Real Life ML

Last week’s post went over the differences between Machine Learning and Deep Learning. To make it short and sweet, a few pieces of information were purposely left out because they deserve their own spot light.

What was left out?

Examples of how the three types of models that go into ML are used in real life AI systems.

To recap the 4 types of models are:

  1. Supervised Learning

  2. Unsupervised Learning

  3. Semi-Supervised Learning

  4. Reinforcement Learning

How are they used in the real-world?

Supervised Learning

  • Image recognition: Identifying specific objects within an image.

  • Self-driving cars: Recognizing traffic signs and pedestrians in real-time.

  • Product search on e-commerce websites: Identifying items in a user-uploaded image to suggest similar products

  • Speech Recognition: Converting spoken language into text, used in voice assistants like Siri and Alexa.

  • Predictive Analytics: Forecasting future trends, like stock market predictions, weather forecasting, and customer churn prediction.

Unsupervised Learning

  • Customer Segmentation: Grouping customers based on similar behaviors or preferences for targeted marketing.

  • Genetic research: Unsupervised learning can be used for genetic clustering

  • Fraud detection: Useful in revealing unusual data points in datasets that can help uncover events or behaviors that deviate from normal patterns in the data, revealing fraudulent transactions or unusual behavior like bot activity. 

Srmi-Supervised Learning:

  • Co-Training Text Classification: Includes having small dataset of labeled news articles ( politics, sports, technology). Train 2 models, each using different features of the text (one model uses word frequency, the other uses sentence structure). Each model predicts labels for the unlabeled data, and the models use each other's predictions as additional training data.

Reinforcement Learning

  • Robotics: Controlling robots to perform tasks in complex environments, such as warehouse automation and autonomous vehicles.

  • Recommendation Systems: Suggesting products or content to users based on their past behavior, used by platforms like Netflix and Amazon.

It is important to note that ML is a subset of AI that focus on the computational aspects of learning. While AI is a broad field focused on building systems that mimic human thought. ML is a subset of AI that uses algorithms to learn from data and make predictions

Previous
Previous

Models Vs. Algorithms

Next
Next

DL Vs. ML