Machine Learning Basics

By Konstantinos Chatzilygeroudis, Ioannis Hatzilygeroudis, Isidoros Perikos. Intelligent Computing for Interactive System Design, 2021

346 citations recorded by the source corpus.

coined in 1959 by Arthur Samuel [Samuel 1959], Tom Mitchell [Mitchell 1997] provided a more formal definition: “A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.” ML has be applied to many real-world problems or tasks, like medical diagno­ sis, robotics, recommendation systems, facial recognition, stock prices prediction, and sentiment analysis, with great success. We can divide ML algorithms into three main categories (see Figure 4.1): Machine Learning Basics

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/287ba5bf00d96af1596aaf80c178392a9c4fcc28

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chenhao Tan
2. Vivian Lai
3. Bo Li
4. Han Liu
5. Bowen Zhou
6. Jinfeng Yi
7. Shuai Di
8. Jingen Liu

In Computer Vision and Pattern Recognition

1. Vivian Lai
2. Bo Li
3. Bowen Zhou
4. Shuai Di
5. Jingen Liu
6. Jiquan Pei
7. Bo Liu
8. Jinfeng Yi

In Signal Processing

1. Bo Li
2. Bowen Zhou
3. Jinfeng Yi
4. Chenhao Tan
5. Peng Qi
6. Jinyu Li
7. Tara N. Sainath
8. Khe Chai Sim

Citations in the corpus

• Trustworthy AI: From Principles to Practices (2021, background): “On the one hand, generalization requires that AI systems make predictions on realistic data, even on domains or distributions on which they are not trained [133].”
• Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making (2021, background): “In practice, a critical growing concern is distribution shift [19, 55, 58].”