Skip to main content

Machine Learning

Introduction​

Machine learning is a powerful technology that is behind various applications such as chatbots, predictive text, language translation apps, personalized content suggestions on Netflix, and personalized social media feeds. It also powers autonomous vehicles and medical diagnosis systems based on images. In fact, machine learning is so ubiquitous in modern artificial intelligence deployments that the terms "machine learning" and "artificial intelligence" are often used interchangeably or ambiguously.

What is machine learning?​

Machine learning is a subfield of artificial intelligence that enables computers to learn without explicit programming, allowing them to perform tasks such as image recognition, language translation, and personalized recommendations.

Machine learning is a subfield of artificial intelligence, which is broadly defined as the capability of a machine to imitate intelligent human behavior. Artificial intelligence systems are designed to perform complex tasks in a way that is similar to how humans solve problems. The goal of AI is to create computer models that exhibit "intelligent behaviors" like humans, such as recognizing visual scenes, understanding natural language text, or performing physical world actions. Machine learning is one method used to achieve this goal, defined by AI pioneer Arthur Samuel as "the field of study that gives computers the ability to learn without explicitly being programmed." [1]

Subcategories of machine learning​

Supervised​

Supervised machine learning models are trained with labeled data sets, enabling the models to learn and become more accurate over time. For example, an algorithm might be trained with pictures of dogs and other things, all labeled by humans, allowing the machine to learn how to identify pictures of dogs on its own. Supervised machine learning is the most common type used today.

Unsupervised​

In unsupervised machine learning, a program searches for patterns in unlabeled data, allowing it to discover trends or patterns that people may not be explicitly looking for. For instance, an unsupervised machine learning program can analyze online sales data to identify different types of clients making purchases.

Reinforcement​

Reinforcement machine learning trains machines through trial and error to take the best action by establishing a reward system. This type of learning can train models to play games or train autonomous vehicles to drive by telling the machine when it made the right decisions, which helps it learn over time what actions it should take.

Lectures​

Advanced Learning​

Books​

  1. The Hundred-Page Machine Learning Book by Andriy Burkov
  2. Machine Learning For Absolute Beginners by Oliver Theobald
  3. Machine Learning for Hackers by Drew Conway and John Myles White
  4. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow by Geron Aurelien
  5. Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville

Resources​

References​

  1. https://mitsloan.mit.edu/ideas-made-to-matter/machine-learning-explained
  2. https://en.wikipedia.org/wiki/Reinforcement_learning
  3. https://www.ibm.com/topics/supervised-learning