Week 9 UAS

Question 1

Types of feedback in Learning?

Answer 1

1. Supervised learning: correct answers for each example
2. Unsupervised learning: correct answers not given
3. Reinforcement learning: occasional rewards

Question 2

Simplest form of supervised learning?

Answer 2

Inductive Learning, learn a function from examples

Question 3

Feed-forward vs recurrent?

Answer 3

– Feed-forward: outputs only connect to later layers
• Learning is easier
– Recurrent: outputs can connect to earlier layers or same layer
• Internal state

Question 4

Neural Networks Evaluation

Answer 4

• Advantages
– Handle errors well
– Graceful degradation
– Can learn novel solutions

• Disadvantages
– “Neural networks are the second best way to do anything”
– Can’t understand how or why the learned network works
– Examples must match real problems
– Need as many examples as possible
– Learning takes lots of processing
• Incremental so learning during play might be possible

Question 5

5 analysis for NLP?

Answer 5

1. Morphological Analysis
   e.g. in-to-nat-ion, en-ter-tain-ment, en-ter-tain-er
2. Syntax Analysis (Grammar or structure)
   e.g. I see the statue
3. Semantic Analysis
   = the meaning of a sentence
   e.g. I saw the boy in the park with a telescope
4. Discourse Integration
   = close relation (cohesion) between sentence or between paragraph
5. Pragmatic Analysis
   = the meaningfulness or the logic in a sentence
   e.g. this world is made of green cheese

Question 6

2 parts of NLP?

Answer 6

1. Natural language understanding
   = try to understand every human language
2. Natural language generation
   = deciding what to say

Question 7

What is prior probability and posterior probability?

Answer 7

prior (unconditional) probability is probability without seeing other events (independent).

posterior (conditional) probability is probability that depends on other events.