Self-improvement for dummies
Short summary:
Self-improvement. for dummies. (Machine Learning). COS 116. 4/23/2007. Instructor: Umar Syed ... Idea: Use example text to generate similar text. ...
Long summary:
Self-improvement for dummies (Machine Learning) COS 116 4/23/2007 Instructor: Umar Syed Recall your final Scribbler lab Task: Program Scribbler to navigate a maze. Avoid walls, avoid “lava”, head towards the goal. Seemed simple. So why was this so challenging? Teach Scribbler to navigate a maze Start with a simple program: 1. Run the maze. 2. Label this trial GOOD or BAD, depending on whether goal was reached. 3. Submit data from the trial to a “learning algorithm”, which uses it to devise a better program. 4. Repeat as needed. Is this how you learned to drive a car? 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! 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! Machine Learning (ML): A subfield within Artificial Intelligence (AI). Algorithms that improve their performance with experience/data. Closely related to Data Mining. Data mining = Finding patterns and relationships in data. ML is not concerned with modeling human intelligence. Imitating nature may not be the best strategy anyway: Birds Airplanes vs Cheetahs Race cars vs Examples of Machine Learning Handwriting recognition [LeCun et al, AT&T, 1998] The LeNet-5 system Trained on a database of 60,000 handwritten digits. Reads about 10% of all the checks cashed in the USA. Handwriting recognition: LeNet-5 Can recognize weird styles: Handwriting recognition: LeNet-5 Can handle stray marks and deformations: Mistakes are usually ambiguous anyway ...
Source: www.cs.princeton.edu
Related
Files under this topic are not filed yet. Please use search bar to find other one
