neural-networks Lecture 1 Quiz

关闭

Lecture 1 Quiz

已通过

6/6 得分（ 100%)

测验通过！

返回第 1 周课程

让您的成就得到认可。 “课程证书帮助您得到求职所需的认可，教学内容帮助您” 掌握工作所需技能。您不仅能提升自己的价值，而且能让自己的价值得到认可。” - Peter B.，美国，软件开发人员

展示你的成就！获取课程证书！ US$ 29 USD  

正确

1 / 1 分

1. 

We often don't know how much data we will need in order for a learning system to generalize well from training data to test data on a given task.

True or false: when choosing how much data to give to a learning system in order to make it generalize well, we need to make sure that we don't give it too much data.

True

False

正确回答 

正确

1 / 1 分

2. 

Data can change over time, in particular we might observe different input/output relationships. In order to account for this we can adapt our learning system to the new data by, for example, training on new examples.

If the relationship between inputs and outputs for old examples has not changed, how can we prevent a neural network from forgetting about the old data?

Prevent the system from changing the weights too much.

正确回答 

Ignore the issue and hope that everything will be OK.

正确回答 

Train two networks, one for old data and one for new data.

正确回答 

The problem with this is that we would not know which network to use for a test case.

Train on a mix of old and new data.

正确回答 

正确

1 / 1 分

3. 

Which of the following are good reasons for why we are interested in unsupervised learning?

It allows us to learn from vast amounts of unlabelled data.

正确回答 

It can be used to learn features that may help with supervised tasks.

正确回答 

It lets us avoid supervised learning entirely.

正确回答 

It allows academic researchers to publish more papers.

正确回答 

正确

1 / 1 分

4. 

Which of the following tasks are neural networks good at?

Recognizing badly written characters.

正确回答 

Neural networks are good at finding statistical regularities that allow them to recognize patterns. They are not good at flawlessly applying symbolic rules or storing exact numbers.

Recognizing fragments of words in a pre-processed sound wave.

正确回答 

Neural networks are good at finding statistical regularities that allow them to recognize patterns. They are not good at flawlessly applying symbolic rules or storing exact numbers.

logical reasoning

正确回答 

Storing lists of names and birth dates.

正确回答 

正确

1 / 1 分

5. 

Which number is biggest?

The number of synapes in a human brain.

正确回答 

Neurons come in many different types and sizes with very different numbers of connections. Some cells in your cerebellum make 250,000 connections. Other neurons in the cerebellum are tiny and probably outnumber all of the other neurons in your brain. This type of variation makes it much harder than you might think to estimate the total number of synapses, but neuroscientists generally estimate about 100 trillion give or take a factor of 10.

The number of milleseconds in a human lifetime.

The number of bits of Random Access Memory (usually just called memory) in a modern laptop.

The Greek national debt in euros

正确

1 / 1 分

6. 

Which of the following facts provides support for the theory that the local neural circuits in most parts of the cortex all use the same general purpose learning algorithm?

If the visual input is sent to the auditory cortex of a newborn ferret, the "auditory" cells learn to do vision.

正确回答 

The fine-scale anatomy of the cortex looks pretty much the same all over.

正确回答 

Brain scans show that different functions (like object recognition and language understanding) are located in different parts of the cortex.

正确回答 

If part of the cortex is removed early in life, the function that it would have served often gets relocated to another part of cortex.

正确回答