Machine Learning for Modern Artificial Intelligence
Hsuan-Tien Lin National Taiwan University
June 25, 2019
other versions presented in Academia Sinica
& TWSIAM Annual Meeting
ML for (Modern) AI
Outline
ML for (Modern) AI
ML Research for Modern AI
ML for Future AI
H.-T. Lin (NTU) ML for Modern AI 1/38
ML for (Modern) AI
From Intelligence to Artificial Intelligence
intelligence: thinking and actingsmartly
• humanly
• rationally
artificialintelligence:computersthinking and actingsmartly
• humanly
• rationally
humanly≈smartly≈rationally
—are humans rational? :-)
ML for (Modern) AI
Traditional vs. Modern [My] Definition of AI
Traditional Definition
humanly ≈ intelligently ≈ rationally My Definition
intelligently ≈ easily
is your smart phone ‘smart’? :-)
modern artificial intelligence
=applicationintelligence
H.-T. Lin (NTU) ML for Modern AI 3/38
ML for (Modern) AI
Examples of Application Intelligence
Siri
By Bernard Goldbach [CC BY 2.0]
Amazon Recommendations
By Kelly Sims [CC BY 2.0]
iRobot
By Yuan-Chou Lo [CC BY-NC-ND 2.0]
Vivino
from nordic.businessinsider.com
ML for (Modern) AI
Machine Learning and AI
Easy-to-Use
Acting Humanly Acting Rationally
Machine Learning
machine learning: core behind modern (data-driven) AI
H.-T. Lin (NTU) ML for Modern AI 5/38
ML for (Modern) AI
ML Connects Big Data and AI
From Big Data to Artificial Intelligence
big data
ML
artificial intelligenceingredient tools/steps dish
(Photos Licensed under CC BY 2.0 from Andrea Goh on Flickr)
“cooking” needs many possible tools & procedures
ML for (Modern) AI
Bigger Data Towards Better AI
best route by shortest path
best route by current traffic
best route by predicted travel time
big datacanmake machine look smarter
H.-T. Lin (NTU) ML for Modern AI 7/38
ML for (Modern) AI
ML for Modern AI
big data
ML AI
human learning/
analysis
domain knowledge
(HumanI)
method
model expert system
• human sometimesfaster learneroninitial (smaller) data
• industry: black plum is as sweet as white
often important to leverage human learning, especiallyin the beginning
ML for (Modern) AI
Application: Tropical Cyclone Intensity Estimation
meteorologists can ‘feel’ & estimate TC intensity from image
TC images
ML
estimationintensityhuman learning/
analysis
domain knowledge
(HumanI)
CNN polar
rotation invariance
current weather
system
better than current system & ‘trial-ready’
(Chen et al., KDD 2018) (Chen et al., Weather & Forecasting 2019)
H.-T. Lin (NTU) ML for Modern AI 9/38
ML Research for Modern AI
Outline
ML for (Modern) AI
ML Research for Modern AI
ML for Future AI
ML Research for Modern AI
Cost-Sensitive Multiclass Classification
H.-T. Lin (NTU) ML for Modern AI 11/38
ML Research for Modern AI
What is the Status of the Patient?
?
H7N9-infected cold-infected healthy
• aclassificationproblem
—grouping ‘patients’ into different ‘status’
are all mis-prediction costs equal?
ML Research for Modern AI
Patient Status Prediction
error measure = society cost XXXX
XXXXXX actual
predicted
H7N9 cold healthy
H7N9 0 1000 100000
cold 100 0 3000
healthy 100 30 0
• H7N9 mis-predicted as healthy:very high cost
• cold mis-predicted as healthy: high cost
• cold correctly predicted as cold: no cost
human doctors consider costs of decision;
how about computer-aided diagnosis?
H.-T. Lin (NTU) ML for Modern AI 13/38
ML Research for Modern AI
Our Works
binary multiclass
regular well-studied well-studied
cost-sensitive known(Zadrozny et al., 2003) ongoing(our works, among others)
selected works of ours
• cost-sensitive SVM(Tu and Lin, ICML 2010)
• cost-sensitive one-versus-one(Lin, ACML 2014)
• cost-sensitive deep learning(Chung et al., IJCAI 2016)
why are peoplenot
using thosecool ML works for their AI? :-)
ML Research for Modern AI
Issue 1: Where Do Costs Come From?
