What types of problems is ML good for? correct answers - Problems that require lots of hand-tuning and long list of rules
- Problems that are too complex and no traditional solution
- Changing environment and need to adapt to new data
Getting insights from large amount of data
Supervised L...
Machine Learning Exam 1
What types of problems is ML good for? correct answers - Problems that require lots of
hand-tuning and long list of rules
- Problems that are too complex and no traditional solution
- Changing environment and need to adapt to new data
Getting insights from large amount of data
Supervised Learning correct answers - labels created by a human
- classification problems(predict a label)
-regression problems(predict a numeric value)
Unsupervised Learning correct answers "Any learning technique that has as its
purpose to group or cluster items, objects, or individuals"
- dimensionality reduction
-clustering
-visualizations
Semi-supervised learning correct answers training data includes a few desired outputs
-only some data is labeled
Batch learning correct answers - must be trained using all available data
- takes long time to process
- retrained from scratch for updated data
Reasons for lower learning rate correct answers - prevent against attacks from outside
actors
-can potentially overshoot the optimal solution
Instance-base learning correct answers -compares new problem instances to ones
seen in training
- does not generalize the problem
Types of Bad Data correct answers 1. insufficient quantity of training data
2. Non-representative training data
3. Poor Quality Data
4. Irrelevant Features
Sampling noise correct answers error associated with sampling a small dataset
sampling bias correct answers large portion of data is not representative due to
sampling method
, Poor Quality Data attributes correct answers - full of errors
- missing data
-outliers
-noise from measurements
Underfitting correct answers when a model is too simple, both training and test errors
are large
- more training data does not help
Testing set correct answers evaluates your model for generalization error
validating set correct answers used for tuning of hyperparameters
Cross-validation correct answers The process by which a second sample group is
given a test to ensure it is applicable to more than one group
- final test set is heldout
No Free Lunch Theorem correct answers if you make no assumptions then there is no
reason to prefer one model over any other, need to evaluate all of them
8 Steps of a ML Project correct answers 1. Look at big picture
2. get the data
3. discover and visualize the data to gain insights
4. prepare the data
5. select a model and train the data
6. fine-tune your model
7. present your solution
8. launch, monitor and maintain system
Mean absolute error correct answers - corresponds to the L1 norm
Root mean square error correct answers Corresponds to L2 norm
- more sensitive to outliers
Why not just use the normal equation that directly minimizes the loss function? correct
answers - inverting a matrix is O(n^3) where n = # features
- grows linearly with the number of samples in the training set
Stochastic Gradient Descent correct answers - picks a random sample and computes
gradients based upon that sample
- extremely fast but random in nature
The benefits of buying summaries with Stuvia:
Guaranteed quality through customer reviews
Stuvia customers have reviewed more than 700,000 summaries. This how you know that you are buying the best documents.
Quick and easy check-out
You can quickly pay through credit card or Stuvia-credit for the summaries. There is no membership needed.
Focus on what matters
Your fellow students write the study notes themselves, which is why the documents are always reliable and up-to-date. This ensures you quickly get to the core!
Frequently asked questions
What do I get when I buy this document?
You get a PDF, available immediately after your purchase. The purchased document is accessible anytime, anywhere and indefinitely through your profile.
Satisfaction guarantee: how does it work?
Our satisfaction guarantee ensures that you always find a study document that suits you well. You fill out a form, and our customer service team takes care of the rest.
Who am I buying these notes from?
Stuvia is a marketplace, so you are not buying this document from us, but from seller HopeJewels. Stuvia facilitates payment to the seller.
Will I be stuck with a subscription?
No, you only buy these notes for $13.49. You're not tied to anything after your purchase.
