1Chapter 4 (Part 3):Artificial Neural NetworksCS 536: Machine LearningLittman (Wu, TA)Artificial Neural Networks[Read Ch. 4][Review exercises 4.1, 4.2, 4.5, 4.9, 4.11]• Threshold units [ok]• Gradient descent [ok]• Multilayer networks [ok]• Backpropagation [ok]• Hidden layer representations [ok]• Example: Face Recognition [today]• Advanced topics [today]2Face RecognitionTypical input images• 90% accurate learning head pose,and recognizing 1-of-20 faces3Learned Weightshttp://www.cs.cmu.edu/tom/faces.htmlw0 w1 w2 w3For left, strt, rght, upAlternative Error FunctionsPenalize large weights:E(w) ≡ 1/2 Sd in D Sk in outputs (tkd-okd)2 + g Sij wji2Train on target slopes as well as values:Tie together weights:• e.g., in phoneme recognition network4Recurrent NetworksUnfolding: BPTT5Another Good QuestionEx. 4.6Project MethodologyLots of good ideas for algorithms anddomains.The hard question is: “How will youevaluate it?”Ultimately, you need to present more thanone algorithm (and perhaps more thanone problem) and you’ll need some wayof saying what worked better.What’s the gold standard?6Simple Project IdeaTake an interesting datasetCompare several learning approachesfor prediction• decision trees• ANNs• instance-based methods• SVMs• boostingTraining/Testing DataGetting labeled data is hard. Ideas:• association: use some features to predictothers. Example: spelling correction.• prediction: use past features to predictfuture.• existing data: UCI repository• natural labels: newswire categories• automatic checker: answer is tricky, butknow if you’re right.• artificial data: generator has a known rule7DatasetsWeather prediction dataSensor data: http://www.greatduckisland.net/Don Smith has log data on dialup usage(use weather, day, time, …)Other log data: network usage, CPU usageGPS data (campus buses, my car)Vision data (score a goal)Bio dataText ClassificationEasy to get lots of text: web, TRECdata, emailPredict topic, authorship, sentiment,style, affect, attitude.8Reinforcement LearningPersonal favoriteCan be challenging to do well: generatedata or direct control• Optimize gas well production• Object tracking• “Tag” grid world• Rover control• animal behavior experimentsCompare approaches (direct policy search,value function learning, model-based, …)Active LearningTake a classic dataset.Explore the tradeoff between size oftraining set and generalization.Devise schemes for choosing items to“pay” for labels to maximizeaccuracy with minimum cost.9Theory StuffAny interest? I’m inclined tointroduce instance-based methodsnext (Ch.
View Full Document
Unlocking...