1
00:00:00,810 --> 00:00:08,040
Welcome to the course on constitutional neural networks where you will learn both the theoretical concepts

2
00:00:08,190 --> 00:00:17,520
behind a CNN model as well as the implementation of deep learning models for image recognition.

3
00:00:17,520 --> 00:00:23,970
My name is Ivy shake and along with my CO instructor grudge I will be leading you through this course

4
00:00:25,620 --> 00:00:32,730
as instructors of courses have over two hundred fifty thousand enrolments worldwide.

5
00:00:32,850 --> 00:00:40,710
We both call engineering and MBA degrees and have experience of data analytics consulting industry while

6
00:00:40,710 --> 00:00:42,080
doing our jobs.

7
00:00:42,120 --> 00:00:49,830
We realized that many data analysts and beginners in the field of machine learning feel a barrier in

8
00:00:49,830 --> 00:00:57,320
learning CNN models and believe that the mathematics in all is overwhelming.

9
00:00:57,330 --> 00:01:01,260
We have designed this course for such students.

10
00:01:01,260 --> 00:01:09,690
We will cover everything up practicing data scientist needs to know from concepts to court without getting

11
00:01:09,810 --> 00:01:12,970
too mathematical about it.

12
00:01:13,110 --> 00:01:21,660
If you put one hour a day regularly within a week you will be able to make CNN based image recognition

13
00:01:21,660 --> 00:01:27,670
models and answer CNN related interview questions.

14
00:01:27,690 --> 00:01:35,660
We start this course by setting up python in your system and doing a crash course in Python.

15
00:01:35,730 --> 00:01:40,940
If you are familiar with these languages you can even skip this part.

16
00:01:41,230 --> 00:01:48,540
Then we understand and be a simple deep learning model with multi level pass approach which is used

17
00:01:48,540 --> 00:01:54,180
for simple classification tasks with these foundations.

18
00:01:54,240 --> 00:02:01,320
We then understand convolution and neural networks and see how they outperform simple neural network

19
00:02:01,320 --> 00:02:03,240
models and imagine condition.

20
00:02:05,220 --> 00:02:14,200
Lastly we build a complete end to end project where we classify colored images and achieve accuracy

21
00:02:14,270 --> 00:02:18,930
is as high as 97 percent.

22
00:02:18,930 --> 00:02:25,650
It has been proven that our curriculum provides solid inclusion to even those professionals who do not

23
00:02:25,650 --> 00:02:29,640
have a strong mathematical background.

24
00:02:29,670 --> 00:02:38,940
The ideal student for this course is a data analyst who wants to expand on the current skills of a student

25
00:02:39,150 --> 00:02:44,330
who wants to have a career in data sciences and machine learning.

26
00:02:44,850 --> 00:02:52,690
The prerequisite for learning and implementing convolution and neural networks are two.

27
00:02:52,720 --> 00:03:01,450
The first is having an understanding of simple and models and secondly knowledge of the software tool.

28
00:03:01,950 --> 00:03:07,650
We have tried to cover both of these and this goes so that you do not have to look for separate courses

29
00:03:07,740 --> 00:03:08,340
for these.

30
00:03:10,320 --> 00:03:17,400
If you have any query or draw toward the course you can post them in the discussion forum.

31
00:03:17,400 --> 00:03:24,030
I will be personally solving all your doubts so feel free to have a look at the course description and

32
00:03:24,030 --> 00:03:25,950
we look forward to seeing you insight.