The Basic Concepts of Machine Learning gaunthan Posted on Oct 14 2017 ? Machine Learning ? ## Definition(s) > - Arthur Samuel (1959). Machine Learning: Field of study that gives computers the ability to learn without being explicitly programmed. > - Tom Mitchell (1998) Well-posed Learning Problem: 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. ## Categories ### Supervised Learning > Given a data set and the "correct answer", try to predict a "correct" answer for new data. So we give the machine some data, and tell it what is the answer. We hope the machine can learn from those data, and eventually can give us a "correct answer" for our new input data. Supervised Learning problems can divided into two categories: - Regression: if the output value is continuous - Classification: if the output value is discrete Predicting the price of a house is much more likely a regression problem, but distinguishing a person in a photo is male or female should be a classification problem. ### Unsupervised Learning > Given a data set, and just let the machine itself to learn from the data, which allows us to approach problems with little or no idea what our results should look like. With unsupervised learning there is no feedback based on the prediction results. Unsupervised Learning can divided into two categories: - clustering: grouping data - non-clustering: The "Cocktail Party Algorithm" 赏 Wechat Pay Alipay Gradient Descent Linux 文本操作技巧总结
