Title: Machine Learning
1(No Transcript)
2The CSE 471
Commercial
- Listening non-stop for 150min per week, for 16
weeks - 4000 (your tuition)..
- Catching up on your beauty sleep in the class
- 300 (chairs not very comfy)
- Redoing the in class exam at home
- 300 (lost family time)
- Keeping up with the 17,578,940 billion bytes of
email/blog - 20 (skimming cost) 1000 (Brain frying cost)
- Spending most of your life these last four months
hacking lisp or doing home works or writing blog
comments for CSE 471 - Priceless
????
What is Stockholm Syndrome and why is it
relevant to CSE471?
3Announcements
- Final homework due today solutions will be
posted by tomorrow - Participation sheet to be filled and returned
today - CEAS Evaluations online. https//intraweb.eas.asu.
edu/eval - Do take part!
- Final exam choice
- In Class (on Tuesday 5/12 9501140AM)
- Take-home (will be given out before the weekend,
and will be due by Tuesday 5/12) - Dont take..
4Take-home vs. In-class
- In-class
- Gets done fastat most 2 hours of pain
- Gets graded fasteasy to grade blank sheets ?
- Take-home
- Doesnt get done fast (You may spend a lot of
time doing it) - Doesnt get graded fastpeople tend to put up a
fight and fill pages ?
5Announcements
- Final/Take home will be released by Wed/Thu
(check your mail and also homepage) - Will be set like an in-class exam (must be
answered on the exam sheet) - But you get to do it at home (or milk of kindness
overfloweth..) - Wed office hours will be held
- Review session needed?
- CEAS Evaluations online. https//intraweb.eas.asu.
edu/eval - Do take part!
- Comments on TA/Tutor performance can be sent to
me using the class anonymous mail facility (or
written up in CEAS evals) - Today
- Learning completed (Perceptron learning until
1130) - Interactive review (113012)
- Summary of what is not done (5min)
6What we did
- Week 6 KR Prop logic
- Week 7 prop logic
- Week 1 Intro Intelligent agent design RN Ch
1, Ch 2 - Week 2 Problem Solving Agents RN Ch 3
3.1--3.5 - Week 3 Informed search RN Ch 3 3.1--3.5
- Week 4 CSPs and Local SearchRN Ch 5.1--5.3 Ch
4 4.3 - Week 5 Local Search and Propositional LogicRN
Ch 4 4.3 Ch 7.1--7.6 - Week 6 Propositional Logic --gt Plausible
reasoningRN Ch 7.1--7.6 ch 13 13.1--13.5
- Week 7 Representations for Reasoning with
Uncertaintych 13 13.1--13.5 - Week 8 Bayes Nets Specification Inferencech
13 13.1--13.5 - Week 9 Bayes Nets Inferencech 13 13.1--13.5
(Here is a fully worked out example of variable
elimination) - Week 10 Sampling methods for Bayes net
Inference First-order logic startch 13.5 - Week 11 Unification, Generalized Modus-Ponens,
skolemization and resolution refutation. - Week 12 Reasoning with change?Planning
- Week 13 Planning, MDPs Gametree search
- Week 14 Learning
7Representation Mechanisms Logic (propositional
first order) Probabilistic logic
Learning the models
Search Blind, Informed Planning Inference
Logical resolution Bayesian inference
How the course topics stack up
8Learning
Dimensions What can be learned? --Any of
the boxes representing the agents
knowledge --action description, effect
probabilities, causal relations in the
world (and the probabilities of
causation), utility models (sort of through
credit assignment), sensor data
interpretation models What feedback is
available? --Supervised, unsupervised,
reinforcement learning --Credit
assignment problem What prior knowledge is
available? -- Tabularasa (agents head is
a blank slate) or pre-existing knowledge
9Chapters Covered
- Table of Contents (Full Version)
- Preface (html) chapter map Part I
Artificial Intelligence 1 Introduction
2 Intelligent Agents Part II Problem
Solving 3 Solving Problems by Searching
4 Informed Search and Exploration 5
Constraint Satisfaction Problems 6
Adversarial Search Part III Knowledge and
Reasoning 7 Logical Agents 8
First-Order Logic 9 Inference in
First-Order Logic 10 Knowledge
Representation Part IV Planning 11 Planning
(pdf) 12 Planning and Acting in the Real
World
- Part V Uncertain Knowledge and Reasoning 13
Uncertainty 14 Probabilistic Reasoning
15 Probabilistic Reasoning Over Time 16
Making Simple Decisions 17 Making Complex
Decisions Part VI Learning 18 Learning from
Observations 19 Knowledge in Learning
20 Statistical Learning Methods 21
Reinforcement Learning Part VII Communicating,
Perceiving, and Acting 22 Communication
23 Probabilistic Language Processing 24
Perception 25 Robotics Part VIII
Conclusions 26 Philosophical Foundations
27 AI Present and Future
10It matters not what you cover, but what you
uncover
A Farside treasury
11Rao I could've taught more...I could've taught
more, if I'd just...I could've taught
more... Yunsong Rao, there are thirty people
who are mad at you because you taught too much.
Look at them.Rao If I'd made more time...I
wasted so much time, you have no idea. If I'd
just...Yunsong There will be generations (of
bitter people) because of what you did.Rao I
didn't do enough.Yunsong You did so much.Rao
This slide. We couldve removed this slide. Why
did I keep the slide? Two minutes, right there.
Two minutes, two more minutes.. This music, a bit
on reinforcement learning. This review. Two
points on bagging and boosting. I could easily
have made two for it. At least one. I couldve
gotten one more point across. One more. One more
point. A point, Yunsong. For this. I could've
gotten one more point across and I didn't. ?
12With understanding comes a sense of loss.
--Marvin Minsky
Here is hoping you too experienced a sense of
loss this semester