A Real Medical Application: Classifying Bacteria
• by human doctors: different treatments⇐⇒ serious costs
• cost matrix averaged from two doctors:
Ab Ecoli HI KP LM Nm Psa Spn Sa GBS
Ab 0 1 10 7 9 9 5 8 9 1
Ecoli 3 0 10 8 10 10 5 10 10 2
HI 10 10 0 3 2 2 10 1 2 10
KP 7 7 3 0 4 4 6 3 3 8
LM 8 8 2 4 0 5 8 2 1 8
Nm 3 10 9 8 6 0 8 3 6 7
Psa 7 8 10 9 9 7 0 8 9 5
Spn 6 10 7 7 4 4 9 0 4 7
Sa 7 10 6 5 1 3 9 2 0 7
GBS 2 5 10 9 8 6 5 6 8 0
issue 2: is cost-sensitive classification really useful?
H.-T. Lin (NTU) ML for Modern AI 15/38
ML Research for Modern AI
Cost-Sensitive vs. Traditional on Bacteria Data
. . . . . .
Are cost-sensitive algorithms great?
RBF kernel
0 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6
OVOSVM
csOSRSVM csOVOSVM csFTSVM
algorithms
cost
.
...Cost-sensitive algorithms perform better than regular algorithm
Jan et al. (Academic Sinica) Cost-Sensitive Classification on SERS October 31, 2011 15 / 19
(Jan et al., BIBM 2011)
cost-sensitivebetter thantraditional;
but why are peoplestill not
using those cool ML works for their AI? :-)
ML Research for Modern AI
Issue 3: Error Rate of Cost-Sensitive Classifiers
The Problem
0.1 0.15 0.2 0.25 0.3
0 0.05 0.1 0.15 0.2
Error (%)
Cost
• cost-sensitive classifier: low cost but high error rate
• traditional classifier: low error rate but high cost
• how can we get theblueclassifiers?: low error rate and low cost
cost-and-error-sensitive:
more suitable forreal-world medical needs
H.-T. Lin (NTU) ML for Modern AI 17/38
ML Research for Modern AI
Improved Classifier for Both Cost and Error
(Jan et al., KDD 2012)
Cost
iris ≈
wine ≈
glass ≈
vehicle ≈
vowel
segment
dna
satimage ≈
usps
zoo
splice ≈
ecoli ≈
soybean ≈
Error
iris
wine
glass
vehicle
vowel
segment
dna
satimage
usps
zoo
splice
ecoli
soybean
now,are people using those cool ML works for their AI? :-)
ML Research for Modern AI
Lessons Learned from
Research on Cost-Sensitive Multiclass Classification
? H7N9-infected cold-infected healthy
1 more realistic (generic) in academia
6=more realistic (feasible) in application e.g. the ‘cost’ ofinputting a cost matrix? :-)
2 cross-domain collaborationimportant
e.g. getting the ‘cost matrix’ fromdomain experts
3 not easy to winhuman trust
—humans are somewhatmulti-objective
H.-T. Lin (NTU) ML for Modern AI 19/38
ML Research for Modern AI
Active Learning by Learning
ML Research for Modern AI
Active Learning: Learning by ‘Asking’
labeling isexpensive:
active learning ‘question asking’
—query ynofchosenxn
unknown target function f : X → Y
labeled training examples ( , +1), ( , +1), ( , +1)
( , -1), ( , -1), ( , -1)
learning algorithm
A
final hypothesis g≈f
+1
active: improve hypothesis with fewer labels (hopefully) by asking questionsstrategically
H.-T. Lin (NTU) ML for Modern AI 21/38
ML Research for Modern AI
Pool-Based Active Learning Problem
Given
• labeled poolDl =n
(featurexn ,label yn(e.g. IsApple?))oN n=1
• unlabeled pool Du=n x˜soS
s=1
Goal
design an algorithm that iteratively
1 strategically querysome˜xs to get associatedy˜s 2 move (x˜s,y˜s)fromDutoDl
3 learnclassifier g(t)fromDl
and improvetest accuracy of g(t) w.r.t#queries
how toquery strategically?
