Machine Learning-[1] Overview
1.1 Machine learning and artificial intelligence, deep learning
1.1.1 The relationship between machine learning, artificial intelligence, and deep learning
- Machine learning is a way to realize artificial intelligence
- Deep learning is a method of machine learning developed
1.1.2 What can machine learning and deep learning do?
There are many application scenarios of machine learning, which can be said to penetrate into various industries. Various scenarios in medical, aviation, education, logistics, e-commerce and other fields.
- Used in mining and prediction fields:
- Application scenarios: store sales forecast, quantitative investment, advertisement recommendation, enterprise customer classification, SQL statement security detection classification...
- Used in the image field:
- Application scenarios: street traffic sign detection, face recognition, etc.
Used in the field of natural language processing:
- Application scenarios: text classification, sentiment analysis, automatic chat, text detection, etc.
At present, it is important to master some skills such as machine learning algorithms, and solve problems from a certain business area.
1.2 What is machine learning
1.2.1 Definition:
Machine learning is to automatically analyze and obtain a model from historical data , and use the model to predict unknown data.
1.2.2 Explanation:
- We people summarize the laws from a large amount of daily experience. When facing new problems, we can use the laws summarized in the past to analyze the actual situation and adopt the best strategy.
Obtain rules from historical data? What is the format of these historical data?
1.2.3 Data set composition
- Structure: characteristic value + target value
Note:
- For each row of data we can call it a sample .
- Some data sets can have no target value:
1.3 Classification of machine learning algorithms
1.3.1 Classification of machine learning algorithms
- Supervised learning (prediction)
- Definition: Input data is composed of input characteristic value and target value. The output of a function can be a continuous value (called regression), or the output can be a finite number of discrete values (called classification).
- Classification k-nearest neighbor algorithm, Bayesian classification, decision tree and random forest, logistic regression, neural network
- Regression linear regression, ridge regression
- Unsupervised learning
- Definition: The input data is composed of input characteristic values.
- Clustering k-means
1.3.2 Examples
(1) Classification problem
Feature value: picture of cat/dog; target value: cat/dog-category
(2) Regression problem
Characteristic value: each attribute information of the house; target value: house price-continuous data
(3) Unsupervised learning
Feature value: each attribute information of the character; target value: none
1.4 Machine learning development process
1.5 Introduction to learning framework and materials
Several issues need to be clarified:
(1) Algorithm is the core, data and calculation are the foundation
(2) Find the correct location
Algorithm design of most complex models is done by algorithm engineers, and we
- Analyze a lot of data
- Analyze specific business
- Apply common algorithms
- Feature engineering, parameter adjustment, optimization
- What should we do?
- Learn to analyze problems, the purpose of using machine learning algorithms, what tasks do you want the algorithm to accomplish
- Master the basic ideas of algorithms and learn to solve problems with corresponding algorithms
- Learn to use libraries or frameworks to solve problems
At present, it is important to master some skills such as machine learning algorithms, and solve problems from a certain business area.
1.5.1 Machine Learning Libraries and Frameworks
1.5.2 Books
1.5.3 Small improvements (but not required)
