1 / 33

Machine learning

Machine learning. Image source: https://www.coursera.org/course/ml. Machine learning. Definition Getting a computer to do well on a task without explicitly programming it Improving performance on a task based on experience. Learning for episodic tasks.

basil
Download Presentation

Machine learning

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Machine learning Image source: https://www.coursera.org/course/ml

  2. Machine learning • Definition • Getting a computer to do well on a task without explicitly programming it • Improving performance on a task based on experience

  3. Learning for episodic tasks • We have just looked at learning in sequential environments • Now let’s consider the “easier” problem of episodic environments • The agent gets a series of unrelated problem instances and has to make some decision or inference about each of them

  4. Example: Image classification input desired output apple pear tomato cow dog horse

  5. Learning for episodic tasks • We have just looked at learning in sequential environments • Now let’s consider the “easier” problem of episodic environments • The agent gets a series of unrelated problem instances and has to make some decision or inference about each of them • In this case, “experience” comes in the form of training data

  6. Training data apple • Key challenge of learning: generalization to unseen examples pear tomato cow dog horse

  7. Example 2: Spam filter

  8. Example 3: Seismic data classification Earthquakes Surface wave magnitude Nuclear explosions Body wave magnitude

  9. The basic machine learning framework y = f(x) • Learning: given a training set of labeled examples{(x1,y1), …, (xN,yN)}, estimate the parameters of the prediction function f • Inference: apply f to a never before seen test examplex and output the predicted value y = f(x) output classification function input

  10. Naïve Bayes classifier A single dimension or attribute of x

  11. Decision tree classifier Example problem: decide whether to wait for a table at a restaurant, based on the following attributes: • Alternate: is there an alternative restaurant nearby? • Bar: is there a comfortable bar area to wait in? • Fri/Sat:is today Friday or Saturday? • Hungry: are we hungry? • Patrons: number of people in the restaurant (None, Some, Full) • Price: price range ($, $$, $$$) • Raining: is it raining outside? • Reservation: have we made a reservation? • Type: kind of restaurant (French, Italian, Thai, Burger) • WaitEstimate: estimated waiting time (0-10, 10-30, 30-60, >60)

  12. Decision tree classifier

  13. Decision tree classifier

  14. Nearest neighbor classifier f(x) = label of the training example nearest to x • All we need is a distance function for our inputs • No training required! Training examples from class 2 Test example Training examples from class 1

  15. Linear classifier • Find a linear function to separate the classes f(x) = sgn(w1x1 + w2x2 + … + wDxD) = sgn(w  x)

  16. Perceptron Input Weights x1 w1 x2 w2 Output:sgn(wx+ b) x3 w3 . . . wD xD

  17. Linear separability

  18. Multi-Layer Neural Network • Can learn nonlinear functions • Training: find network weights to minimize the error between true and estimated labels of training examples: • Minimization can be done by gradient descent provided f is differentiable • This training method is called back-propagation

  19. Differentiable perceptron Input Weights x1 w1 x2 w2 Output:(wx+ b) x3 w3 . . . Sigmoid function: wd xd

  20. NY Times article YouTube video

  21. NY Times article

  22. Unsupervised Learning • Deep learning relies a lot on unsupervised learning • Idea: Given only unlabeled data as input, learn some sort of structure • The objective is often more vague or subjective than in supervised learning. This is more of an exploratory/descriptive data analysis

  23. Unsupervised Learning • Clustering • Discover groups of “similar” data points

  24. Unsupervised Learning • Quantization • Map a continuous input to a discrete (more compact) output 2 1 3

  25. Unsupervised Learning • Dimensionality reduction, manifold learning • Discover a lower-dimensional surface on which the data lives

  26. Unsupervised Learning • Density estimation • Find a function that approximates the probability density of the data (i.e., value of the function is high for “typical” points and low for “atypical” points) • Can be used for anomaly detection

  27. Other types of learning • Semi-supervised learning:lots of data is available, but only small portion is labeled (e.g. since labeling is expensive) • Why is learning from labeled and unlabeled data better than learning from labeled data alone? ?

  28. Other types of learning • Active learning: the learning algorithm can choose its own training examples, or ask a “teacher” for an answer on selected inputs S. Vijayanarasimhan and K. Grauman, “Cost-Sensitive Active Visual Category Learning,” 2009

  29. Structured Prediction Word Image Source: B. Taskar

  30. Structured Prediction Parse tree Sentence Source: B. Taskar

  31. Structured Prediction Word alignment Sentence in two languages Source: B. Taskar

  32. Structured Prediction Bond structure Amino-acid sequence Source: B. Taskar

  33. Structured Prediction • Many image-based inference tasks can loosely be thought of as “structured prediction” model Source: D. Ramanan

More Related