Machine Learning Department School of Computer Science ...
[Pages:55]10-601 Introduction to Machine Learning
Machine Learning Department School of Computer Science Carnegie Mellon University
PAC Learning +
Midterm Review
Matt Gormley Lecture 15
March 7, 2018
1
ML Big Picture
Learning Paradigms:
What data is available and when? What form of prediction?
? supervised learning ? unsupervised learning ? semi-supervised learning ? reinforcement learning ? active learning ? imitation learning ? domain adaptation ? online learning ? density estimation ? recommender systems ? feature learning ? manifold learning ? dimensionality reduction ? ensemble learning ? distant supervision ? hyperparameter optimization
Theoretical Foundations:
What principles guide learning? q probabilistic
q information theoretic q evolutionary search
q ML as optimization
Application Areas Key challenges? NLP, Speech, Computer Vision, Robotics, Medicine, Search
Problem Formulation: What is the structure of our output prediction?
boolean
Binary Classification
categorical
Multiclass Classification
ordinal
Ordinal Classification
real
Regression
ordering
Ranking
multiple discrete Structured Prediction
multiple continuous (e.g. dynamical systems)
both discrete & cont.
(e.g. mixed graphical models)
Facets of Building ML Systems:
How to build systems that are robust, efficient, adaptive, effective?
1. Data prep
2. Model selection
3. Training (optimization / search)
4. Hyperparameter tuning on validation data
5. (Blind) Assessment on test data
Big Ideas in ML:
Which are the ideas driving development of the field? ? inductive bias ? generalization / overfitting ? bias-variance decomposition ? generative vs. discriminative ? deep nets, graphical models ? PAC learning ? distant rewards
2
LEARNING THEORY
3
Questions For Today
1. Given a classifier with zero training error, what can we say about generalization error? (Sample Complexity, Realizable Case)
2. Given a classifier with low training error, what can we say about generalization error? (Sample Complexity, Agnostic Case)
3. Is there a theoretical justification for regularization to avoid overfitting? (Structural Risk Minimization)
4
PAC/SLT mPoAdeCls/fSorLSTuMperovidseedlLearning
Data Source
Distribution D on X
Learning Algorithm
Expert / Oracle
Labeled Examples
(x1,c*(x1)),..., (xm,c*(xm))
Alg.outputs
h : X ! Y
x1 > 5
x6 > 2
+1
+1
-1
c* : X ! Y
+ + +
+ -- -
-
6
Slide from Nina Balcan
Two Types of Error
True Error (aka. expected risk) Train Error (aka. empirical risk)
7
PAC / SLT Model
8
Three Hypotheses of Interest
9
................
................
In order to avoid copyright disputes, this page is only a partial summary.
To fulfill the demand for quickly locating and searching documents.
It is intelligent file search solution for home and business.
Related download
- computing slater rankings using duke computer science
- ranking the schools best undergraduate engineering programs
- ranking wily people who rank each other
- top 20 computer science programs in america
- historical ranking of carnegie mellon among universities
- research notebook computational computer science
- school of computer science scs carnegie mellon university
- beyond independent relevance methods and evaluation
- machine learning department school of computer science
- ranking in heterogeneous networks with geo location
Related searches
- high school computer science curriculum
- high school computer science projects
- list of computer science topics
- benefits of computer science degree
- history of computer science pdf
- fundamentals of computer science pdf
- benefits of computer science career
- benefits of computer science education
- doctor of computer science salary
- examples of computer science math
- list of computer science journals
- examples of computer science projects