Find Jobs
Hire Freelancers

Artificial neural network regression on (Nsample, None, 6) -> (Nsample, 3) datasets

$250-750 USD

Закрито
Опублікований about 6 years ago

$250-750 USD

Оплачується при отриманні
In this job, you're asked to use machine learning to fit a dataset of shape (Nsample, None, 6) -> (Nsample, 3). Code for generating the dataset is provided given in [login to view URL], together with an attempted solution that failed. The idea / intuition / bigger picture / scenario / real-life meaning of the dataset is provided in project.jpg. Sorry for my mediocre English / Machine Learning / Upwork vocabulary. ---------------------------------------------------------------------------- Here's a description of the 'bigger picture' of the dataset. The Coulomb's law says that force between 2 electrical charges is inversely proportional to the square of the distance between them. Imagine you're Coulomb, and you are asked to rediscover that law using Machine Learning. You have the three-dimensional distance between 2 electrical charges, a vector with shape (3), and the force, a vector of shape (3). You collect the force data on many different three-dimensional distances. You get a dataset of shape (Nsample, 3) -> (Nsample, 3). You use straightforward multi-layer perceptron to fit this dataset and are successful. Imagine you're Coulomb and asked to use ML to regress the force-distance law again. But this time, you are bad at experiments, so whenever you try to make 2 electrically charged bodies, you end up making 1000-2000 of them. You can still measure the force on an electrical charge, but this force results not from a pair of electrical charges, but 1000-2000 pairs SUMMED together! What's worse, 1000-2000 is a VARIABLE range, maybe 1001 for one run and 1500 for another! So, for each sample, you have 1000-2000 three-dimensional distances (None,3), and a total force (3). You collect the force data on many such systems and end up with a dataset of shape (Nsample, None, 3) -> (Nsample, 3). What should you do now? That is this project's question. It is definitely doable - Coulomb did it using mathematics, so we sure can do it using ML regression. A minor point: - Imagine the three-dimensional distances is 6 dimensional. Thus a (Nsample, None, 6) -> (Nsample, None, 3) dataset. I want you to study this because it's harder. Coulomb did it using math, so we should be able to do it using ML. ---------------------------------------------------------------------------- My only criterion of success is accuracy. I'd say 5-6% relative RMSE error? You can either use my code for generating dataset. Alternatively, if you know what Coulomb's law is and understand the foregoing idea, you can roll your own code; but you should use the system size specified in my code. Too small a system and the question is too easy. I have even included my solution to this question. It works, but the accuracy is liked <50%. That's why I need an ML expert who had some experience and expertise, instead of a half-ass programmer like myself whose only qualification is "knows how to write Tensorflow code".
ID проекту: 16313121

Про проект

16 пропозицій(-ї)
Дистанційний проект
Активність 6 yrs ago

Хочете заробити?

Переваги подання заявок на Freelancer

Вкажіть свій бюджет та терміни
Отримайте гроші за свою роботу
Опишіть свою пропозицію
Реєстрація та подання заявок у проекти є безкоштовними
16 фрілансерів(-и) готові виконати цю роботу у середньому за $583 USD
Аватарка користувача
I have read your project details. I have to ask a few questions. Can you please message me via chat so we can discuss all the details to elicit all the requirements and hence start the development? I will showcase all the skills and my experience for this project over the chat. Please message me so we can resume this discussion. Can you provide me all the functional/Non-functional requirements via a document?
$555 USD за 10 дні(-в)
5,0 (15 відгуки(-ів))
6,8
6,8
Аватарка користувача
As a person with Masters in Computational Electromagnetics, I can thoroughly understand your problem. A solution can be provided in Python, and a suitable neural network model will be provided. ANN Performance metrics and visualization aids will be provided wherever suitable. Further details on the road map is possible after initial contact.
$555 USD за 10 дні(-в)
5,0 (13 відгуки(-ів))
4,7
4,7
Аватарка користувача
I m good at using NN for structured data. I can achieve this. I have written several blogs over ML and have expertise. Im applyin deep learning to my startup product. Accuracy is all the matters. I will start providing accurate solutions gradually.
$750 USD за 10 дні(-в)
5,0 (4 відгуки(-ів))
4,3
4,3
Аватарка користувача
A proposal has not yet been provided
$1 000 USD за 10 дні(-в)
5,0 (1 відгук)
3,0
3,0
Аватарка користувача
Dear Sir, Nice to meet you. I read the project description and have done several project in machine learning. i can complete project in 7 days with limited budget and times. for more info ping me.
$555 USD за 10 дні(-в)
2,5 (3 відгуки(-ів))
3,5
3,5
Аватарка користувача
Hello, I am a data scientist with 1+ year of experience in neural networks, predictive modelling, analytics. I have worked on building neural networks using various libraries like tensorflow, scikit-learn, etc. I am highly interested in working on this project. I look forward to hear from you. Thank you
$555 USD за 10 дні(-в)
5,0 (1 відгук)
0,8
0,8
Аватарка користувача
A proposal has not yet been provided
$333 USD за 15 дні(-в)
0,0 (0 відгуки(-ів))
0,0
0,0
Аватарка користувача
I have relevant experience and knowledge of neural network for this project. Also, I have worked with imaging data which is 3-dimensional data like the project requirements.
$833 USD за 20 дні(-в)
0,0 (0 відгуки(-ів))
0,0
0,0

Про клієнта

Прапор UNITED STATES
Cambridge, United States
0,0
0
На сайті з лют. 16, 2018

Верифікація клієнта

Дякуємо! Ми надіслали на вашу електронну пошту посилання для отримання безкоштовного кредиту.
Під час надсилання електронного листа сталася помилка. Будь ласка, спробуйте ще раз.
Зареєстрованих користувачів Загальна кількість опублікованих робіт
Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)
Copyright © 2024 Freelancer Technology Pty Limited (ACN 142 189 759)
Завантажуємо для перегляду
Дозвіл на визначення геолокації надано.
Ваш сеанс входу закінчився, і сеанс було закрито. Будь ласка, увійдіть знову.