Lecture 1: Introduction to the Course EECS 545: Machine Learning - PDF document

Lecture 1: Introduction to the Course EECS 545: Machine Learning Benjamin Kuipers EECS 545: Machine Learning • Professor Benjamin Kuipers – 647-6887, kuipers@umich.edu – Office hours: TTh 2:00 - 3:00, CSE 3741 • GSI: Gyemin Lee – gyemin@eecs.umich.edu – Office hours: MW 1:00 - 2:30, EECS 2420 1

Who is Benjamin Kuipers? • This is my first semester at Michigan. – University of Texas at Austin, 1985 - 2008 – MIT, 1984 - 1985 – Tufts University, 1978 - 1984 – MIT, 1972 - 1978; PhD, 1977 – Harvard University, 1970 - 1972 – Swarthmore College, 1966 - 1970; BA, 1970. – Ann Arbor High School, 1963 - 1966 Who is Benjamin Kuipers? • Research on representation and use of commonsense knowledge. – Modeling the cognitive map of large-scale space • Critical role of the topological map – Robot exploration and mapping • Concept of distinctive state – Qualitative reasoning about physical systems • QSIM algorithm for qualitative simulation – Learning from uninterpreted sensors and effectors • Bootstrap learning from pixels to high-level concepts 2

What is Machine Learning? • Learning, done by a machine! – That is, learning well enough understood that we can formally describe the process and implement it as an algorithm. • It’s a branch of artificial intelligence. – The problem of understanding the mind as a computation, and how a physical system can have a mind. What is Learning? • Learning facts about the world . – French explorers enter Michigan in 1621. – University of Michigan established 1817. – Michigan becomes a state in 1837. • • • • • Collecting facts is relatively superficial, but still raises significant problems. – Q: What is the knowledge representation? 3

What is Learning? • Learning facts about the world . – French explorers enter Michigan in 1621. – University of Michigan established 1817. – Michigan becomes a state in 1837. • Spanish explorers enter Texas in 1519. • Texas independence from Mexico 1836. • Texas becomes a state in 1845. • University of Texas established 1883. • Collecting facts is relatively superficial, but still raises significant problems. – Q: What is the knowledge representation? What is Learning? • Learning to classify observations . – Classifying observed plants or animals – Diagnosing diseases from symptoms and tests – Identifying faces in images • • • Supervised learning: given a training set – {feature vectors plus classifications} – learn to classify new instances – Q: What are the best features? 4

What is Learning? • Learning skilled action . – Learning to balance, and walk, then run. – Learning to ride a bicycle. • • • Reinforcement learning: – given a reward signal – learn sequences of actions to maximize discounted future reward. – Q: Where does the reward signal come from? What is Learning? • Learning useful categories and features . – Dogs are more similar to other dogs than to cats. – Retrievers resemble other retrievers. – Chihuahuas resemble other chihuahuas. • • • Unsupervised learning: – Clustering by similarity defines categories. – Features that discriminate well are useful. – Dimensionality reduction to a few features. – Q: Which categories and features are useful? 5

How does a baby (human or robot) get knowledge of its own? • The baby, assailed by eyes, ears, nose, skin, and entrails at once, feels it all as one great blooming, buzzing confusion … – [William James, 1890] • How does it get high-level concepts? – Places, paths, objects, actions, plans, etc. – Foundational domains: space, time, . . . Our Gedankenexperiment • Consider a baby robot, a learning agent , born with uninterpreted sensors and effectors – We pretend that evolutionary learning is done by the individual, not by the species. • The baby has only pixel-level experience: – Disorganized collection of sensor elements – Incremental motor signals • How does it learn object-level concepts? – Places, paths, objects, actions, etc. – The macro-scale components of adult knowledge 6

Here’s the platform I want! • But here’s what we have … Lassie “sees” the world with a Laser Rangefinder • 180 ranges over 180 ° planar field of view • About 13” above the ground plane • 10-12 scans per second 7

Laser Rangefinder Image • 180 narrow beams at 1º intervals. Disorganized Sensor: 180 “Pixels” 8

