Relevant projects to help COVID19. let’s act together
Jeremy just advised to check mask fit by verifying it’s making it impossible to smell something with a strong odor. Beware asnomia (loss of smell) is a possible Covid-19 symptom, so do check you’re able to smell without the mask before you perform this test.
Thank you so much for continuing to perform this service during this horrific time. We all appreciate it, so much.
A famous actor from India: Shah Rukh Khan (SRK) also made a fun(ny) video spreading awareness about the virus . He too has mentioned the important of masks towards the end.
You can check out the questionnaire solutions over here (in progress):
Does the question “How many cats are in this picture?” count as classification or regression?
Here is a great crowd sourcing site in partnership with Harvard business school and Boston Children’s (unfortunately US info only)
I don’t think I’ve seen a counting task being done with either classification or regression.
The way I’d frame this would be as an object detection problem where the model puts a bounding box around each subject. And then you count the number of bounding boxes.
Just want to point out that currently we are still discussing chapter 1, which you can read here
It’s a particular type of regression, because the number of cats is an integer while normally regression problems deal with continuous variables, but it’s still regression.
You could make this into a classification problem if you were to label examples as “one”, “two”, “three”, “many” and then teach the model to recognize those situations as classes.
If there is overfitting, I guess there must be underfitting as well. I guess that means the the predictions are not accurate enough. Is that right?
I’ve heard people describe overfitting as training error being below validation error. Does this rule of thumb end up being roughly the same as yours (validation error increasing)?
Is k-fold cross-validation a way to avoid validation set overfitting? Should it be used systematically if yes?
Yes, under-fitting just means that your predictions are not as accurate as they could be. “accurate enough” is subjective.
Yep underfitting also exists and is defined as:
when a statistical model or machine learning algorithm cannot adequately capture the underlying structure of the data
Typing Jeremy’s response as this is important. As you start overfitting, your training loss will continue to get better, but your validation loss will start to go up. It won’t start to get better, it will start to go worse. As we’ll see, this is not necessarily a bad sign in itself. The important thing to look at is your metric getting worse, not your loss function getting worse.
It is a good technique for that, but it’s also expensive to run. If your model takes days to train, training 10 times is going to be painful. So in my opinion you have to use your judgement on when to use it. But if you have the possibility and it’s not too painful, then it’s probably a good idea to run it.
the reverse question – if training loss is more than validation loss – is the model underfitting ?