# What Is Machine Learning?

Machine learning is the study of computer algorithms that can be automatically improved through experience. Machine learning uses big data or past experience to optimize the performance standards of computer programs.

# What Is Machine Learning?

Machine Learning (ML) in simple terms can be defined as the science of getting computers to act and learn without explicit programming to perform those actions. It has become quite popular in recent years, however, the term itself was coined in 1959 by Arthur Samuel who defined Machine Learning as ‘the field of study that gives computers the ability to learn without being explicitly taught’.

A more recent and formal definition of Machine Learning was created by Tom Mitchell and describes it as a well-defined learning problem — ‘A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E.’

Machine Learning usage has become so common that you probably use it many times a day without even knowing it. For example, when you search on Google or Bing or any other search engine, in the background there is a learning algorithm that has learned how to rank pages based on user queries. Similarly, when you see the photodetection feature on different social media applications or see spam filter filtering out bogus/unwanted emails in your mailbox, behind the scene is a Machine learning algorithm that learns and detect faces or spams emails respectively. A more recent technology use case is the advent of self-driving cars.

# What is Machine Learning Platform for AI?

Machine Learning Platform for AI is designed to serve businesses within Alibaba Group, such as Taobao, Alipay, and Amap.com. It enables developers of Alibaba Group to use AI technologies in an efficient, concise, and standard way. Machine Learning Platform for AI was officially released in 2018. It has gained tens of thousands of enterprises and individual developers and has become one of the leading machine learning platforms on the cloud in China.

Machine Learning Platform for AI supports the following underlying computing frameworks:

- Flink, a stream computing framework.
- TensorFlow, an optimized deep learning framework based on open-source TensorFlow.
- Parameter Server, a computing framework that can process hundreds of billions of samples in parallel.
- Spark, PySpark, MapReduce, and other mainstream open-source computing frameworks.

Machine Learning Platform for AI provides the following services:

- Machine Learning Studio: a service for visualized modeling and distributed training.
- Data Science Workshop (DSW): a Notebook-based service for interactive AI research and development.
- AutoLearning: a service for automated modeling.
- Elastic Algorithm Service (EAS): a service that allows you to deploy models as online prediction services.

Machine Learning Platform for AI provides the following benefits:

- Services provided by Machine Learning Platform for AI can be used separately or in combination. Machine Learning Platform for AI provides an all-in-one platform for machine learning. After training data is prepared in Object Storage Service (OSS) or MaxCompute, you can use Machine Learning Platform for AI to streamline all workflows, including data uploading, data preprocessing, feature engineering, model training, model evaluation, and model publishing (to both online and offline environments).
- Machine Learning Platform for AI can be integrated with DataWorks and allows you to process data by using Structured Query Language (SQL), user-defined functions (UDFs), user-defined aggregation functions (UDAFs), and MapReduce. This ensures higher flexibility and efficiency.
- Experiments that are used to train and generate models can be scheduled in DataWorks. You can run scheduled tasks in the staging or production environment. This enables data isolation.

# What is the difference between deep learning and machine learning?

Most work in machine learning is focused on finding efficient algorithms that can take a set of input data and produce from them a set of outputs (“right answers”) based on patterns identified in the input data. For instance, you might give your algorithm input data about sale prices for homes in Melbourne last year, accompanied by data about each house sold, such as its ZIP code, size in square feet, number of bedrooms, and so on. Once you had “trained” your machine learning model on this data, say by providing it with all information *except* house prices and having it learn to predict them, then you could use this model to accurately judge the sale prices of homes that the system had not to seem before.

Where does “deep learning” fit into all this? Deep learning is just one of the many algorithms that have come from the work done in machine learning. You can think of “deep learning” as being one of many tools in machine learning’s toolbox.

Specifically, deep learning is a neural network-based learning technique that uses neural networks composed of many layers of artificial neurons. The “deep” in deep learning refers to the fact that deep learning’s neural networks have many layers. The layers are what makes deep learning, “deep”. The moniker “deep” is often misinterpreted to mean that deep learning is somehow more insightful or powerful than other machine learning techniques. Although it’s a very powerful and flexible technique, it is not necessarily better than the other tools machine learning gives us: it’s one option among many.

# What is the difference between Machine Learning and Artificial Intelligence?

Artificial Intelligence and Machine Learning are used interchangeably by a lot of people but Artificial Intelligence is more like a superset of Machine Learning and is even a wider field in scope. Though it is a bit vague to define Artificial Intelligence (boundaries) as it keeps on changing with the advancement of technology, in simple terms, AI can be defined as a science to make computers behave in a manner that brings them closer to human levels of intelligence and capability. It is quite a broad and vague field in terms of scope but the overall idea is to simulate human intelligence to solve problems or behave in an ‘intelligent’ way, similar to how humans might behave in a given situation. For example, a robot performing certain tasks based on the situation instead of simply performing repetitive tasks (automation) is an example of AI. Thus, Machine learning can be considered a branch or sub-field of AI, serving to achieve the overarching aims of AI.

