Applying Convolutional Neural Network

$30-150 USD

Closed

Posted

over 7 years ago

$30-150 USD

Paid on delivery

I am in the process to implement 'Convolutional Neural Network' using Tensor-Flow (Python lib). My input data is graphical (Example Show in [login to view URL]) and for each input data I'll provide 04 graphs. All 04 graphs represent one feature but in different domains. The number of labels for each set of 04 graphs is 15 (Example of 14 Data-sets is shown in [login to view URL]). I'm new to CNN and want this project to be implemented in Python. I'm in the process to acquire data nowadays and need a freelancer to train the data such that whenever I provide these four set of graphs for a single feature, I should get the respective labels/concepts with least error. Kindly provide me answer of the following questions while carefully applying bid to the said project. 1) Provide me a clear example of a similar job you have done in the past? 2) Do you have any recommendations in changing the labels before starting the project (I mean if you require me to increase or decrease the number of labels or to make amendments in the data/labels)? Note: It should be noted that I have GTX 1080 GPU. I can provide online access to my system if the freelancer don't exhibit the said facility.

Artificial Intelligence

Python

Project ID: 12995980

About the project

11 proposals

Remote project

Active 7 yrs ago

Looking to make some money?

Email address

Benefits of bidding on Freelancer

Set your budget and timeframe

Get paid for your work

Outline your proposal

It's free to sign up and bid on jobs

11 freelancers are bidding on average $160 USD for this job

@srajbr

Hello, Instead of providing all four graphs in a single file, 4 different files will be much better. Also, instead of graphs if you can get the values which represent the graph its far more better. If you want to stick with graphs will time/distance series be the same for all graphs. For the output labels, I will need a list of all the possible values it can have for each 15 values. Regards, Samiran

$166 USD in 7 days

5.0

(5 reviews)

4.0

@pbq

1. The similar task is of course the classic MNIST digits recognition project. 2. You have to digitize the 4 input graphs into numbers. e.g. digitize according x and y axiels. 3. it is noticed that some labels are same for all inputs, you can remove such labels for more efficient training. Your budget is bit low considering the time to be spent on it. Regards, Michael

$300 USD in 15 days

4.9

(6 reviews)

4.0

@shashwatv1

-Used CNN for digit recognizing problem (very similar to your problem. predict label for an image) -Code available on Kaggle. My username is SUICIDESQUAD -Scholar of best institute in India(IIT Delhi) -Have expertise in Machine Learning

$35 USD in 3 days

5.0

(2 reviews)

2.8

@vijaykumariitkgp

Hi, this is Vijay. I worked on many projects in machine learning. Recently I worked on CNN and rnn projects. I'm assuring you I will complete your works.

$140 USD in 20 days

0.0

(0 reviews)

0.0

@seankahn

A clear Example of a job I have done in past : In Chemical Engineering, reactor temperature and reactant concetration is being plotted against . There is NO information known on the error/oulier distribution. task is to find similar events in time. To do this, the python script attempts to fit the graph, via multiple types of fitting (exponential, polynomial ... ) , uses covex hull method to detect outliers - and then classifies the period of interest . Such a classification would look like : timestep : 26 to 59 features identified : {[26,37] convex, increasing}, {[37,38] spike, up}, {[38,42] noise CANTFIT} , {[42,58] concave, decreasing} Then, this is fed into a fuzzifier, and a weighting is generated. That is then fed into a ANN. Then, you can feed the ANN with a longer time series or more serieses - it will then cut out regions in the time series which match your goal. So far I don't have any recommendations. But I am interested in discussing it out more with you. I am aalso available on skype: sean_s_con

$100 USD in 10 days