Main content
Computer science
Course: Computer science > Unit 1
Lesson 1: Intro to algorithmsWhat is an algorithm and why should you care?
Current time:0:00Total duration:5:28
Want to join the conversation?
To get started, your account must be at least 3 days old, have a verified email address, and have at least 5,000 energy points.
No posts yet.
Video transcript
- [Voiceover] What is an algorithm? One definition might be a set of steps to accomplish a task. You might have an algorithm for getting from home to school, for making a grilled cheese sandwich, or for finding what you're
+looking for in a grocery store. In computer science, an
+algorithm is a set of steps for a computer program
+to accomplish a task. Algorithms put the science
+in computer science. And finding good algorithms
+and knowing when to apply them will allow you to write
+interesting and important programs. Let's talk about a few famous algorithms. How does Google Hangouts
+transmit live video across the Internet so quickly? They use audio and video
+compression algorithms. How does Google Maps figure out how to get from Dallas, Texas to Orlando, Florida so that you can get to Disney World? They use a route finding algorithm. How does Pixar color a
+3D model of a character based on the lighting in a virtual room? They use a rendering algorithm. How does Nasa choose how
+to arrange the solar panels on the International Space Station and when to rearrange them? They use an optimization
+and a scheduling algorithm. Those algorithms are more complex than our everyday algorithms like making a grilled cheese sandwich. But they boil down to the same thing, a set of steps to accomplish a task. If you know something
+about existing algorithms, you can save yourself some effort and make your programs faster by applying the right one. For example, let's say
+that you're writing a game and you want the user to be able to play against the computer. Well, you could look at
+checkers games for inspiration. Computer scientists have
+figured out how to write checkers programs that never lose by using the minimax search algorithm to search through the huge
+tree of possible moves. If your game is similar to checkers, then you might be able to use algorithms based on these techniques. If not, then knowing the
+limitations of those algorithms might lead you to redesign your game if it requires having a
+skilled computer player. It's also important to know
+how to design new algorithms as well as how to analyze their
+correctness and efficiency. In the biological sciences, new algorithms are
+continually being designed with purposes like designing
+the molecular structures that are the core of
+disease fighting drugs. In physics, algorithms simulate climate and weather patterns. In other algorithms, search
+and analyze the vast data about stars in the
+universe that's collected by automated space telescopes. Across all the sciences,
+and even on websites like Khan Academy, efficient
+algorithms are needed to analyze huge data sets
+or to select intelligently from a vast number of possible decisions. In just about any area
+you might be interested, new algorithms will allow
+massive computational power to be harnessed to do things
+that people really need and care about. Now, not all algorithms are created equal. So what makes a good algorithm? The two most important criteria are that it solves a problem and that it does so efficiently. Most of the time, we want an algorithm to give us an answer that
+we know is always correct. Sometimes we can live with an algorithm that doesn't give us the correct
+answer or the best answer because the only perfect algorithms that we know for those problems take a really, really long time. For example, let's say we want a program that would determine
+the most efficient route for a truck that delivers packages, starting and ending the day at a depot. It would take weeks to run going through all the possibilities. But if we're okay with a program that would determine a route that's good but maybe not the best, then it could run in seconds. In some case, good is good enough. How do you measure the
+efficiency of an algorithm? We could time how long
+it takes to run the code, but that would only tell
+us about that particular implementation in a certain
+programming language on a particular computer and just for the input it was given. Instead, computer
+scientists use a technique called asymptotic analysis, which allows algorithms to
+be compared independently of a particular programming
+language or hardware so that we can conclusively say that yes, some algorithms are more
+efficient than others. Now you can learn about algorithms and asymptotic analysis on Khan Academy thanks to the contribution
+of two Dartmouth college professors. Tom Cormen is the first author of the most popular
+college algorithms textbook in the world, plus the author of Algorithms Unlocked. Devin Balkcom designed
+Dartmouth's intro CS course and researches robotics. He built the world's first
+origami folding robot. Tom and Devin will teach
+you many of the algorithms that you would learn in APCS or CS 101, like searching algorithms,
+sorting algorithms, recursive algorithms
+and my personal favorite, graph algorithms. There will be tons of
+interactive visualizations, quizzes and coding challenges to help you understand better along your learning journey.