![8
• Web search
• Computational
biology
• Finance
• E-commerce
• Space exploration
• Robotics
• Information
extraction
• Social networks
• Debugging software
• [Your favorite area]](https://image.slidesharecdn.com/launchingintomachinelearning-200701124922/85/Launching-into-machine-learning-8-320.jpg)
![[Farabet et al. ICML 2012, PAMI
2013]
19](https://image.slidesharecdn.com/launchingintomachinelearning-200701124922/85/Launching-into-machine-learning-19-320.jpg)
![A Typical Speech Recognition
System
ML used to predict of phone states from the sound
spectrogram
Deep learning has state-of-the-art
results
# Hidden Layers 1 2 4 8 10 12
Word Error Rate % 16.0 12.8 11.4 10.9 11.0 11.1
Baseline GMM performance = 15.4%
[Zeiler et al. “On rectified linear units for
speech recognition” ICASSP 2013]
21](https://image.slidesharecdn.com/launchingintomachinelearning-200701124922/85/Launching-into-machine-learning-21-320.jpg)
Launching into machine learning
- 1. Organizing Secretary Dr.R.Gunavathi, Head & Associate professor, PG & Research Department of Computer Applications PG & Research Department of Computer Applications organized IoT – Applications and Machine Learning
- 2. -By Sushama Assistant Professor (CSE) JECRC University
- 3. “Learning is any process by which a system improves performance from experience.” - Herbert Simon Definition by Tom Mitchell (1998): Machine Learning is the study of algorithms that • improve their performance P • at some task T • with experience E. A well-defined learning task is given by <P, T, E>. 3
- 5. ML is used when: • Human expertise does not exist (navigating on Mars) • Humans can’t explain their expertise (speech recognition) • Models must be customized (personalized medicine) • Models are based on huge amounts of data (genomics) Learning isn’t always useful: • There is no need to “learn” to calculate payroll 5
- 7. 7 • Recognizing patterns: – Facial identities or facial expressions – Handwritten or spoken words – Medical images • Generating patterns: – Generating images or motion sequences • Recognizing anomalies: – Unusual credit card transactions – Unusual patterns of sensor readings in a nuclear power plant • Prediction: – Future stock prices or currency exchange rates
- 8. 8 • Web search • Computational biology • Finance • E-commerce • Space exploration • Robotics • Information extraction • Social networks • Debugging software • [Your favorite area]
- 9. “Machine Learning: Field of study that gives computers the ability to learn without being explicitly programmed.” -Arthur Samuel (1959) 9
- 10. 10 Improve on task T, with respect to performance metric P, based on experience E T: Playing checkers P: Percentage of games won against an arbitrary opponent E: Playing practice games against itself T: Recognizing hand-written words P: Percentage of words correctly classified E: Database of human-labeled images of handwritten words T: Driving on four-lane highways using vision sensors P: Average distance traveled before a human-judged error E: A sequence of images and steering commands recorded while observing a human driver. T: Categorize email messages as spam or legitimate. P: Percentage of email messages correctly classified. E: Database of emails, some with human-given labels
- 11. 11
- 12. • Nevada made it legal for autonomous cars to drive on roads in June 2011 • As of 2013, four states (Nevada, Florida, California, and Michigan) have legalized autonomous cars Penn’s Autonomous Car (Ben Franklin Racing Team) 12
- 13. 13
- 14. Laser Terrain Mapping Stanley Learning from Human Drivers Sebastian Adaptive Vision Pat h Plannin g Images and movies taken from Sebastian Thrun’smultimedia w1e4bsite.
- 15. 15
- 16. pixels edges object parts (combination of edges) object models 16
- 17. 17
- 18. Trained on 4 classes (cars, faces, motorbikes, airplanes). Second layer: Shared- features and object- specific features. Third layer: More specific features. 18
- 19. [Farabet et al. ICML 2012, PAMI 2013] 19
- 20. Input images Samples from feedforward Inference (control) Samples from Full posterior inference Generating posterior samples from faces by “filling in”experiments (cf. Lee and Mumford, 2003). Combine bottom-up and top-down inference. Slide credit: Andrew 20
- 21. A Typical Speech Recognition System ML used to predict of phone states from the sound spectrogram Deep learning has state-of-the-art results # Hidden Layers 1 2 4 8 10 12 Word Error Rate % 16.0 12.8 11.4 10.9 11.0 11.1 Baseline GMM performance = 15.4% [Zeiler et al. “On rectified linear units for speech recognition” ICASSP 2013] 21
- 22. Slide credit: Li Deng, MS 22
- 23. 23
- 24. • Supervised (inductive) learning – Given: training data + desired outputs (labels) • Unsupervised learning – Given: training data (without desired outputs) • Semi-supervised learning – Given: training data + a few desired outputs • Reinforcement learning – Rewards from sequence of actions 24
- 25. • Given (x1, y1), (x2, y2), ..., (xn, yn) • Learn a function f(x) to predict y givenx – y is real-valued == regression 9 8 7 6 5 4 3 2 1 0 1970 1980 1990 2000 2010 2020 SeptemberArcticSeaIce Extent(1,000,000sq km) 26
- 26. • Given (x1, y1), (x2, y2), ..., (xn, yn) • Learn a function f(x) to predict y givenx – y is categorical == classification Breast Cancer (Malignant / Benign) 1(Malignant) 0(Benign) Tumor Size 27
- 27. 28 • Given (x1, y1), (x2, y2), ..., (xn, yn) • Learn a function f(x) to predict y givenx – y is categorical == classification Breast Cancer (Malignant / Benign) 1(Malignant) 0(Benign) Tumor Size Tumor Size
- 28. 29 • Given (x1, y1), (x2, y2), ..., (xn, yn) • Learn a function f(x) to predict y given x – y is categorical == classification Breast Cancer (Malignant / Benign) 1(Malignant) 0(Benign) Tumor Size Predict Benign Predict Malignant Tumor Size
