Santiago Profile picture
3 Apr, 14 tweets, 3 min read
25 True|False machine learning questions that are horrible for interviews but pretty fun to answer.

Most importantly: they will make you think and will keep your knowledge sharp.

These are mostly beginner-friendly.

1. A "categorical feature" is a feature that can only take a limited number of possible values.

2. Precision is a performance metric that defines a classification model's ability to identify only relevant samples.

3. Recall is a performance metric that defines a classification model's ability to identify all relevant samples.

4. One-hot encoding is an excellent solution to transform categorical features with high cardinality.

5. The F1 Score is a metric defined as the harmonic mean of precision, recall, and accuracy.

6. As the number of hidden layers increases in a neural network, its capacity also increases.

7. Initializing a neural network's weights with zero is our best bet to allow the network to converge.

8. As the dropout ratio used in a neural network increases, the network's capacity also increases.

9. Stochastic Gradient Descent is the proper technique to use when the full dataset doesn't fit in memory.

10. Batch Normalization is an efficient backpropagation technique that allows neural networks to learn.

11. Gradient Descent is an algorithm used to minimize overfitting in neural networks.

12. Having high bias means the model is too simple and can't capture many features during the training phase. This is also known as overfitting.

13. Softmax is an activation function that always returns the input value if it's positive and zeroes otherwise.

14. In neural networks, an activation function's most essential role is to decide whether a unit (or neuron) should fire.

15. Using a learning rate that's too low will cause the training process to be very slow.

16. ReLU (or Rectified Linear Unit) is an activation function that, given an input vector, generates an output where the sum of the values in the vector is equal to one.

17. Your model's accuracy can't be used as a loss function to train a neural network.

18. An autoencoder is a neural network that automatically learns by using its inputs as the expected output.

19. Convolutional neural networks are translation invariant.

20. Autoencoders are one of the most popular supervised learning methods.

21. The type of problem where you need to classify the input into a single class is called "multi-class classification."

22. Dropout is an excellent regularization technique that speeds the training process.

23. A neural network with a single layer is capable of approximating any function.

24. Leaky ReLU is an activation function that allows the passing of small-sized negative values if the network's input value is less than zero.

25. Bagging is the concept of splitting a dataset and randomly placing it into bags for training a model.

If you want to check your answers, take a look at this picture. Every row contains 5 of the answers, with 1 = True and 0 = False.

If you found this helpful, follow me, and let's keep spreading machine learning content all over Twitter!

• • •

Missing some Tweet in this thread? You can try to force a refresh

Keep Current with Santiago

Santiago Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!


Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @svpino

4 Apr
Learning a new language is not an obvious decision, especially when you are just starting in the industry.

Here are 10 frequently asked questions about learning Python 🐍. Hopefully, these give you the answers you are looking for.

1. Can I learn Python for free?

Yes. There are multiple YouTube videos, tutorials, and courses that will teach you Python for free.

But if you can afford it, I'd recommend you find a good MOOC that gives you some structure.

↓ 1/10
2. Is Python hard to learn?

It's not, especially compared with other languages out there.

That being said, becoming an expert is a life-long journey.

But one year of experience is more than enough for you to do whatever you decide to do.

↓ 2/10
Read 13 tweets
2 Apr
You want to build a function to retrieve a value from a sequential list of unordered elements.

What would be the best approach?
You can assume that the size of the list is unknown.

Oh, sorry if this was confusing.

By "sequential list" I meant that elements come one after the other in memory. Think of a regular array.

It doesn't mean that you can't access elements out of order.

Read 4 tweets
2 Apr
When we start with machine learning, we learn to split our datasets in testing and training by taking a percentage of the data.

Unfortunately, this practice could lead to overestimating the performance of your model.

Imagine a dataset of pictures with people doing signals with their hands.

As we were told, we take 70% of the images for training and the remaining 30% for testing. We are careful to maintain the original ratio between classes.

How could this be a problem?

There are a lot of pictures of Mary in the dataset. She is showing different signals with her hands.

Also Joe. He was a model too that participated in the creation of the dataset.

Read 10 tweets
1 Apr
Pick one of these two.

They will both help you write better Python.
Both of these are great books to open from time to time and read an individual section.

They give you bite-sized tips and advice that you can incorporate immediately into your work.

Replace 30 minutes of Netflix every week with some reading.

Read 4 tweets
1 Apr
One way to reduce overfitting is by automatically augmenting your data.

Think about this: if you had an infinite number of samples, you would never overfit because your model would see every possibility out there.

↓ 1/7
Data augmentation is a way to generate more data using an existing dataset.

For example, by applying small transformations to existing images, you can generate many useful variations.

Here are some examples of possible variations that you could generate for an image:

▫️ Zoomed-in
▫️ Randomly cropped
▫️ Horizontally shifted
▫️ Horizontally flipped
▫️ Slightly rotated
▫️ More illuminated

Read 8 tweets
31 Mar
Coming soon, in Python 🐍 3.10: "Pattern Matching."

Looks sick!
No, this is not a switch statement. Pattern matching is very different.

With patterns, you get a small language to describe the structure of the values you want to match. Look at one of the examples to see how you can match an element of a tuple.
You can use patterns to match even more complex structures. You can nest them. You can have redundancy checking.

Pattern matching is a feature you can find in functional languages.

It's excellent that Python decided to add it! I'm really excited about it.
Read 4 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!