WEBVTT 00:02.720 --> 00:03.370 Hey, everyone. 00:03.740 --> 00:07.970 So there are some few things related to course I would like to discuss in this video. 00:08.480 --> 00:12.740 So I would highly suggest you please, please do not skip this video. 00:13.280 --> 00:18.980 This video will give you a complete overview of what we are going to exactly learn in this course. 00:19.790 --> 00:22.550 And there are some few important things related to course. 00:22.580 --> 00:24.010 I will discuss later on. 00:24.830 --> 00:25.190 All right. 00:25.490 --> 00:30.620 So we'll get started of our journey with a very basic introduction. 00:31.100 --> 00:33.140 And I'll be white and I'll be full, sir. 00:33.170 --> 00:35.060 What are the different applications of an LP? 00:35.690 --> 00:39.920 And then no much theory will just tape dive into installation. 00:41.000 --> 00:44.330 So we'll see how to get started on Google. 00:44.330 --> 00:44.840 Carl Levin, what? 00:44.840 --> 00:54.350 I mean, mainly data, two libraries, which will be our focus, a special library for an LP and an 00:54.350 --> 00:54.820 antique. 00:55.310 --> 01:01.130 So in the next section, we will see some of the basic natural language processing related tasks and 01:01.190 --> 01:08.720 all those tasks like a tokenization stemming limitations, stop 40 moil vocabulary, part of speech, 01:08.720 --> 01:11.930 tagging, everything we will see with this special library. 01:12.530 --> 01:14.930 And this particular cause is very much hands on. 01:15.290 --> 01:19.160 So there are many practical projects on which we are going to work upon. 01:19.610 --> 01:22.460 So one of them is a spam classification. 01:22.610 --> 01:28.030 Then whether a restaurant reviews production will be a good or bad Amazon. 01:28.790 --> 01:31.850 Hi Emily B Yelp Review Classification Project. 01:32.510 --> 01:34.730 And then we will see two more projects. 01:34.790 --> 01:41.600 Actually, one of them is a automated text summarisation and Twitter sentiment analysis. 01:41.840 --> 01:48.230 So that is mainly our very first part of the course where mainly we are going to work up on. 01:49.380 --> 01:50.890 Machine learning related technique. 01:51.120 --> 01:57.210 And we'll be applying this machine learning technique on the top of this tax data in the next part of 01:57.210 --> 01:59.800 this course, or I would say a second part of this course. 02:00.150 --> 02:03.490 Our main focus will be on a deep learning part. 02:04.050 --> 02:06.810 So we'll start with the basics of deep learning. 02:06.990 --> 02:10.470 And for deep learning basics, fight with me, my friend. 02:10.530 --> 02:12.180 Veejays going to join with you. 02:13.480 --> 02:14.990 We learn about avoid inbreeding. 02:15.490 --> 02:17.800 We learn about how to do this. 02:17.920 --> 02:22.780 Text classification with advance deep learning technique like a neural network. 02:22.980 --> 02:24.190 A recurrent neural network. 02:24.940 --> 02:27.220 And there is a one full fledged project. 02:27.310 --> 02:32.140 We will see like automated text generation with pensive look at us. 02:32.270 --> 02:33.050 Anna, LSD. 02:33.940 --> 02:40.360 And for those of you who just want to refresh their concept related to data science and data processing 02:40.720 --> 02:41.680 data analysis. 02:42.010 --> 02:49.500 So for them there are three Bonnar section IO Edik like Numpty Library, Pendas Library and Immaculately 02:49.600 --> 02:50.920 Library Chris course. 02:51.490 --> 02:55.300 And then in the appendix, hieratic a text processing. 02:55.360 --> 03:02.350 So whenever you want to deal with any kind of filing a patent or tax, filing, a patent video, filing 03:02.350 --> 03:04.210 a patent, how to deal with that. 03:04.660 --> 03:07.540 So that part is included in the appendix. 03:07.810 --> 03:14.010 So overall, I can say that it's a very comprehensive cause, complete causes for of practicals only. 03:14.560 --> 03:16.410 And this is about the basic cause. 03:16.520 --> 03:17.050 Or what do you.