The productivity opportunities by applying machine learning algorithms in a fab

Machine learning has become a ubiquitous and essential part of business operations. Amazon uses algorithms to nudge their customers to purchase a product they might like. Given a purchase history for a customer and a large inventory of products, identify those products in which that customer will be interested and likely to purchase. A model of this decision process would allow a computer to make recommendations to a customer and motivate product purchases. Machine learning solves problems that cannot be solved by numerical means alone. These algorithms can not only increase an enterprise's internal efficiency, but machine learning algorithms also be used to deepen consumer loyalty. That is to say, machine learning provides potential solutions in all these domains and more, and is set to be a pillar of our future civilization. Of course, machine learning is also very important in a fab because it could help us solve problems including defects selection, image detection, fabrication scheduling rule, and so on. Machine learning builds heavily on statistics. When we train our machine model to learn, we have to give it a statistically representative sample as training data. If the training set isn't representative, we run the risk of the machine learning patterns that are not complete. Then, if the training set is too small, we won't learn enough and may even reach inaccurate conclusions.