1 00:00:01,060 --> 00:00:04,780 In this lecture, we will understand the concept of a very good. 2 00:00:06,740 --> 00:00:14,610 We have been saying they know that a cell in the Convolutional did get information from a set of big 3 00:00:14,610 --> 00:00:22,010 cells or a set of cells in the previously, for example, that red cell in the Convolutional. 4 00:00:22,010 --> 00:00:27,290 It is getting information from these nine cells and this writer, Daniel. 5 00:00:29,550 --> 00:00:30,810 But what does this mean? 6 00:00:32,190 --> 00:00:35,580 How is it getting the information from all these pixels? 7 00:00:36,960 --> 00:00:39,080 We have 25 pixels here. 8 00:00:40,440 --> 00:00:48,630 And our cell here can have only one value, which should be the representative value for these 25 pixels. 9 00:00:50,340 --> 00:00:56,700 So we need to find a way to convert these 25 values of pixels into one value. 10 00:00:58,550 --> 00:01:07,320 This is done by using a feed filter is a matrix of same dimensions as our window of receptive feed. 11 00:01:08,730 --> 00:01:11,580 So if the window is five Crossfade. 12 00:01:12,570 --> 00:01:14,950 Think that is also a dimension five. 13 00:01:14,990 --> 00:01:15,460 CROSSFIRE. 14 00:01:17,050 --> 00:01:21,790 If it is up three close three feet, there will also be of three across three dimensions. 15 00:01:24,870 --> 00:01:33,690 No, we have a window of five into five pixels containing pixel value and we have a five in two five 16 00:01:34,560 --> 00:01:36,870 matrix containing some values. 17 00:01:39,000 --> 00:01:43,860 We multiply each pixel value with the corresponding filter value. 18 00:01:45,280 --> 00:01:47,500 And add all of these products up. 19 00:01:49,540 --> 00:01:51,370 So the pixel value hit. 20 00:01:53,500 --> 00:02:00,760 Will be multiplied with zero point for the next pixel value will be multiplied with zero point three. 21 00:02:01,120 --> 00:02:01,750 And so on. 22 00:02:02,770 --> 00:02:05,850 And all these products will be added to. 23 00:02:07,610 --> 00:02:09,620 This will give us one number. 24 00:02:10,370 --> 00:02:15,230 And this number will represent information in these 25 pixels. 25 00:02:18,190 --> 00:02:23,310 Now the question comes, how do we decide the values and district that? 26 00:02:25,290 --> 00:02:27,360 The answer to this is very pleasing. 27 00:02:28,290 --> 00:02:30,330 We do not have to decide these values. 28 00:02:31,600 --> 00:02:34,370 I'd network will learn these values also. 29 00:02:35,620 --> 00:02:39,610 So when we are training our model, these values will be self-reliant. 30 00:02:43,330 --> 00:02:50,290 Now to demonstrate how it does work and how they are able to extract certain features out. 31 00:02:51,900 --> 00:02:54,990 I have taken a five into five foot image. 32 00:02:56,510 --> 00:03:01,670 With zero one type pixel values and a three by three feet that. 33 00:03:05,690 --> 00:03:06,680 Look at the speed that. 34 00:03:07,810 --> 00:03:10,600 This figure looks like a cross. 35 00:03:11,810 --> 00:03:16,610 That is the diagonal values are one and the other are Z2. 36 00:03:18,600 --> 00:03:24,280 If we use this figure with a straight up one, we get this output. 37 00:03:27,570 --> 00:03:30,720 The D.A. below shows you how we get this output. 38 00:03:33,020 --> 00:03:40,040 How the picture values are multiplied and their product values are added up to good first value. 39 00:03:40,610 --> 00:03:44,020 Then the next value and then the next and so on. 40 00:03:49,370 --> 00:03:54,800 This final output, which we get after applying, if we get is called a feature map. 41 00:03:56,630 --> 00:04:05,110 A feature map, because each way that highlights some feature of the input image, the images on the 42 00:04:05,110 --> 00:04:10,780 right are demonstrating how particular features are highlighted by Fragos. 