1 00:00:00,510 --> 00:00:07,080 Let's start from the top with what is machine learning while machine learning is broad. 2 00:00:07,250 --> 00:00:13,650 It contains many different aspects and you'll see many different definitions of it online. 3 00:00:13,760 --> 00:00:19,640 But for the sake of this course we're going to keep it practical in a single sentence. 4 00:00:19,640 --> 00:00:26,090 Machine learning is using an algorithm or computer program to learn about different patterns in data 5 00:00:26,750 --> 00:00:33,890 and then taking that algorithm and what it's learned to make predictions about the future using similar 6 00:00:33,890 --> 00:00:41,430 data machine learning algorithms are also called models and we'll use the term interchangeably throughout 7 00:00:41,430 --> 00:00:48,330 the course how machine learning algorithms differ from normal algorithms and computer programs is the 8 00:00:48,330 --> 00:00:50,100 learning aspect. 9 00:00:50,370 --> 00:00:57,780 Let's use an example where a normal algorithm could be a set of instructions such as how to turn a pile 10 00:00:57,780 --> 00:01:02,170 of raw ingredients into your favorite honey mustard chicken dish. 11 00:01:02,520 --> 00:01:08,220 The set of instructions might start out by saying first come up the vegetables then season the chicken 12 00:01:08,340 --> 00:01:15,240 then preheat the oven etc. And if you follow these steps correctly you'll end up with your favorite 13 00:01:15,450 --> 00:01:17,880 honey mustard chicken dish. 14 00:01:17,940 --> 00:01:20,000 That's making me hungry actually. 15 00:01:20,760 --> 00:01:21,360 We'll get back to it. 16 00:01:21,900 --> 00:01:29,070 What's important to note here is you started with an input your set of ingredients and a set of instructions 17 00:01:29,310 --> 00:01:32,490 on what to do to get to your favorite dish. 18 00:01:32,520 --> 00:01:39,450 What happens with a machine learning algorithm is instead of starting with an input and a set of instructions. 19 00:01:39,570 --> 00:01:43,490 You start with an input and ideal output. 20 00:01:43,620 --> 00:01:49,310 In our case the ingredients is the input and the output is our favorite chicken dish. 21 00:01:49,500 --> 00:01:55,680 And what a machine learning algorithm does is it looks at the input the raw ingredients and then it 22 00:01:55,680 --> 00:01:57,660 looks at the output. 23 00:01:57,660 --> 00:02:05,640 The favorite chicken dish and it tries to figure out the set of instructions in between these two now 24 00:02:05,650 --> 00:02:06,910 think about this. 25 00:02:07,000 --> 00:02:12,220 If you tried to do this on your first try you might not get great results. 26 00:02:12,400 --> 00:02:15,740 You might put in too much spice and the dishes come out far too hot. 27 00:02:15,970 --> 00:02:21,040 When you second try and you get a little closer but when it comes to machine learning sometimes there 28 00:02:21,040 --> 00:02:28,700 may be hundreds thousands or tens of thousands of these combinations of inputs and outputs. 29 00:02:28,840 --> 00:02:34,870 If you looked at the set of ingredients and ideal outputs your favorite chicken dish 100 plus times 30 00:02:35,350 --> 00:02:40,930 you'd probably get pretty good or pretty close to figuring out what the set of instructions are to make 31 00:02:40,930 --> 00:02:48,320 that dish now we're missing out a few steps here but this is what machine models do in a nutshell. 32 00:02:48,320 --> 00:02:56,020 They find patterns collected in data so we can use those patterns for future problems in our chicken 33 00:02:56,020 --> 00:03:01,900 dish example a machine learning algorithm might find a way to create a delicious chicken dish given 34 00:03:01,900 --> 00:03:03,230 the right ingredients. 35 00:03:03,460 --> 00:03:09,580 That way instead of thinking about what dish we could make with what's in the fridge the machine learning 36 00:03:09,580 --> 00:03:17,400 algorithm tells us you want to be thinking Hey I've heard about data analysis and data science as well. 37 00:03:17,620 --> 00:03:19,520 How are all these different. 38 00:03:19,870 --> 00:03:21,730 Great question. 39 00:03:21,730 --> 00:03:27,760 Data analysis is looking at a set of data and gaining an understanding of it by comparing different 40 00:03:27,760 --> 00:03:33,980 examples different features and making visualizations like graphs for our example. 41 00:03:34,000 --> 00:03:39,340 This might be looking at different samples of ingredients and comparing them to all the ingredients 42 00:03:39,340 --> 00:03:45,370 have in common are some of the missing something which have the most of a certain type of thing. 43 00:03:45,740 --> 00:03:53,050 Data science is running experiments on a set of data with the hopes of finding actionable insights within 44 00:03:53,050 --> 00:03:54,100 it. 45 00:03:54,100 --> 00:03:58,930 One of these experiments may be to build a machine learning model. 46 00:03:59,050 --> 00:04:04,780 This model might look at 10000 different sets of ingredients and 10000 different chicken dishes. 47 00:04:04,780 --> 00:04:10,320 Then tell us based on a set of new ingredients that we have which chicken dish. 48 00:04:10,420 --> 00:04:18,190 These ingredients are most likely to make you can consider data analysis and machine learning as a part 49 00:04:18,280 --> 00:04:20,170 of data science. 50 00:04:20,200 --> 00:04:26,230 Don't worry if all of this seems unclear for now by the end of this course you'll have had plenty of 51 00:04:26,230 --> 00:04:31,170 hands on experience with all of these before the next lesson. 52 00:04:31,200 --> 00:04:35,640 Take a minute to think about an example of a set of instructions you followed before. 53 00:04:35,640 --> 00:04:41,640 Do you think if you were showing the inputs and the end goal of something enough times you could work 54 00:04:41,640 --> 00:04:44,330 backwards and figure out the instructions it took to get there.