Presentation is loading. Please wait.

Presentation is loading. Please wait.

Machine Learning Godfather to the Singularity. Traditional programming Machine learning Computer Data Program Output Computer Data Output Program.

Similar presentations


Presentation on theme: "Machine Learning Godfather to the Singularity. Traditional programming Machine learning Computer Data Program Output Computer Data Output Program."— Presentation transcript:

1 Machine Learning Godfather to the Singularity

2 Traditional programming Machine learning Computer Data Program Output Computer Data Output Program

3 Machine Learning Applications

4 Visual Search, Waterfalls User’s Query: System’s Response: Yes NO!User Feedback:

5 Example: Boundary Detection Is this a boundary?

6 Learning a classifier Given some set of features with corresponding labels, learn a function to predict the labels from the features xx x x x x x x o o o o o x2 x1

7 Sample Applications Web search Computational biology Finance E-commerce Space exploration Robotics Information extraction Social networks Debugging [Your favorite area]

8 Other Applications of ML The Google search engine uses numerous machine learning techniques – Spelling corrector: “spehl korector”, “phonitick spewling”, “Brytney Spears”, “Brithney Spears”, … – Grouping together top news stories from numerous sources (news.google.com)news.google.com – Analyzing data from over 3 billion web pages to improve search results – Analyzing which search results are most often followed, i.e. which results are most relevant

9 Other Applications of ML (cont’d) ALVINN, developed at CMU, drives autonomously on highways at 70 mph – Sensor input only a single, forward-facing camera

10 Other Applications of ML (cont’d) SpamAssassin for filtering spam Data mining programs for: – Analyzing credit card transactions for anomalies – Analyzing medical records to automate diagnoses Intrusion detection for computer security Speech recognition, face recognition Biological sequence analysis Each application has its own representation for features, learning algorithm, hypothesis type, etc.

11 How Do We Learn? HumanMachine Memorizek-Nearest Neighbors, Case-based learning Observe someone else, then repeat Supervised Learning, Learning by Demonstration Keep trying until it works (riding a bike) Reinforcement Learning 20 QuestionsDecision Tree Pattern matching (faces, voices, languages) Pattern Recognition Guess that current trend will continue (stock market, real estate prices) Regression

12 General Inductive Learning (Scientific Method) Hypothesis Observations Feedback, more observations Refinement Induction, generalization Actions, guesses

13 What is Machine Learning? Building machines that automatically learn from experience – Important research goal of artificial intelligence Applications: – Data mining programs that learn to detect fraudulent credit card transactions – Programs that learn to filter spam – Autonomous vehicles that learn to drive on public highways

14 Why use Machine Learning? We cannot write the program ourselves We don’t have the expertise (circuit design) We cannot explain how (speech recognition) Problem changes over time (packet routing) Need customized solutions (spam filtering)

15 Machine Learning Optimize a criterion (reach a goal) using example data or past experience Infer or generalize to new situations – Statistics: inference from a (small) sample – Probability: distributions and models – Computer Science: Algorithms: solve the optimization problem efficiently Data structures: represent the learned model

16 Slide: Erik Sudderth

17 Technologies Supervised learning – Decision tree induction – Inductive logic programming – Instance-based learning – Bayesian learning – Neural networks – Support vector machines (SVM) – Model ensembles – Learning theory Unsupervised learning – Clustering – Dimensionality reduction

18 Regression Methods k-Nearest Neighbors Support Vector Machines Neural Networks Bayes Estimator

19 Unsupervised Learning No labels or feedback Learn trends, patterns Applications – Customer segmentation: e.g., targeted mailings – Image compression – Image segmentation: find objects This course – k-means and EM clustering – Hierarchical clustering

20 Reinforcement Learning Learn a policy: sequence of actions Delayed reward Applications – Game playing – Balancing a pole – Solving a maze This course – Temporal difference learning

21 Hypothesis Type: Artificial Neural Network Designed to simulate brains “Neurons” (processing units) communicate via connections, each with a numeric weight Learning comes from adjusting the weights

22 Perceptron (Simple Neural Net) A single layer feed-forward network consists of one or more output neurons, each of which is connected with a weighting factor w ij to all of the inputs x i. xixi b b

23 Machine Learning vs. Expert Systems ES: Expertise extraction tedious; ML: Automatic ES: Rules might not incorporate intuition, which might mask true reasons for answer – E.g. in medicine, the reasons given for diagnosis x might not be the objectively correct ones, and the expert might be unconsciously picking up on other info – ML: More “objective”

24 Machine Learning vs. Expert Systems (cont’d) ES: Expertise might not be comprehensive, e.g. physician might not have seen some types of cases ML: Automatic, objective, and data-driven – Though it is only as good as the available data


Download ppt "Machine Learning Godfather to the Singularity. Traditional programming Machine learning Computer Data Program Output Computer Data Output Program."

Similar presentations


Ads by Google