機器學(xué)習(xí)

甘肅 張亞萍

機器學(xué)習(xí)是人工智能的核心，它用數(shù)據(jù)或以往的經(jīng)驗來優(yōu)化計算機程序的性能，而不需要通過人工干預(yù)對其進行明確編程。該技術(shù)旨在使計算機更智能、更高效。

主題語境：科技 篇幅：333詞 建議用時：6分鐘

Machine learning is a way of teaching computers to do tasks. In the past, computers relied on detailed, step-by-step instructions written by people to do anything. But with machine learning, computers pick up new skills on their own, using examples or experience. This makes machine learning a powerful form of artificial intelligence (AI) is the ability of a machine to think or learn like a person. AI systems power many kinds of machines—from smartphones to robots.

There are a few types of machine learning. The most common is supervised (監(jiān)督)learning. In this method, a computer is fed lots of labelled training data. For instance, it may look at many photos of dogs. Each photo might be labelled with the dog's breed. By studying those photos, the computer learns what each breed looks like. Then, the computer can pick out dog breeds in new, unlabelled photos. The more data the computer studies,the better it gets at its task.

Another important kind of machine learning is reinforcement (強化) learning. Using this type of learning is sort of like training your dog to do a trick. The computer learns to achieve some goals by interacting with its environment.When the computer makes a choice that brings it closer to its goal, it gets a virtual reward. Through trial and error, the computer learns to make better choices. This type of machine learning has helped computers master difficult games. It has also been used to teach self-driving cars how to get around.

Machine learning has helped create technology all around us. It powers language translators and search engines. When your streaming services recommend new shows you might like, that's machine learning at work. Machine learning systems also organize posts in social media feeds.They even help diagnose diseases.In many ways,the problem-solving power of machine learning is reshaping the world.

Machine learning and other types of artificial intelligence are behind computer-made artwork.

Reading Cheak

1.What is machine learning about?

A.Computers replacing people's thinking.

B.People teaching computers to do tasks.

C.People learning with the help of computers.

D.Computers learning new skills on their own.

2.What does a computer do in supervised learning?

A.It is put into labelled training data.

B.It is fond of photos of dogs.

C.It is able to recognize a new breed.

D.It is asked to perform tasks like a dog.

3.Which of the following belongs to reinforcement learning?

A.Selling self-driving cars.

B.Designing computer games.

C.Getting abilities from mistakes.

D.Acquiring knowledge by playing tricks.

4.What is the author's attitude towards the future of machine learning?

A.Negative.

B.Positive.

C.Doubtful.

D.Worrying.

Language Study

Ⅰ. Difficult sentence in the text

When the computer makes a choice that brings it closer to its goal, it gets a virtual reward.當(dāng)計算機做出使其更接近目標(biāo)的選擇時，它會獲得虛擬獎勵。

【點石成金】本句是一個主從復(fù)合句，句中，When 引導(dǎo)時間狀語從句，that 引導(dǎo)定語從句，修飾先行詞a choice。

Ⅱ. Text-centered chunks

rely on 依靠

pick up（不費力地）學(xué)會；獲得

for instance 例如；比如

look like 看起來像；看上去像

pick out（經(jīng)仔細研究）找出；辨別出

get around 傳播；各處走動

at work 起作用