Examples of Machine Learning Applications

Examples of Machine Learning Applications

Let’s look at some concrete examples of Machine Learning tasks, along with the techniques that can tackle them:

       i.          Analyzing images of products on a production line to automatically classify them

     ii.          Detecting tumors in brain scans

   iii.          Automatically classifying news articles

   iv.          Automatically flagging offensive comments on discussion forums

     v.          Summarizing long documents automatically

   vi.          Creating a chatbot or a personal assistant

  vii.          Forecasting your company’s revenue next year, based on many performances’ metrics

viii.          Making your app react to voice commands

   ix.          Detecting credit card fraud

     x.          Segmenting clients based on their purchases so that you can design a different marketing strategy for each segment

   xi.          Representing a complex, high-dimensional dataset in a clear and insightful diagram

  xii.          Recommending a product that a client may be interested in, based on past purchases

xiii.          Building an intelligent bot for a game

 

 

       i.          Analyzing images of products on a production line to automatically classify them:

·       This is image classification, typically performed using convolutional neural networks.

     ii.          Detecting tumors in brain scans:

·       This is semantic segmentation, where each pixel in the image is classified (as we want to determine the exact location and shape of tumors), typically using CNNs as well.

   iii.          Automatically classifying news articles:

·       This is natural language processing (NLP), and more specifically text classification, which can be tackled using recurrent neural networks (RNNs), CNNs, or Transformers.

   iv.          Automatically flagging offensive comments on discussion forums:

·       This is also text classification, using the same NLP tools.

     v.          Summarizing long documents automatically:

·       This is a branch of NLP called text summarization, again using the same tools.

   vi.          Creating a chatbot or a personal assistant:

·       This involves many NLP components, including natural language understanding (NLU) and question-answering modules.

  vii.          Forecasting your company’s revenue next year, based on many performances’ metrics:

·       This is a regression task (i.e., predicting values) that may be tackled using any regression model, such as a Linear Regression or Polynomial Regression model, a regression SVM, a regression Random Forest, or an artificial neural network.

·       If you want to take into account sequences of past performance metrics, you may want to use RNNs, CNNs, or Transformers.

viii.          Making your app react to voice commands:

·       This is speech recognition, which requires processing audio samples: since they are long and complex sequences, they are typically processed using RNNs, CNNs, or Transformers.

   ix.          Detecting credit card fraud:

·       This is anomaly detection.

     x.          Segmenting clients based on their purchases so that you can design a different marketing strategy for each segment:

·       This is clustering.

   xi.          Representing a complex, high-dimensional dataset in a clear and insightful diagram:

·       This is data visualization, often involving dimensionality reduction techniques.

  xii.          Recommending a product that a client may be interested in, based on past purchases:

·       This is a recommender system.

·       One approach is to feed past purchases (and other information about the client) to an artificial neural network, and get it to output the most likely next purchase.

·       This neural net would typically be trained on past sequences of purchases across all clients.

xiii.          Building an intelligent bot for a game: 

·       This is often tackled using Reinforcement Learning, which is a branch of Machine Learning that trains agents (such as bots) to pick the actions that will maximize their rewards over time (e.g., a bot may get a reward every time the player loses some life points), within a given environment (such as the game).

·       The famous AlphaGo program that beat the world champion at the game of Go was built using RL.

YouTube Link: https://www.youtube.com/watch?v=KQyRT7mK4eI

Source: Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow by Aurélien Géron