Machine Learning

Question 1

What is Machine Learning

Answer 1

Machine learning studies algorithm and representation that allow machines to improve performance on their tasks from experience

Question 2

What can ML do?

Answer 2

• Assist you at home
• Image captioning
• Estimate prices of your ride (e.g. Careem, Uber)
• Translate
• Predict stock prices
• Monitor unusual behavior (Traffic Cameras)
• Find good search results

Question 3

What is learning?

Answer 3

The ability to use previous data to perform future actions

Question 4

What is supervised learning?

Answer 4

The machine experiences a series of inputs(x1,x2,x3,x4,…) along with the correct labels(y1,y2,y3,y4,…) and it aims to learn a mapping so that it can make a correct prediction for a new input

Question 5

What is Unsupervised Learning?

Answer 5

• Algorithms that learn patterns from unlabelled data.
• The machine builds a model that can be used for various tasks such as reasoning, decision making,predicting things,communicating, etc

Question 6

Generative vs. Discriminative Models

Answer 6

• Generative Models try to model how the input data was generated
• Discriminative models try to learn the decision boundary between different classes of data

Question 7

Reinforcement Learning

Answer 7

• Agent’s utility is defined by the reward function.
• It interacts with the environment and receives feedback in the form of rewards or punishments.

Question 8

Different tribes in AI/ML

Answer 8

• Symbolists
• Bayesians
• Analogizers
• Connectionists
• Evolutionaries

Question 9

What are 5 Big Ideas in Artificial Intelligence

Answer 9

1.Perception: Computers percieve the world through sensors.
2. Representation and Reasoning:Agents maintain representations of the world and use them for reasoning.
3. Learning: Computers can learn from data.
4. Natural Interaction: Intelligent agents require many kinds of knowledge to interact naturally with humans.
5. Social Impact: AI can impact society in both positive and negative ways.