Structured Sensor Array The Egocentric Range Image 9

The World-Centered Range Image The World-Centered Range Image 10

Image History in 2D Histogram Statistical Learning Methods Used • Correlation (time-series and histograms) • k -means and agglomerative clustering • Multidimensional scaling • Dimensionality reduction (PCA, Isomap) • Sensory flow • Image matching (ICP) • Markov localization (max likelihood pose) • . . . 11

Objects as Explanations • A static model explains most observations. – So focus on the discrepancies • Cluster in space; Track over time • Merge images to make shape models – Modayil & Kuipers [2004, 2006, 2007, 2008]. Identify Dynamic Sensor Returns 12

Clustering into Objects Track Objects over Time 13

Describe the Scene • Describe the scene in terms of: – Static world – Robot’s own pose – Object in a fixed position – Object and trajectory • Individual objects Learning Object Shapes • Merge range scans to get shape models • Cluster shapes to get object categories 14

Learning Object Categories • Clustering shapes by perceptual features Learn about Actions • Learn actions to affect objects. Learn: – Qualitative description of effect – Bounds on prerequisite state – Control law to perform the action • For a mobile robot that can move and push: – Move to desired point in nearby space. – Turn to face object. – Push (Move, to get object to move also) 15

Learn about Actions • Learn action properties. Simple planning. From Pixels to Concepts • Learn high-level concepts by identifying structure in the pixel stream. – Space is learned as a minimal explanation for sensory correlations. – Objects are learned as a minimal explanation for discrepancies from fixed-value model – Actions are learned as minimal descriptions of motions interacting with objects – Plans combine actions to achieve goals. • What are the methods for doing this? 16

EECS 545: Machine Learning • The purpose is to learn these methods. – Statistical learning from Bishop. – Reinforcement learning from Sutton & Barto. • Reading and lectures cover the Theory part. – Homework problems are an important part. – Do them, and grade them, in groups. – Presentations to the class. • Programming projects cover the Practice part. – Each person submits their own projects. – Help each other learn and do the projects. Work Together • Help each other learn the material. – Read and discuss it with each other. – Catch and correct each other’s mistakes. – Don’t let someone avoid learning. – Think like a teacher! • We will form groups. – Do your homework (blue or black pencil or pen). – Correct someone else’s homework (red pen). – Hand it in (for a completion grade). 17

Programming Projects • Applying machine learning to a problem: – In Theory there’s no difference between theory and practice. – But in Practice , there is. • We’re going to learn to find and describe objects in a stream of video input. – Individual projects. – Help each other succeed. Understanding Video Input • Video: a high-density stream of pixels. – The viewer imposes an interpretation. – How? (exploit redundancy) • Build a model of static background (#1). • Individuate and track foreground objects (#2). • Stabilize variations in static background (#3). • Build models of foreground objects (#4). 18

Traffic Video; Fixed Camera Static Background 19

Foreground “Objects” Stabilize Hand-Held Camera 20

Open Issues • Collect your own videos and test your methods. • More complex pixel models for #1, to handle waving branches, etc. – Read Stauffer & Grimson, PAMI , 2000. • How can we learn that shadows in #2 are not parts of objects? • #3 is essentially a SLAM problem (Simultaneous Localization And Mapping). – How can we focus attention on informative features? • Need a new video for #4, to make object modeling a 2D problem (tractable), rather than a 3D problem (too hard). Plan for Class Sessions • Each class is 80 minutes: 12:10 - 1:30 pm – 30-40 minutes for my lecture – 20-30 minutes for student presentation • Need volunteers for next Tuesday and Thursday! – 20-30 minutes to discuss projects • Attend every class session. And exams: – Mid-term: February 19 (12:00 - 1:30 pm). – Final exam: April 30 (1:30 - 3:30 pm). 21

Now Form Groups! • Each group should have 2-4 students. – Make sure your schedules are compatible! • Submit a sheet for each group. – Names, phones, and emails for all members. – Keep copies for yourselves. • Volunteers to present problem solutions next Tuesday and Thursday. – (These should be easier.) 22