The Fundamentals of Machine Learning

How would you define Machine Learning?

Machine Learning is the science (and art) of programming computers so they can learn from data.
A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E. Tom Mitchell, 1997

Can you name four types of problems where it shines?

• Machine Learning techniques are better predictors then traditional program
• Machine Learning it can start flagging tag without human intervention
• Another area where Machine Learning shines is for problems that either are too complex for traditional approaches or have no known algorithm.
• Machine Learning can help humans learn

What is a labeled training set?

In supervised learning, the training set you feed to the algorithm includes the desired solutions, called labels

What are the two most common supervised tasks?

A typical supervised learning task is classification.
Another typical task is to predict a target numeric value.

Can you name four common unsupervised tasks?

Clustering
Anomaly detection and novelty detection

What type of Machine Learning algorithm would you use to allow a robot to walk in various unknown terrains?

Reinforcement Learning

What type of algorithm would you use to segment your customers into multiple groups?

Clustering algorithm.
Hierarchical clustering algorithm

Would you frame the problem of spam detection as a supervised learning problem or an unsupervised learning problem?

supervised learning

What is an online learning system?

In online learning, you train the system incrementally by feeding it data instances sequentially, either individually or in small groups called mini-batches.

What is out-of-core learning?

Online learning algorithms can also be used to train systems on huge datasets that cannot fit in one machine’s main memory,this is called out-of-core learning.

What type of learning algorithm relies on a similarity measure to make predictions?

Instance-base learning

What is the difference between a model parameter and a learning algorithm’s hyperparameter?

life_satisfactioin = θ0 + θ1 * GDP_per_capita
θ0 and θ1 are the model parameter.
You can make your model represent any linear function, by tweaking these parameters,
The amount of regularization to apply during learning can be controlled by a hyperparameter.

What do model-based learning algorithms search for? What is the most common strategy they use to succeed? How do they make predictions?

The way to generalize from a set of examples is to build a model of these examples and then use that model to make predictions.

Can you name four of the main challenges in Machine Learning?

Insufficient Quantity of Training Data
Nonrepresentative Training Data
Poor-Quality Data
Irrelevant Features
Overfitting the Training Data
Underfitting the Training Data

If your model performs great on the training data but generalizes poorly to new instances, what is happening? Can you name three possible solutions?

Overfitting
Simplify the model
Gather more training data.
Reduce the noise in the training data

What is a test set, and why would you want to use it?

you train your model using the training set, and you test it using the test set.

What is the purpose of a validation set?

to evaluate several candidate models and select the best one.

What is the train-dev set, when do you need it, and how do you use it?

After the model is trained (on the training set, not on the train-dev set), you can evaluate it on the train-dev set.

What can go wrong if you tune hyperparameters using the test set?

perform well in the test. but perform bad in new data.