You've landed at the right place. oDesk is now Upwork. Learn about the new platform.

Machine Learning Jobs

33 were found based on your criteria {{ paging.total | number:0 }} were found based on your criteria

show all
  • Hourly ({{ jobTypeController.getFacetCount("hourly") | number:0}})
  • Fixed Price ({{ jobTypeController.getFacetCount("fixed") | number:0}})
show all
only
only
only
show all
only
only
only
only
only
show all
only
only
only
Looking for the Team App?
Download the New Upwork Team App
Fixed-Price - Intermediate ($$) - Est. Budget: $800 - Posted
List of URLs: lakorn.guchill.com www.seriesubthai.tv www.kodhit.mobi cuptv.com www.startclip.com cn.upyim.com www.jengmak.com www.songdee.com th.hao123.com www.friv.com newsupdate.todayza.com diply.com tvshow.guchill.com www.subthaiseries.com www.tunwalai.com www.yumzap.com www2.adintrend.com devian.tubemate.home lakorn.guchill.com www.kodhit.mobi cuptv.com www.jengmak.com Step 1 Review the list of URL’s above, mine the top 1000 pages from that URL by using a crawler. Step 2 Extract terms from each of the these web pages that are mined Step 3 Determine if the terms from these web pages, match terms from the entertainment list or match elements from the news list. (Fill in the attached worksheet) Step 4 For each site create a new worksheet and repeat process
Skills: Machine learning Data Analytics Data scraping Web scraping
Fixed-Price - Intermediate ($$) - Est. Budget: $30 - Posted
I have 2 sets of data - a FIT and TEST data. I ran each one of them through the Linear Regression classifer in WEKA 3.6, under 3 methods: M5 method, Greedy Method, and No Attribute Selection. I also ran the sets under the Decision Stump classifier. I need to analyze the outputs between the different methods as well as compare the two sets to each other, based on the following criteria that is spit out: Correlation coefficient Mean absolute error Root mean squared error Relative absolute error Root relative squared error
Skills: Machine learning Data mining Statistics Weka
Fixed-Price - Intermediate ($$) - Est. Budget: $150 - Posted
I'd like to use Google's TensorFlow (deep learning neural network) to generate new content for me. I have about a 150 emails from a 10 year span. I'd like to use Google's Tensor Flow to generate/predict what these emails may sound like for the next 90 years. This is an experiment into utilizing neural networks. I understand that the information may be garbled. I do not expect a perfect response. I want something that is developed and coded well. I want to use the following batches of information: --> Existing batch of emails which have been condensed into a spreadsheet with certain topics and themes. Freelancer will have access to all emails and their content. --> RSS feeds from a single newspaper (with a filter for a particular topic/s). Freelancer will help identify good keywords for the particular project and use them to 'inform' the neural network. This will help it generate more accurate content. --> One wikipedia page listing content related to emails --> One multi sheet Spreadsheet showing incidents related to emails (not very extensive) What I need is a piece of software to connect to Google's TensorFlow to generate this content based upon all of this information. As I continue to get more emails (around 1 per month) and the wiki pages and other content sources update I'd like to be able to 'feed' it into Tensor flow to increase its accuracy. Somebody recently did this with episodes of Friends (http://www.thedailybeast.com/articles/2016/01/20/meet-the-robot-writing-friends-sequels.html) A good quote from the article was: "It's quite simple - It works by predicting the next letter to follow a given sequence of letters, and the predictions are determined by what it learned about language." Feel free to message me, we can discuss this in length. The freelancer is expected to put together a sensible structure for Tensorflow. His/her work will be reviewed by another coder who is familiar with neural networks/tensor flow.
Skills: Machine learning Calculus GitHub Python
Fixed-Price - Expert ($$$) - Est. Budget: $3,500 - Posted
We are looking to have a computer vision expert create a very specific .NET/Mono compatible library for us to use in an application we are creating. This will include (either entirely from scratch or using the help of open source, commercial friendly libraries): - Implementing a very performant rotation/scale invariant template matching routine, and training routine for it. - Implementing geometry detection (size, location, rotation) of circles and rectangles. - Implementing camera calibration routines to calibrate cameras based on known grids or shapes, and applying that calibration to the other routines. - Various other routines as you determine necessary to meet the requirements outlined in the attached document. If these tasks are things you feel you can excel at then please see the attached document which outlines the deliverables for this project, as well as the acceptable languages and required platforms. Please DO NOT bid on this project if you have not read the attached document. Please have a portfolio or references to show your experience with customized computer vision routines and algorithms. You will have direct and prompt answers to any questions from the developer of both the application that will use this library and the machine that it is being used for. An extremely detailed document of use cases for each routine can also be provided once hired. Unlimited sample images can be provided to order from the machine this will be used with. We would like to find someone who can pursue this aggressively, with an ideal deadline of 30 days, but more would be considered for the right candidate. PLEASE NOTE: Bids above and below the budget given will still be seriously considered based on experience, ability to dedicate a large amount of time, communication skills, etc.
Skills: Machine learning .NET Framework Algorithm Development C#
Fixed-Price - Expert ($$$) - Est. Budget: $100 - Posted
We have built a model that predicts "score" based on 120 variables using a data set of 60,000 customers. The current model gives a weighted kappa of 0.65, and we need to bring it up to 0.72. We need your quick help to optimize the Python algorithm that we built. If you are interested, message me and we will send over the code and the data set we are working on.
Skills: Machine learning Predictive Analytics Python Scripting
Fixed-Price - Expert ($$$) - Est. Budget: $200 - Posted
c++ or c# library (dll with source code) that provides a function or method that predicts a process variable. The dataset model for the process can be agreed upon to produce the highest accuracy and the minimum error in prediction. The solution should be based on machine learning algorithms most likely regression (two-class classification can also be considered).
Skills: Machine learning Artificial Intelligence Predictive Analytics
Looking for the Team App?
Download the New Upwork Team App
Fixed Price Budget - ${{ job.amount.amount | number:0 }} to ${{ job.maxAmount.amount | number:0 }} Fixed-Price - Est. Budget: ${{ job.amount.amount | number:0 }} Open to Suggestion Hourly - Est. Time: {{ [job.duration, job.engagement].join(', ') }} - Posted
Skills: {{ skill.prettyName }}
Looking for the Team App?
Download the New Upwork Team App