WEBVTT 00:00.120 --> 00:01.120 Welcome back. 00:01.120 --> 00:04.000 Now let's learn about machine learning. 00:04.120 --> 00:12.200 Machine learning is a subfield of artificial intelligence, which is defined as the capability of a 00:12.200 --> 00:21.080 machine to simulate intelligent human behavior and to perform complex tasks in a manner that is similar 00:21.080 --> 00:24.720 to the way humans solve problems. 00:24.760 --> 00:33.240 To understand machine learning, you need to know the algorithms that drive the opportunities of machine 00:33.240 --> 00:36.040 learning and its limitations. 00:36.080 --> 00:44.520 In general, machine learning algorithms are used in a wide range of applications like fraud detection, 00:44.560 --> 00:52.880 computer vision, autonomous vehicle predictive analytics where it is not computationally feasible to 00:52.920 --> 01:00.640 develop conventional algorithms that meet the requirements of real time and predictive nature of work. 01:00.920 --> 01:09.510 Now, let's deep dive into the machine learning and why it's different from traditional programming. 01:09.630 --> 01:13.870 In traditional programming, you give the computer strict rules. 01:13.870 --> 01:16.990 If it's a circle, then it's a ball. 01:16.990 --> 01:24.310 So you get data and program, give it to the computer, and the computer give you the output. 01:24.470 --> 01:25.670 This is the coding. 01:25.710 --> 01:26.590 Simple coding. 01:26.590 --> 01:27.750 Simple program. 01:27.950 --> 01:31.750 If it's a circle, go and label it as a ball. 01:31.950 --> 01:37.630 While in machine learning you give the computer examples and answers. 01:37.630 --> 01:41.430 Show many pictures labeled ball or not ball. 01:41.430 --> 01:49.190 For example, uh, you give it the data and output to the computer, and the computer figures out the 01:49.190 --> 01:50.670 rules itself. 01:50.870 --> 02:01.790 So you you give the computer circles and, and, uh, and images for balls and not balls, for example, 02:01.830 --> 02:08.550 a computer, uh, keyboard, mouse images of many objects. 02:08.550 --> 02:12.910 And tell the computer that those are not balls. 02:12.950 --> 02:13.470 Okay. 02:13.710 --> 02:18.870 So the computer will recognize and figure out the rules itself. 02:19.070 --> 02:25.350 So if you give it another object, it will detect if it is a ball or not. 02:25.470 --> 02:32.550 So the idea here is giving the computer examples and answers. 02:32.590 --> 02:34.710 Examples and data. 02:34.710 --> 02:45.110 And the computer will generate the rule itself from Netflix recommendations and Amazon Alexa to self-driving 02:45.110 --> 02:48.190 cars and your photo applications. 02:48.190 --> 02:49.550 Image recognition. 02:49.750 --> 02:55.310 ML is rapidly becoming part of our daily lives. 02:55.510 --> 03:02.910 Instead of hard coding every possibility, we show the computer thousands of examples. 03:03.230 --> 03:14.350 It looks for patterns and builds its own model to make predictions or decisions on new data it has never 03:14.350 --> 03:15.510 seen before. 03:15.750 --> 03:18.230 Think of it like teaching a child. 03:18.230 --> 03:27.780 Machine learning is a branch of artificial intelligence that focuses on developing models and algorithms 03:27.780 --> 03:34.820 that let computers learn from data without being explicitly programmed for every task. 03:34.940 --> 03:44.340 In simple words, ML teaches the systems to think and understand like a human by learning from the data. 03:44.500 --> 03:45.980 ML algorithms. 03:46.100 --> 03:53.140 Machine learning algorithms are used in a wide range of applications. 03:53.260 --> 03:59.860 We talked about fraud detections, computer vision, autonomous vehicle predictive analytics where it 03:59.860 --> 04:05.980 is not computationally feasible to develop conventional algorithms that meet the requirements of real 04:06.020 --> 04:09.100 time and predictive nature of work. 04:09.220 --> 04:17.260 Also, machine learning in marketing can help you better understand customers for tailored campaigns 04:17.260 --> 04:24.420 in sales, ML can predict customer behavior and personalize the customer experience at scale. 04:24.460 --> 04:30.540 In the next video, we're gonna talk about the real life ML example.