ML Research for Modern AI
How to Query Strategically?
Strategy 1
askmost confused question
Strategy 2
askmost frequent question
Strategy 3
askmost debateful question
• choosingone single strategy isnon-trivial:
0 10 20 30 40 50 60
0.45 0.5 0.55 0.6 0.65 0.7 0.75 0.8
% of unlabelled data
Accuracy
RAND UNCERTAIN PSDS QUIRE
0 10 20 30 40 50 60
0.4 0.5 0.6 0.7 0.8 0.9
% of unlabelled data
Accuracy
RAND UNCERTAIN PSDS QUIRE
0 10 20 30 40 50 60
0.5 0.6 0.7 0.8 0.9 1
% of unlabelled data
Accuracy
RAND UNCERTAIN PSDS QUIRE
application intelligence: how to choose strategy smartly?
H.-T. Lin (NTU) ML for Modern AI 23/38
ML Research for Modern AI
Idea: Trial-and-Reward Like Human
when do humanstrial-and-reward?
gambling
K strategies:
A1, A2, · · · , AK
tryone strategy
“goodness” of strategy asreward
K bandit machines:
B1, B2, · · · , BK
tryone bandit machine
“luckiness” of machine asreward
intelligent choice of strategy
=⇒intelligent choice ofbandit machine
ML Research for Modern AI
Active Learning by Learning
(Hsu and Lin, AAAI 2015)K strategies:
A1, A2, · · · , AK
try one strategy
“goodness” of strategy as reward
Given: K existing active learning strategies for t = 1, 2, . . . , T
1 let some bandit modeldecide strategy Ak to try
2 query the ˜xssuggested by Ak, and compute g(t)
3 evaluategoodness of g(t) asrewardoftrialto update model
only remaining problem: what reward?
H.-T. Lin (NTU) ML for Modern AI 25/38
ML Research for Modern AI
Design of Reward
ideal rewardafter updating classifier g(t) by the query (xnt,ynt):
accuracy ofg(t) ontest set {(x0m,ym0 )}Mm=1
—test accuracyinfeasiblein practice because labelingexpensive more feasible reward: training accuracy on the fly
accuracy of g(t) onlabeled pool {(xnτ,ynτ)}tτ =1
—butbiasedtowardseasierqueries
weighted training accuracyas a better reward:
acc. of g(t) oninv.-prob. weightedlabeled pool n
(xnτ,ynτ,p1
τ) ot
τ =1
—‘bias correction’fromquerying probability within bandit model Active Learning by Learning (ALBL):
bandit +weighted training acc. as reward
ML Research for Modern AI
Comparison with Single Strategies
UNCERTAINBest
5 10 15 20 25 30 35 40 45 50 55 60 0.55
0.6 0.65 0.7 0.75 0.8 0.85 0.9
% of unlabelled data
Accuracy ALBL
RAND UNCERTAIN PSDS QUIRE
vehicle
PSDSBest
5 10 15 20 25 30 35 40 45 50 55 60 0.5
0.55 0.6 0.65 0.7 0.75 0.8
% of unlabelled data
Accuracy ALBL
RAND UNCERTAIN PSDS QUIRE
sonar
QUIREBest
5 10 15 20 25 30 35 40 45 50 55 60 0.5
0.55 0.6 0.65 0.7 0.75
% of unlabelled data
Accuracy ALBL
RAND UNCERTAIN PSDS QUIRE
diabetes
• no single best strategyfor every data set
—choosing needed
• proposedALBLconsistentlymatches the best
—similar findings across other data sets
ALBL: effective inmaking intelligent choices
H.-T. Lin (NTU) ML for Modern AI 27/38
ML Research for Modern AI
Discussion for Statisticians
weighted training accuracy 1t Pt τ =1
1
pτ qynτ =g(t)(xnτ)y as reward
• is rewardunbiased estimatorof test performance?
