Machines: Are They Helpful Or Too Much Trouble?

Machines: They are useful or too much a problem. The history of the industrial revolution and various stages are very important. Population growth and capital, credit and business expansion are one of those stages. The role of entrepreneurs, workers and inventions in promoting production is another stage. Textiles, coal, transportation and public services are starting to become valuable to people. The social influence is that women and children work in factories and mines. Severe living environment, crowded room, and many diseases.

Fortunately, there are several things that you can move and adapt without troubles. Plug converter can be used for kitchen tools such as lamp, telephone, answering machine, radio, computer, printer, fax, fitness equipment, humidifier, coffee maker, mixer, mixer, food processor

To my surprise, the entire article was written without mentioning machine learning. The problem introduced in this article is the reason for machine learning. It is used to create very complex software that makes rule-based methods successful. In machine learning, we start with the final product and "growth" software and train it to adapt to its environment. What is present in the software is a model that needs to be executed, not an explicit instruction that mechanically indicates the behavior. Code generation is the goal of machine learning and the mathematics necessary for its success is achieved through iteration and convergence, not explicitly designed by programmers.

I often ask how to start machine learning. In most cases, it is difficult for people to understand the math behind everything. I must admit that I do not like mathematics. Mathematics is an abstract way to describe things. I think that the description method of machine learning is too abstract to understand.

You can not drill down on all machine learning topics. There are lots to learn, this field is growing rapidly. After mastering basic concepts, I concentrate on specific field projects of interest regardless of natural language understanding, computer vision, deep reinforcement learning, robot engineering and other fields. Massachusetts Institute of Technology 18.05, Introduction of Probability and Statistics, by Jeremy Orloff and Jonathan Bloom. It provides intuition for stochastic reasoning and statistical reasoning. This helps to understand how the machine thinks, plan and make decisions. All statistics: a concise course of statistical reasoning written by Larry Wasserman. A primer on statistical data. stone