- 29. Tumor Size Ag e - Clump Thickness - Uniformity of Cell Size - Uniformity of Cell Shape … • x can be multi-dimensional – Each dimension corresponds to an attribute 30
- 30. • Given x1, x2, ..., xn (without labels) • Output hidden structure behind the x’s – E.g., clustering 31
- 31. Genes Individuals Genomics application: group individuals by genetic similarity 32
- 32. Organize computing clusters Social network analysis Image credit: NASA/JPL-Caltech/E. Churchwell (Univ. of Wisconsin, Madison) Astronomical data analysisMarket segmentation 33
- 33. 34 • Independent component analysis – separate a combined signal into its original sources
- 34. 35 • Independent component analysis – separate a combined signal into its original sources
- 35. 36 • Given a sequence of states and actions with (delayed) rewards, output a policy – Policy is a mapping from states actions that tells you what to do in a given state • Examples: – Credit assignment problem – Game playing – Robot in a maze – Balance a pole on your hand
- 36. 37 Agent and environment interact at discrete timesteps Agent observes state at step t: st S : t 0, 1, 2, K produces action at step t : at A(st ) gets resulting reward : and resulting next state : rt1 st 1 . . . st at rt +1 st +1 at +1 rt +2 st+2 at +2 rt +3 st +3 . . . at +3
- 37. 38
- 38. 39 • Learn policy from user demonstrations
- 39. 40
- 40. • Choose the training experience • Choose exactly what is to be learned – i.e. the target function • Choose how to represent the target function • Choose a learning algorithm to infer the target function from the experience Environment/ Experience Learner Knowledge Performance Element Training data Testing data 41
- 41. • We generally assume that the training and test examples are independently drawn from the same overall distribution of data – We call this “i.i.d” which stands for “independent and identically distributed” • If examples are not independent, requires collective classification • If test distribution is different, requires transfer learning 42
- 42. • Tens of thousands of machine learning algorithms – Hundreds new every year • Every ML algorithm has three components: – Representation – Optimization – Evaluation 43
- 43. 44 • Numerical functions – Linear regression – Neural networks – Support vector machines • Symbolic functions – Decision trees – Rules in propositional logic – Rules in first-order predicate logic • Instance-based functions – Nearest-neighbor – Case-based • Probabilistic Graphical Models – Naïve Bayes – Bayesian networks – Hidden-Markov Models (HMMs) – Probabilistic Context Free Grammars (PCFGs) – Markov networks
- 44. 45 • Gradient descent – Perceptron – Backpropagation • Dynamic Programming – HMM Learning – PCFG Learning • Divide and Conquer – Decision tree induction – Rule learning • Evolutionary Computation – Genetic Algorithms (GAs) – Genetic Programming (GP) – Neuro-evolution
- 45. 47 • Accuracy • Precision and recall • Squared error • Likelihood • Posterior probability • Cost / Utility • Margin • Entropy • K-L divergence etc.
- 46. • Understand domain, prior knowledge, and goals • Data integration, selection, cleaning, pre- processing, etc. • Learn models • Interpret results • Consolidate and deploy discovered knowledge Loop 48
- 47. 49 • Learning can be viewed as using direct or indirect experience to approximate a chosen target function. • Function approximation can be viewed as a search through a space of hypotheses (representations of functions) for one that best fits a set of training data. • Different learning methods assume different hypothesis spaces (representation languages) and/or employ different search techniques.
- 48. 50
- 49. 51 • 1950s – Samuel’s checker player – Selfridge’s Pandemonium • 1960s: – Neural networks: Perceptron – Pattern recognition – Learning in the limit theory – Minsky and Papert prove limitations of Perceptron • 1970s: – Symbolic concept induction – Winston’s arch learner – Expert systems and the knowledge acquisition bottleneck – Quinlan’s ID3 – Michalski’s AQ and soybean diagnosis – Scientific discovery with BACON – Mathematical discovery with AM
- 50. 52 • 1980s: – Advanced decision tree and rule learning – Explanation-based Learning (EBL) – Learning and planning and problem solving – Utility problem – Analogy – Cognitive architectures – Resurgence of neural networks (connectionism, backpropagation) – Valiant’s PAC Learning Theory – Focus on experimental methodology • 1990s – Data mining – Adaptive software agents and web applications – Text learning – Reinforcement learning (RL) – Inductive Logic Programming (ILP) – Ensembles: Bagging, Boosting, and Stacking – Bayes Net learning
- 51. 53 • 2000s – Support vector machines & kernel methods – Graphical models – Statistical relational learning – Transfer learning – Sequence labeling – Collective classification and structured outputs – Computer Systems Applications (Compilers, Debugging, Graphics, Security) – E-mail management – Personalized assistants that learn – Learning in robotics and vision • 2010s – Deep learning systems – Learning for big data – Bayesian methods – Multi-task & lifelong learning – Applications to vision, speech, social networks, learning to read, etc. – ???
- 52. 54 • Supervised learning – Decision tree induction – Linear regression – Logistic regression – Support vector machines & kernel methods – Model ensembles – Bayesian learning – Neural networks & deep learning – Learning theory • Unsupervised learning – Clustering – Dimensionality reduction • Reinforcement learning – Temporal difference learning – Q learning • Evaluation • Applications