no for learned g(t) (yes for fixed g)
• is reward fixedbefore playing?
no because g(t)learned from (xnt,ynt)
• is rewardindependent of each other?
no because past history all in reward
—ALBL: tools from statistics +wild/unintended usage
‘application intelligence’ outcome:
open-source toolreleased
(https://github.com/ntucllab/libact)
ML Research for Modern AI
Lessons Learned from
Research on Active Learning by Learning
by DFID - UK Department for International Development;
licensed under CC BY-SA 2.0 via Wikimedia Commons
1 Is Statistics the same as ML or AI?
• does it really matter?
• Modern AI should embraceevery useful tool from other fields.
2 scalability bottleneckof ‘application intelligence’:
choiceof methods/models/parameter/. . .
3 think outside of themathbox:
‘unintended’ usage may begood enough
4 important to bebraveyetpatient
• idea: 2012
• paper:(Hsu and Lin, AAAI 2015); software:(Yang et al., 2017)
H.-T. Lin (NTU) ML for Modern AI 29/38
ML Research for Modern AI
Tropical Cyclone Intensity Estimation
ML Research for Modern AI
Experienced Meteorologists Can ‘Feel’ and Estimate Tropical Cyclone Intensity from Image
Can ML do the same/better?
• lack ofML-ready datasets
• lack ofmodel that properly utilizes domain knowledge issues addressed in our latest works
(Chen et al., KDD 2018) (Chen et al., Weather & Forecasting 2019)
H.-T. Lin (NTU) ML for Modern AI 31/38
ML Research for Modern AI
Flow behind Our Proposed Model
TC images
ML
estimationintensityhuman learning/
analysis
domain knowledge
(HI)
CNN polar
rotation invariance
current weather
system
is proposedCNN-TCbetter than current weather system?
ML Research for Modern AI
Results
RMS Error
ADT 11.75
AMSU 14.40
SATCON 9.66 CNN-TC 9.03
CNN-TC much betterthan current weather system (SATCON)
why are peoplenot using thiscool ML model? :-)
H.-T. Lin (NTU) ML for Modern AI 33/38
ML Research for Modern AI
Lessons Learned from
Research on Tropical Cyclone Intensity Estimation
1 again,cross-domain collaborationimportant e.g. even from ‘organizing data’ to be ML-ready
2 not easy to claimproduction ready
—can ML be used for ‘unseenly-strongTC’?
3 good AI system requiresboth human and machine learning
—still an ‘art’ to blend the two
ML for Future AI
Outline
ML for (Modern) AI
ML Research for Modern AI
ML for Future AI
H.-T. Lin (NTU) ML for Modern AI 35/38
ML for Future AI
AI: Now and Next
2010–2015 AI becomes promising, e.g.
• initial success of deep learningon ImageNet
• mature tools for SVM (LIBSVM) and others
2016–2020 AI becomes competitive, e.g.
• super-human performance of alphaGoand others
• all big technology companies becomeAI-first
2021–
AI becomes necessary
• “You’ll not be replaced by AI, butby humans who know how to use AI”
(Sun, Chief AI Scientist of Appier, 2018)
ML for Future AI
Needs of ML for Future AI
more creative win humanrespect e.g. Appier’s 2018 work on
design matching clothes
(Shih et al., AAAI 2018)
more explainable win humantrust e.g. my students’
work on
automatic bridge bidding
(Yeh et al., IEE ToG 2018)
more interactive win humanheart e.g. my student’s work (w/ DeepQ) on efficient disease diagonsis
(Peng et al., NeurIPS 2018)
H.-T. Lin (NTU) ML for Modern AI 37/38
ML for Future AI
Summary
• ML for (Modern) AI:
tools + human knowledge ⇒easy-to-use application
• ML Research for Modern AI:
need to bemore open-minded
—in methodology, in collaboration, in KPI
• ML for Future AI:
crucial to be ‘human-centric’
Thank you! Questions?