# Machine Learning Algorithms for Machine Learning Beginners

# Regression Algorithms

In most Machine Learning courses, regression algorithms are the first to be introduced for two reasons:

Regression algorithms are relatively simple, and discussing them allows you to slide easily from statistics on to Machine Learning.

Regression algorithms provide the foundation for some of the powerful algorithms to be discussed late

There are two regression algorithm subtypes: linear regression and logistic regression.

We have already touched on linear regression via the House Price Problem. Let’s figure out how to find the straight line that best fits all the data.

The “least squares” method is used to solve this problem. The thinking behind this method is: to find the line that best represents a set of data; and find the line that most closely follows the observed data points in the data set. Not all of the data points lie exactly along a straight line, so the best fit line is the one with the least deviation from those points. To minimize the deviation, find a straight line that minimizes the sum of the squares of all the distances between the points and the line.

The least-squares method converts an optimization problem into an extreme function value problem. In mathematics, we can find the extreme values of a function by looking at the point where the derivative is 0. However, this method is not suitable for computers because they may fail to solve the problem or the computation may be too intensive.

In computer science, there is a specialized discipline called numerical computation. It strives to increase accuracy and efficiency when computers run various computations. For example, the famous gradient descent method and Newton method are classic numerical computation algorithms. They are also well-suited to find extreme values of functions. The gradient descent method is one of the simplest and most effective methods for solving regression The neural networks and recommendation algorithms to be discussed later have linear regression factors, and the gradient descent method is applied in other algorithms.

Logistic regression algorithms are similar to linear regression algorithms. However, the types of problems addressed by linear regression are different from those addressed by logistic regression. Linear regression deals with numerical problems with final predictions being numbers, such as a house price.

Logistic regression, on the other hand, is used in classification algorithms. The predictions made out of logistic regression are discrete classes like logistic regression is often used to determine a spam email or if a user will click on an advertisement.

In practice, logistic regression simply adds a Sigmoid function to the results computed by linear regression. This function converts the numerical result into a probability between 0 and 1 (images of the Sigmoid function are not very intuitive, but you need to understand that larger values are closer to 1 and smaller values are closer to 0). Next, we make a prediction based on this probability. For example, if the probability is greater than 0.5, we can classify an email as spam or judge a tumor to be malignant.

# Related Blog：

For a better understanding of Machine Learning, please refer to the following:

# Alibaba Cloud PAI: New Features of Alibaba Cloud’s Machine Learning Platform

Step up the digitalization of your business with Alibaba Cloud 2020 Double 11 Big Sale! Get new user coupons and explore over 16 free trials, 30+ bestselling products, and 6+ solutions for all your needs!

This article is based on the speech and the related PowerPoint slides, and covers the following topics:

- PAI overview
- Custom algorithm upload
- DTplus Smart Eco-market
- AutoML2.0 automatic parameter tuning
- AutoLearning

# What is Recommended System Based on Machine Learning? How to Build One?

In this article, Alibaba technical expert Aohai introduces how to establish a simple recommender system based on Machine Learning Platform for AI (PAI) within 10 minutes. This article focuses on four parts: the personalized recommendation process, collaborative filtering algorithm, architecture of the recommender system, and practices.

# Applying Machine Learning to Big Data Processing

This tutorial will discuss the preprocessing aspect of the machine learning pipeline, coving the ways in which data in handled, paying special attention to the techniques of standardization, normalization, feature selection and extraction, and data reduction. Last, this tutorial goes over how you can implement these techniques in a simple way.

# Related Products:

# Machine Learning Platform for AI

Machine Learning Platform for AI provides end-to-end machine learning services, including data processing, feature engineering, model training, model prediction, and model evaluation. Machine Learning Platform for AI combines all of these services to make AI more accessible than ever.

# Related Campaign:

# Challenges and Breakthroughs of Machine Learning

Experts from TensorFlow, NVIDIA, and Alibaba Cloud introduce cutting-edge machine learning technologies.

# Machine Learning Course

# Machine Learning for Beginners — Linear Regression

This course is the first class of the Alibaba Cloud Machine Learning Algorithm QuickStart series, It mainly introduces the basic concept and algorithm principle of linear regression model, as well as the model evaluation metrics, explains and demonstrates a complete process of building linear regression analysis and prediction model in PAI, prepare for the knowledge associate with subsequent machine learning courses.

# Machine Learning Specialty

The Machine Learning Career Path teaches users about end-to-end machine learning services, including data processing, feature engineering, model training, model prediction, and model evaluation. Alibaba Cloud’s Machine Learning Platform combines all of these services to make AI more accessible than ever. Learn how to use this platform through the completion of this learning path.

**Alibaba Tech**

First hand and in-depth information about Alibaba’s latest technology → Facebook: **“Alibaba Tech”**. Twitter: **“AlibabaTech”**.