reveal.js/media/Machine Learning Explained in 100 Seconds [PeMlggyqz0Y].tsv

1	start	end	text
2	0	6480	Machine learning. Teach a computer how to perform a task, without explicitly programming it to perform said task.
3	6620	13420	Instead, feed data into an algorithm to gradually improve outcomes with experience, similar to how organic life learns.
4	13580	20400	The term was coined in 1959 by Arthur Samuel at IBM, who was developing artificial intelligence that could play checkers.
5	20540	26880	Half a century later, and predictive models are embedded in many of the products we use every day, which perform two fundamental jobs.
6	38600	43280	The first step in the process is to acquire and clean up data. Lots and lots of data.
7	43480	47780	The better the data represents the problem, the better the results. Garbage in, garbage out.
8	47900	52160	The data needs to have some kind of signal to be valuable to the algorithm for making predictions.
9	52160	59920	And data scientists perform a job called feature engineering to transform raw data into features that better represent the underlying problem.
10	60240	64240	The next step is to separate the data into a training set and testing set.
11	64460	71800	The training data is fed into an algorithm to build a model, then the testing data is used to validate the accuracy or error of the model.
12	71980	77700	The next step is to choose an algorithm, which might be a simple statistical model like linear or logistic regression,
13	77940	81260	or a decision tree that assigns different weights to features in the data.
14	81260	86640	Or you might get fancy with a convolutional neural network, which is an algorithm that also assigns
15	86640	91300	weights to features, but also takes the input data and creates additional features automatically.
16	91640	96300	And that's extremely useful for datasets that contain things like images or natural language,
17	96420	99020	where manual feature engineering is virtually impossible.
18	99260	103960	Every one of these algorithms learns to get better by comparing its predictions to an error function.
19	116220	121780	Python is the language of choice among data scientists, but R and Julia are also popular options,
20	121920	125320	and there are many supporting frameworks out there to make the process approachable.
21	125500	132680	The end result of the machine learning process is a model, which is just a file that takes some input data in the same shape that it was trained on,
22	132860	136900	then spits out a prediction that tries to minimize the error that it was optimized for.
23	136900	141980	It can then be embedded on an actual device or deployed to the cloud to build a real-world product.
24	142180	144500	This has been Machine Learning in 100 Seconds.
25	144580	147160	Like and subscribe if you want to see more short videos like this,
26	147320	150500	and leave a comment if you want to see more machine learning content on this channel.
27	150620	153040	Thanks for watching, and I will see you in the next one.