Template Presentation Support 0
×

250

Views

 1 : Self-improvement for dummies(Machine Learning) COS 116, Spring 2010 Adam Finkelstein
 2 : Artificial Intelligence Definition of AI (Merriam-Webster): The capability of a machine to imitate intelligent human behavior Branch of computer science dealing with the simulation of intelligent behavior in computers Definition of Learning: To gain knowledge or understanding of or skill in by study, instruction, or experience Today: Later:
 3 : Today’s lecture: Machine Learning Machine learning = “Programming by example” Show the computer what to do, without explaining how to do it. The computer programs itself! In fact, continuous improvement via more data/experience.
 4 : Recall your final Scribbler lab Task: Program Scribbler to navigate a maze. Avoid walls, avoid “lava”, head towards the goal. As maze becomes more complex, programming becomes much harder. (Why?)
 5 : Program Scribbler to navigate a maze Program Teach Scribbler to navigate a maze Start with a simple program: Run the maze. Label this trial GOOD or BAD, depending on whether goal was reached. Submit data from the trial to a “learning algorithm”, which uses it to devise a better program. Repeat as needed. Is this how you learned to drive a car?
 6 : Note: imitating nature may not be best Examples: Birds Airplanes vs Cheetahs Race cars vs
 7 : Machine’s “experience” of the world n sensors, each produces a number: “experience” = an array of n numbers Example: video camera: 480 x 640 pixels n = 480 ? 640 = 307200 In practice, reduce n via some processing
 8 : Example: Representing wood samples Brownness scale 1 … 10 Texture scale 1 … 10 (3, 7) = wood that is fairly light brown but kind of on the rough side light dark smooth rough
 9 : A learning task and its mathematical formulation Given: 100 samples of oak, maple Figure out labeling(“clustering”) Given a new sample, classify it as oak, maple… oak maple “Clustering” New point
 10 : An algorithm to produce 2 clusters Some notions: Mean of k points (x1, y1), (x2, y2), ... , (xk, yk) is (“center of gravity”) Distance between points (x1, y1), (x2, y2) is ( (x1 – x2)2 + (y1 – y2)2 )½
 11 : 3-means Algorithm (cont.) Start by randomly picking 3 data points as your “means” Repeat many times: { Assign each point to the cluster whose mean is closest to it Compute means of the clusters } http://en.wikipedia.org/wiki/K-means_clustering
 12 : What about learning a more complicated object? Speech? Motion? Handwriting? Similar datarepresentations, but more “dimensions”
 13 : One major idea: modeling uncertainty using probabilities Example: Did I just hear “Ice cream” or “I scream”? Assign probability ½ to each Listen for subsequent phoneme _?_ “is”: use knowledge of usage patterns… Increase probability of “Ice cream” to 0.9
 14 :
 15 : Spam filtering How would you define Spam to a computer? Descriptive approach: “Any email in ALL CAPS, unless it’s from my kid brother, or that contains the word ‘mortgage’, unless it’s from my real estate agent, …” Difficult to come up with an good description! Learning approach: “Train” the computer with labeled examples of spam and non-spam (a.k.a. ham) email. Easy to find examples of spam – you probably get hundreds a day!
 16 : Spam Filtering Given: A spam corpus and ham corpus. Goal: Determine whether a new email is spam or ham. Step 1: Assign a “spam score” to each word: Fspam(word) = Fraction of emails in spam corpus that contain word. Fham(word) = Fraction of emails in ham corpus that contain word. Observe: SpamScore(word) > 1 if word is more prevalent in spam. SpamScore(word) < 1 if word is more prevalent in ham.
 17 : Spam Filtering Step 2: Assign a “spam score” to the email: SpamScore(email) = SpamScore(word1) x … x SpamScore(wordn), where wordi is the ith word in email. Observe: SpamScore(email) >> 1 if email contains many spammy words. SpamScore(email) << 1 if email contains many hammy words. Step 3: Declare email to be spam if SpamScore(email) is high
 18 : Spam Filtering Advantages of this type of spam filter: Though simple, catches 90+% of spam! No explicit definition of spam required. Customized for your email. Adaptive – as spam changes, so does filter
 19 : Text synthesis (simplistic version) Idea: Use example text to generate similar text. Input: 2007 State of the Union Address. Output: “This war is more competitive by strengthening math and science skills. The lives of our nation was attacked, I ask you to make the same standards, and a prompt up-or-down vote on the work we've done and reduce gasoline usage in the NBA.”
 20 : Text synthesis How it works: Output one word at a time. Let (v, w) be the last two words outputted. Find all occurrences of (v, w) in the input text. Of the words following the occurrences of (v, w), output one at random. Repeat. Variants: Last k words instead of last 2 words.
 21 : Handwriting recognition [LeCun et al, AT&T, 1998] The LeNet-5 system Trained on a database: 60,000 handwritten digits Reads ~10% of all checks cashed in the US
 22 : Handwriting recognition: LeNet-5 Can recognize weird styles:
 23 : Handwriting recognition: LeNet-5 Can handle stray marks and deformations: Mistakes are usually ambiguous anyway:
 24 : Aside: How to get large amounts of data? (major problem in ML) Answer 1: Use existing corpuses (lexis-nexis, WWW for text) Answer 2: Create new corpuses by enlisting people in fun activities. (Recall Image-Labeling Game in Lab 1)
 25 : Example: SAT Analogies Bird : Feathers :: Fish : ____ Idea: Search web to learn relationships between words. [Turney 2004] Example: Is the answer above “water” or “scales”? Most common phrases on the web: “bird has feathers”, “bird in air”, “fish has scales”, “fish in water”. Conclusion: Right answer is “scales”.
 26 : SAT Analogies [Turney 2004] On a set of 374 multiple-choice SAT analogies, this approach got 56% correct. High-school seniors on the same set: 57% (!) Mark of “Scholastic Aptitude”?
 27 : Image labeling [Blei et al, 2003] Another solution: Learn captions from examples. System trained on a Corel database 6,000 images with captions. Applied to images without captions. Princeton prof!
 28 :
 29 : Helicopter flight [Abbeel et al 2005] Idea: Algorithm learns to pilot a helicopter by observing a human pilot. Results: Even better than the human pilot.