Machine Learning For Dummies. John Paul Mueller
Читать онлайн книгу.
target="_blank" rel="nofollow" href="https://www.csee.umbc.edu/courses/471/papers/turing.pdf">
https://www.csee.umbc.edu/courses/471/papers/turing.pdf). In this paper, Turing explored the idea of how to determine whether machines can think. Of course, this paper led to the Imitation Game involving three players. Player A is a computer and Player B is a human. Each must convince Player C (a human who can’t see either Player A or Player B) that they are human. If Player C can’t determine who is human and who isn’t on a consistent basis, the computer wins.
A continuing problem with AI is too much optimism. The problem that scientists are trying to solve with AI is incredibly complex. However, the early optimism of the 1950s and 1960s led scientists to believe that the world would produce intelligent machines in as little as 20 years. After all, machines were doing all sorts of amazing things, such as playing complex games. AI currently has its greatest success in areas such as logistics, data mining, and medical diagnosis.
Exploring what machine learning can do for AI
Machine learning relies on algorithms to analyze huge datasets. Currently, machine learning can’t provide the sort of AI that the movies present. Even the best algorithms can’t think, feel, present any form of self-awareness, or exercise free will. What machine learning can do is perform predictive analytics far faster than any human can. As a result, machine learning can help humans work more efficiently. The current state of AI, then, is one of performing analysis, but humans must still consider the implications of that analysis — making the required moral and ethical decisions. The “Considering the Relationship between AI and Machine Learning” section of this chapter delves more deeply into precisely how machine learning contributes to AI as a whole. The essence of the matter is that machine learning provides just the learning part of AI, and that part is nowhere near ready to create an AI of the sort you see in films.
Genetics: Slow learning from one generation to the next
Teaching: Fast learning from organized sources
Exploration: Spontaneous learning through media and interactions with others
Considering the goals of machine learning
At present, AI is based on machine learning, and machine learning is essentially different from statistics. Yes, machine learning has a statistical basis, but it makes some different assumptions than statistics do because the goals are different. Table 1-1 lists some features to consider when comparing AI and machine learning to statistics.
TABLE 1-1: Comparing Machine Learning to Statistics
| Technique | Machine Learning | Statistics |
|---|---|---|
| Data handling | Works with big data in the form of networks and graphs; raw data from sensors or the web text is split into training and test data. | Models are used to create predictive power on small samples. |
| Data input | The data is sampled, randomized, and transformed to maximize accuracy scoring in the prediction of out-of-sample (or completely new) examples. | Parameters interpret real-world phenomena and provide a stress on magnitude. |
| Result | Probability is taken into account for comparing what could be the best guess or decision. | The output captures the variability and uncertainty of parameters. |
| Assumptions | The scientist learns from the data. | The scientist assumes a certain output and tries to prove it. |
| Distribution | The distribution is unknown or ignored before learning from data. | The scientist assumes a well-defined distribution. |
| Fitting | The scientist creates a best fit, but generalizable, model. | The result is fit to the present data distribution. |
Defining machine learning limits based on hardware
Huge datasets require huge amounts of memory. Unfortunately, the requirements don’t end there. When you have huge amounts of data and memory, you must also have processors with multiple cores and high speeds. One of the problems that scientists are striving to solve is how to use existing hardware more efficiently. In some cases, waiting for days to obtain a result to a machine learning problem simply isn’t possible. The scientists who want to know the answer need it quickly, even if the result isn’t quite right. With this in mind, investments in better hardware also require investments in better science. This book considers some of the following issues as part of making your machine learning experience better:
Obtaining a useful result: As you work through the book, you discover that you need to obtain a useful result first, before you can refine it. In addition, sometimes tuning an algorithm goes too far and the result becomes quite fragile (and possibly useless outside a specific dataset).
Asking the right question: Many people get frustrated in trying to obtain an answer from machine learning because they keep tuning their algorithm without asking a different question. To use hardware efficiently, sometimes you must step back and review the question you’re asking. The question might be wrong, which means that even the best hardware will never find the answer.
Relying on intuition too heavily: All machine learning questions begin as a hypothesis. A scientist uses intuition to create a starting point for discovering the answer to a question. Failure is more common than success when working through a machine learning experience. Your intuition adds the art to the machine learning experience, but sometimes intuition is wrong and you have to revisit your assumptions.
https://devblogs.nvidia.com/parallelforall/bidmach-machine-learning-limit-gpus/ and https://towardsdatascience.com/what-is-a-gpu-and-do-you-need-one-in-deep-learning-718b9597aa0d.