43 00:04:12,870 --> 00:04:21,330 For example, if we use a vertical feet, that that is the middle column of this matrix is one one one, 44 00:04:22,470 --> 00:04:24,990 and these side columns are zero zero zero. 45 00:04:27,100 --> 00:04:31,150 This type of thing that transforms the image to this image. 46 00:04:33,350 --> 00:04:40,580 Notice that vertical white lanes are enhanced and the rest of the image is blurred. 47 00:04:42,810 --> 00:04:45,870 Similarly, if we use the horizontal for that. 48 00:04:47,130 --> 00:04:50,230 That is this middle role will be one one, one. 49 00:04:52,800 --> 00:04:56,310 And top and bottom row will consist of Zeitels. 50 00:04:57,870 --> 00:05:00,060 If we use such a horizontal filter. 51 00:05:01,180 --> 00:05:02,260 We got this image. 52 00:05:03,610 --> 00:05:09,460 You can notice that horizontal white lines are highlighted and the rest is blurred. 53 00:05:11,980 --> 00:05:13,450 This is what Peter does. 54 00:05:14,760 --> 00:05:20,910 A fate that is a set of values which transforms the window by doing some of products. 55 00:05:22,520 --> 00:05:29,180 What we get after the playing of that is called a feature map, each feature map has some particular 56 00:05:29,180 --> 00:05:30,400 feature highlighted. 57 00:05:33,320 --> 00:05:37,770 So what we will do is we will use many types of quader. 58 00:05:38,810 --> 00:05:44,600 So that each filter creates different feature maps containing different features. 59 00:05:46,340 --> 00:05:51,560 This means our convolutional live is going to be a bundle of feature maps. 60 00:05:52,870 --> 00:05:56,470 And each region map has some particular highlighted feature. 61 00:05:57,910 --> 00:06:01,870 Important thing to notice here is what happens in the next lit. 62 00:06:03,390 --> 00:06:04,650 So this cell. 63 00:06:05,640 --> 00:06:09,000 In the first feature map of Convolutional led to. 64 00:06:10,260 --> 00:06:11,250 What does this seat. 65 00:06:12,310 --> 00:06:17,280 Is it only this rectangle on the first feature map of previously? 66 00:06:18,250 --> 00:06:22,500 Or this rectangle on all feature maps in the previously. 67 00:06:24,410 --> 00:06:32,210 The answer is that each sale on Convolutional leered two will be getting information of all the featured 68 00:06:32,210 --> 00:06:34,070 maps and the previously. 69 00:06:35,610 --> 00:06:43,050 Because only then can these cells combine the different features to find more high level features. 70 00:06:46,050 --> 00:06:47,870 Let's summarize again for clarity. 71 00:06:49,280 --> 00:06:55,130 We apply a filter on the previous list of data to extract features. 72 00:06:58,100 --> 00:07:01,730 The output after a playing field is called a feature map. 73 00:07:03,490 --> 00:07:08,710 We apply many different types of windows to extract many different types of features. 74 00:07:09,920 --> 00:07:12,710 This gives us a bundle of feature maps. 75 00:07:14,660 --> 00:07:18,480 The first Bundalong feature maps is called Convolutional Leered One. 76 00:07:21,860 --> 00:07:26,210 Congressional leered to Volks on these extracted features. 77 00:07:27,530 --> 00:07:30,110 To extract even higher level features. 78 00:07:33,670 --> 00:07:36,670 Next, we are going to discuss about the input layer. 79 00:07:38,250 --> 00:07:41,690 Input, it also has multiple layers of information. 80 00:07:42,790 --> 00:07:44,390 These layers are called Jenelle's. 81 00:07:44,950 --> 00:07:47,290 We talk about tunnels in the next video.