Learning with Different Output Space Y

More Binary Classification Problems

例如：

• credit approve/disapprove
• email spam/non-spam
• patient sick/not sick
• advertisement profitable/not profitable
• answer correct/incorrect

Multiclass Classification

例如：

• written digits 0,1,...,9
• pictures apple,orange,strawberry
• email spam,primary,social,promotion,update

Regression

例如：

• patient features how many days before recovery
• company data stock price
• climate data temperature

Structured Learning

• sentencestructure(class of each word)
• protein data protein folding
• speech data speech parse tree
  Mini summary
  binary classification:
  multiclass classification:
  regression:
  structured learning: = structures

Learning with Different Data Label

Supervised Learning(every with corresponding )

Unsupervised Learning( without ,clustering,a challenge but useful problem)

• articles topics
• consumer profiles consumer groups
  unsupervised learning :diverse,with possibly very different performance goals

Semi-supervised(with some )

• face images with a few labeled ⇒ face identifier (Facebook)
• medicine data with a few labeled ⇒ medicine effect predictor
semi-supervised learning: leverage unlabeled data to avoid ‘expensive’ labeling

Reinforcement Learning(a very 'different' but natural way of learning)

learning with 'partial/implicit information'(often sequentially)
比如说，你教小狗‘sit down’，但是它并不会真的‘sit’，但是它会学到‘sit is good’。
因此，可以说，reinforcement: implicit by goodness()
Mini summary
supervised learning:all
semi-supervised:some
unsupervised:no
reinforcement learning:implicit by goodness

Learning with Different Protocol

Batch Learning(Batch Supervised multiclass classification:learning from all known data)

• batch of (email,spam?)spam filter
• batch of(patient,cancer?)concer classifier
• batch of patient datagroup of patients

Online Learning(hypothesis 'improves' through receiving data instances sequentially)

online spam filter,with sequentially:

1. observe an email
2. predict spam status with current
3. receive 'desired label ' from user,then update with()

Active learning(Learning by 'Asking')

当输入一个时，算法不知道对应的，然后向目标函数query the of chosen ，这就是Active learning :improve hypothesis with fewer labels(hopefully)by asking questions strategically
Mini summary
batch:all known data
online:sequence(passive)data
active:strategically-observed data

Learning with Different Input Space X

Concrete Features(each dimension ofrepresents 'sophisticated physical meaning')

• (size,mass)for coin classification
• customer info for credit approval
• patient info for cancer diagnosis

Raw Features(often need human or machines to convert to concrete ones)

• Digit Recognition Problem:featuresmeaning of digit(simple physical meaning,thus more difficult for ML than concrete features)
• image pixels
• speech signal

Abstract Learning(again need features'conversion/extraction/construction')

• rating prediction problem
• student ID in tutoring system
• advertisement ID in online ad system
  Mini summary
  concrete:sophisticated(and related) physical meaning
  raw:simple physical meaning
  abstract:no(or little)physical meaning