Explore Courses Blog Tutorials Interview Questions
0 votes
in Data Science by (17.6k points)

Recently i was doing the Machine Learning course at Coursera by Prof. Andrew Ng. After doing this course i have understand the basics of Machine Learning Algorithms, but i have the following questions:

  • Where can i find the Real world Machine Learning use case examples?

  • What tools or framework are used in Industry/Production for Machine
    Learning projects?

  • How Machine Learning models are used or deploy in production?

  • How to become Data Scientist? Or What should i do next?

Any suggestion,books,courses or tutorial links will be highly appreciated.

1 Answer

0 votes
by (41.4k points)
edited by

Here are some real world machine learning use case examples:

1.Spam Filtering:Most of the Spam filtering techniques are based on text categorization methods.Thus, filtering spam turns out to be classification problem.So, supervised Machine Learning techniques is used to filter the email spam messages.

2.Netflix Recommendation:It uses unsupervised Machine Learning technique.It classifies and shows the content as per users likings.

3.Speech Recognition:It is majorly used for voice user interface and voice searches.It firstly recognizes the spoken words and then converts it into text.

4.Image Recognition:It is used to classify or recognize images.It is also used for face detection in an image.

Tools or framework that are used in Industry:

Machine Learning:

  • Python(Sci-kit learn)
  • R (mostly used in academia nowadays)
  • GraphLab
  • Spark MLlib
  • Apache Mahout

Deep Learning:

  • Tensorflow and Keras
  • Pytorch
  • DeepLearning4j
  • Mxnet

 How Machine Learning models are used or deploy in production?

For production, you have to first build a model, validate & evaluate that model, then the model is finally deployed as web/rest service to be used by other applications/services. Deploying a machine learning model depends on number of factors such as-

  • How often you will retrain your model?
  • Is the model trained offline? Or are you deploying an online learning model?
  • How would you test your newer version of the model? - A/B testing or Bandit variation.
  • Along with other generic things - latency, throughput, data input/output format etc.

There are some cloud-based machine learning service provider like Azure ML( BigML( etc, where you can upload your dataset and after that do some data processing, train and evaluate your machine learning model and then finally deploy it as web service in the cloud.

Also all major cloud platform nowadays provide  machine learning platform, where we can build our own model, after that we can evaluate them and then finally deploy it in the cloud. It gives more flexibility to build the model with almost all major machine learning or deep learning frameworks, and as per requirement gives the flexibility to deploy.

If you want to learn Machine Learning and Deep Learning thoroughly then you must follow Intellipaat's tutorial for beginners.

Thinking of getting a master's degree in Data Science? Enroll in the Masters in Data Science in Philippines!

Browse Categories