Here's a translation of the paper's abstract into Turkish:

Özet

Symbolik regressiyon (SR) observed data'dan underlying mathematical expressions'u keşfetmek için birçok teknik geliştirilmiştir. Bu çalışmanın ana katılımcıları, daha yüksek boyutlu problemler ve constant factors öğrenmek için neural ağlar veya genetik programlamayı kullanarak expression ağacını aradığı categorilerdir. Bu yaklaşımların birincisi, arama mevkiindeki büyük aralık ve yüksek boyutlu problemlerde çok daha zor olur. İkincisi ise, synthetic veriler ile eğitilen transformer tabanlı bir model kullanarak hızlı tahmin edebilir. Ancak bu yaklaşım, sabit sayısal dimensiyonlarda kiçi olarak kullanılabilir ve veri gelirine uygun şekilde sınıflandırılamayacaktadır. Bu çalışmanın amacı, DYSYMNET'u geliştirmek ve bunu kullanarak SR yöntemlerindeki bu sınırlamaları aşmaktadır.

DYSYMNET, veri gelirine göre daha iyi uyumlu olan ifadeler keşfetmek için çeşitli yapıları ve optimize edilmesini sağlar. Neural ağların topology yapısına benzer şekilde, DYSYMNET yüksek boyutlu problemlerine de daha etkili bir şekilde cevirebilir ve constant faktorlerin optimize edilmesinde de etkileyebilir.

Bu çalışmanın sonuçları, standard veri setlerini kullanarak yapay zeka ile ilgili birçok deneme gerçekleştirilmiştir ve SRBench'te daha fazla değişken olup büyük boyutlu problemlerle karşılaştırılmıştır. Sonuçlar, DYSYMNET'un performansını göstererek state-of-the-art derecede fitted accuracy ve noise ile karşılaştırmalarda daha yüksek birperformans sağlamasını göstermektedir.

Sign up or log in to comment