Intro Flashcards
3 practical goals of ML
1) Reduce Time to write programs
2) Customize and scale Products
3) Solve Problems that you can’t solve with traditional approach
Example of ML Reducing Time ?
Spell Checker. Instead of explicitly programming rules (i. before e etc) you provide data.
Example of ML Customizing Products ?
Spell Checker in different languages. Traditionally you’d have to start over with each language
Example of ML Solving Problems tough to approach with traditional programming.
Facial and Speech recognition.
Why is ML better at solving complex problems ?
Don’t need to tell the algorithm what to do, only need to show algorithm examples.
ML from a Philosophic perspective ?
Changes the way you think about a problem. Traditional software engineers trained to think logically and mathematically. ML shifts that from a mathematical scientist to a natural science.
How does ML shift from a mathematical/logical approach ?
Natural Science. Making observations about an uncertain world. Running experiments and using statistic, not logic, to analyze the results of the experiment.